Remote Sensing doi: 10.3390/rs16061073
Authors: Anastasia Zolotukhina Alexander Machikhin Anastasia Guryleva Valeria Gresis Anastasia Kharchenko Karina Dekhkanova Sofia Polyakova Denis Fomin Georgiy Nesterov Vitold Pozhar
Chlorophyll plays a crucial role in the process of photosynthesis and helps to regulate plants’ growth and development. Timely and accurate evaluation of leaf chlorophyll content provides valuable information about the health and productivity of plants as well as the effectiveness of agricultural treatments. For non-contact and high-performance chlorophyll content mapping in plants, spectral imaging techniques are the most widely used. Due to agility and rapid random-spectral-access tuning, acousto-optical imagers seem to be very attractive for the detection of vegetation indices and chlorophyll content assessment. This laboratory study demonstrates the capabilities of an acousto-optic imager for evaluation of leaf chlorophyll content in six crops with different biophysical properties: Ribes rubrum, Betula populifolia, Hibiscus rosa-sinensis, Prunus padus, Hordeum vulgare and Triticum aestivum. The experimental protocol includes plant collecting, reference spectrophotometric measurements, hyperspectral imaging data acquisition, processing and analysis and building a multi-crop chlorophyll model. For 90 inspected samples of plant leaves, the optimal vegetation index and model were found. Obtained values of chlorophyll concentrations correlate well with reference values (determination coefficient of 0.89 and relative error of 15%). Applying a multi-crop model to each pixel, we calculated chlorophyll content maps across all plant samples. The results of this study demonstrate that acousto-optic imagery is very promising for fast chlorophyll content assessment and other laboratory spectral-index-based measurements.
]]>Remote Sensing doi: 10.3390/rs16061072
Authors: Wujiao Dai Xin Li Wenkun Yu Xuanyu Qu Xiaoli Ding
Large-scale engineering structures deform and vibrate under the influence of external forces. Obtaining displacement and vibration is crucial for structural health monitoring (SHM). Global navigation satellite system (GNSS) and inertial measurement unit (IMU) are complementary and widely used in SHM. In this paper, we propose an SHM scheme where IMU and multi-antenna GNSS are tightly integrated. The phase centers of multiple GNSS antennas are transformed into the IMU center, which increases the observation redundancy and strengthens the positioning model. To evaluate the performance of tight integration of IMU and multiple GNSS antennas, high-rate vibrational signals are simulated using a shaking table, and the errors of horizontal displacement of different positioning schemes are analyzed using recordings of a high-precision ranging laser as the reference. The results demonstrate that applying triple-antenna GNSS/IMU integration for measuring the displacement can achieve an accuracy of 2.6 mm, which is about 33.0% and 30.3% superior than the accuracy achieved by the conventional single-antenna GNSS-only and GNSS/IMU solutions, respectively.
]]>Remote Sensing doi: 10.3390/rs16061070
Authors: Peng Chen Jinxin Lin Qing Zhao Lei Zhou Tianliang Yang Xinlei Huang Jianzhong Wu
Building change detection (BCD) plays a vital role in city planning and development, ensuring the timely detection of urban changes near metro lines. Synthetic Aperture Radar (SAR) has the advantage of providing continuous image time series with all-weather and all-time capabilities for earth observation compared with optical remote sensors. Deep learning algorithms have extensively been applied for BCD to realize the automatic detection of building changes. However, existing deep learning-based BCD methods with SAR images suffer limited accuracy due to the speckle noise effect and insufficient feature extraction. In this paper, an attention-guided dual-branch fusion network (ADF-Net) is proposed for urban BCD to address this limitation. Specifically, high-resolution SAR images collected by TerraSAR-X have been utilized to detect building changes near metro line 8 in Shanghai with the ADF-Net model. In particular, a dual-branch structure is employed in ADF-Net to extract heterogeneous features from radiometrically calibrated TerraSAR-X images and log ratio images (i.e., difference images (DIs) in dB scale). In addition, the attention-guided cross-layer addition (ACLA) blocks are used to precisely locate the features of changed areas with the transformer-based attention mechanism, and the global attention mechanism with the residual unit (GAM-RU) blocks is introduced to enhance the representation learning capabilities and solve the problems of gradient fading. The effectiveness of ADF-Net is verified using evaluation metrics. The results demonstrate that ADF-Net generates better building change maps than other methods, including U-Net, FC-EF, SNUNet-CD, A2Net, DMINet, USFFCNet, EATDer, and DRPNet. As a result, some building area changes near metro line 8 in Shanghai have been accurately detected by ADF-Net. Furthermore, the prediction results are consistent with the changes derived from high-resolution optical remote sensing images.
]]>Remote Sensing doi: 10.3390/rs16061071
Authors: Yeonha Shin Heesub Shin Jaewoo Ok Minyoung Back Jaehyuk Youn Sungho Kim
Deep learning technology for real-time small object detection in aerial images can be used in various industrial environments such as real-time traffic surveillance and military reconnaissance. However, detecting small objects with few pixels and low resolution remains a challenging problem that requires performance improvement. To improve the performance of small object detection, we propose DCEF2-YOLO. Our proposed method enables efficient real-time small object detection by using a deformable convolution (DFConv) module and an efficient feature fusion structure to maximize the use of the internal feature information of objects. DFConv preserves small object information by preventing the mixing of object information with the background. The optimized feature fusion structure produces high-quality feature maps for efficient real-time small object detection while maximizing the use of limited information. Additionally, modifying the input data processing stage and reducing the detection layer to suit small object detection also contributes to performance improvement. When compared to the performance of the latest YOLO-based models (such as DCN-YOLO and YOLOv7), DCEF2-YOLO outperforms them, with a mAP of +6.1% on the DOTA-v1.0 test set, +0.3% on the NWPU VHR-10 test set, and +1.5% on the VEDAI512 test set. Furthermore, it has a fast processing speed of 120.48 FPS with an RTX3090 for 512 × 512 images, making it suitable for real-time small object detection tasks.
]]>Remote Sensing doi: 10.3390/rs16061068
Authors: Bing Chen Xinghong Cheng Debin Su Xiangde Xu Siying Ma Zhiqun Hu
Stationary or mobile microwave radiometers (MRs) can measure atmospheric temperature, relative humidity, and water vapor density profiles with high spatio-temporal resolution, but cannot obtain the vertical variations of wind field. Based on a dataset of brightness temperatures (TBs) measured with a mobile MR over the Three-River-Source Region of the Tibetan Plateau from 18 to 30 July 2021, we develop a direct retrieval method for the wind profile (WP) based on the Long Short-Term Memory (LSTM) network technique, and obtain the reliable dynamic variation characteristics of the WP in the region. Furthermore, the ground-based radiative transfer model for TOVS (RTTOV-gb) was employed to validate the reliability of the TB observation, and we analyzed the impact of weather conditions, altitude, observational mode, and TB diurnal variation on the accuracy of the TB measurement and the retrieval of the WP. Results show that the TB from the mobile observation (MOTB) on clear and cloudy days are close to those of the simulated TB with the RTTOV-gb model, while TB measurements on rainy days are far larger than the modeled TBs. When compared with radiosonde observations, the WPs retrieved with the LSTM algorithm are better than the ERA5 reanalysis data, especially below 350 hPa, where the root mean square errors for both wind speed and wind direction are smaller than those of ERA5. The major factors influencing WP retrieval include the weather conditions, altitude, observational mode, and TB diurnal variation. Under clear-sky and cloudy conditions, the LSTM retrieval method can reproduce the spatio-temporal evolution of wind field and vertical wind shear characteristics. The findings of this study help to improve our understanding of meso-scale atmospheric dynamic structures, characteristics of vertical wind shear, atmospheric boundary layer turbulence, and enhance the assessment and forecasting accuracy of wind energy resources.
]]>Remote Sensing doi: 10.3390/rs16061069
Authors: Duan Sun Wang Zha Yu Yang
Spatiotemporal assessment and a comprehensive understanding of cropland sustainability are prerequisites for ensuring food security and promoting sustainable development. However, a remote sensing-based approach framework that is suitable for large-scale and high-precision assessment and can reflect the overall sustainability of cropland has not yet been developed. This study considered a typical lateritic red soil region of Guangdong Province, China, as an example. Cropland sustainability was examined from three aspects: natural capacity, management level, and food productivity. Ten typical indicators, including soil organic matter, pH, irrigation guarantee capability, multiple cropping index, and food productivity, among others, were constructed using remote sensing technology and selected to represent these three aspects. Based on the indicator system, we assessed the spatiotemporal patterns of cropland sustainability from 2010 to 2020. The results showed that the natural capacity, management level, and food productivity of cropland had improved over the 10 years. The cropland sustainability score increased from 67.95 to 69.08 over this period. The sustainability scores for 68.64% of cropland were increased and were largely distributed in the eastern and western region of the study area. The croplands with declining sustainability scores were mostly distributed in the central region. The prefecture-level regions differed in cropland sustainability, with Zhongshan, Zhuhai, and Qingyuan cities exhibiting the highest values, and Zhanjiang the lowest. Exploring the underlying mechanisms of cropland sustainability and proposing improvement measures can guide decision-making, cropland protection, and efficient utilization, especially in similar lateritic red soil regions of the world.
]]>Remote Sensing doi: 10.3390/rs16061067
Authors: Tingting Wang Zhiyong Suo Jingjing Ti Boya Yan Hongli Xiang Jiabao Xi
As an improvement on the traditional model-based Yamaguchi four-component decomposition method, in recent years, to fully utilize the polarization information in the coherency matrix, four-component target decomposition methods Y4R and S4R have been proposed, which are based on the rotation of the coherency matrix and the expansion of the volume model, respectively. At the same time, there is also an improved G4U method proposed based on Y4R and S4R. Although these methods have achieved certain decomposition results, there are still problems with overestimation of volume scattering and insufficient utilization of polarization information. In this paper, a unitary transformation extension to the four-component target decomposition method of PolSAR based on the properties of the Jacobi method is proposed. By analyzing the terms in the basic scattering models, such as volume scattering, in the existing four-component decomposition methods, it is clear that the reason for the existence of the residual matrix in the existing decomposition methods is that the off-diagonal term T13 and the real part of T23 of the coherency matrix T do not participate in the four-component decomposition. On this basis, a matrix transformation method is proposed to decouple terms T13 and ReT23, and the residual matrix decomposed based on this method is derived. The performance of the proposed method was validated and evaluated using two datasets. The experimental results indicate that, compared with model-based methods such as Y4R, S4R and G4U, the proposed method can enhance the contribution of double-bounce scattering and odd-bounce scattering power in urban areas in both sets of data. The computational time of the proposed method is equivalent to Y4R, S4R, etc.
]]>Remote Sensing doi: 10.3390/rs16061066
Authors: Elizabeth Baby George Cécile Gomez Nagesh D. Kumar
The deployment of remote sensing platforms has facilitated the mapping of soil properties to a great extent. However, the accuracy of these soil property estimates is compromised by the presence of non-soil cover, which introduces interference with the acquired reflectance spectra over pixels. Therefore, current soil property estimation by remote sensing is limited to bare soil pixels, which are identified based on spectral indices of vegetation. Our study proposes a composite mapping approach to extend the soil properties mapping beyond bare soil pixels, associated with an uncertainty map. The proposed approach first classified the pixels based on their bare soil fractional cover by spectral unmixing. Then, a specific regression model was built and applied to each bare soil fractional cover class to estimate clay content. Finally, the clay content maps created for each bare soil fractional cover class were mosaicked to create a composite map of clay content estimations. A bootstrap procedure was used to estimate the standard deviation of clay content predictions per bare soil fractional cover dataset, which represented the uncertainty of estimations. This study used a hyperspectral image acquired by the Airborne Visible/Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) sensor over cultivated fields in South India. The proposed approach provided modest performances in prediction (Rval2 ranging from 0.53 to 0.63) depending on the bare soil fractional cover class and showed a correct spatial pattern, regardless of the bare soil fraction classes. The model’s performance was observed to increase with the adoption of higher bare soil fractional cover thresholds. The mapped area ranged from 10.4% for pixels with bare soil fractional cover >0.7 to 52.7% for pixels with bare soil fractional cover >0.3. The approach thus extended the mapped surface by 42.4%, while maintaining acceptable prediction performances. Finally, the proposed approach could be adopted to extend the mapping capability of planned and current hyperspectral satellite missions.
]]>Remote Sensing doi: 10.3390/rs16061065
Authors: Rehman Eon Brian N. Wenny Ethan Poole Sarah Eftekharzadeh Kay Matthew Montanaro Aaron Gerace Kurtis J. Thome
The launch of Landsat 9 (L9) on 27 September 2021 marks the ongoing commitment of the Landsat mission to delivering users with calibrated Earth observations for fifty years. The two imaging sensors on L9 are the Thermal Infrared Sensor-2 (TIRS-2) and the Operational Land Imager-2 (OLI-2). Shortly after launch, the image data from OLI-2 and TIRS-2 were evaluated for both radiometric and geometric quality. This paper provides a synopsis of the evaluation of the spatial response of the TIRS-2 instrument. The assessment focuses on determining the instrument’s ability to detect a perfect knife edge. The spatial response was evaluated both pre- and post-launch. Pre-launch testing was performed at NASA Goddard Space Flight Center (GSFC) under flight-like thermal vacuum (TVAC) conditions. On orbit, coastline targets were identified to evaluate the spatial response and compared against Landsat 8 (L8). The pre-launch results indicate that the spatial response of the TIRS-2 sensor is consistent with its predecessor on board L8, with no noticeable decline in image quality to compromise any TIRS science objectives. Similarly, the post-launch analysis shows no apparent degradation of the TIRS-2 focus during the launch and the initial operational timeframe.
]]>Remote Sensing doi: 10.3390/rs16061064
Authors: Dedalo Marchetti Yunbin Yuan Kaiguang Zhu
We launched this Special Issue with the aim of collecting papers that use satellite data and new methodologies to understand the preparatory phase of medium–large earthquakes in the world [...]
]]>Remote Sensing doi: 10.3390/rs16061063
Authors: Jianping Hu Bo Yin Chaoqun Guo
Precipitation prediction plays a crucial role in people’s daily lives, work, and social development. Especially in the context of global climate variability, where extreme precipitation causes significant losses to the property of people worldwide, it is urgently necessary to use deep learning algorithms based on radar echo extrapolation for short-term precipitation forecasting. However, there are inadequately addressed issues with radar echo extrapolation methods based on deep learning, particularly when considering the inherent meteorological characteristics of precipitation on spatial and temporal scales. Additionally, traditional forecasting methods face challenges in handling local images that deviate from the overall trend. To address these problems, we propose the METEO-DLNet short-term precipitation prediction network based on meteorological features and deep learning. Experimental results demonstrate that the Meteo-LSTM of METEO-DLNet, utilizing spatial attention and differential attention, adequately learns the influence of meteorological features on spatial and temporal scales. The fusion mechanism, combining self-attention and gating mechanisms, resolves the divergence between local images and the overall trend. Quantitative and qualitative experiments show that METEO-DLNet outperforms current mainstream deep learning precipitation prediction models in natural spatiotemporal sequence problems.
]]>Remote Sensing doi: 10.3390/rs16061062
Authors: Hua Xu Weiming Cheng Baixue Wang Keyu Song Yichi Zhang Ruibo Wang Anming Bao
As the core area of human activities and economic development in the Xinjiang Autonomous Region, the hilly oasis zone of Xinjiang directly affects the regional sustainable development and stability of the ecosystem. Understanding the effects of different geomorphic types on vegetation distribution is crucial for maintaining vegetation growth and development, especially the improvement in the terrestrial ecological environment in arid areas under the background of climate change. However, there are few studies on the effect of spatial differences in detailed geomorphic types on vegetation distribution patterns. Therefore, this paper divides the Xinjiang hilly oasis zone into six geomorphologic level zones and innovatively investigates the influence of detailed geomorphologic types on the spatial distribution of vegetation and vegetation cover. Further, the area proportion of detailed landform types corresponding to different vegetation coverage in each geomorphic area was quantitatively calculated. Finally, the Geodetector method was used to detect the drivers of interactions between vegetation and the environment. The findings are shown as follows: (1) In the same climate zone, the spatial differentiation of landforms has a great influence on the vegetation distribution, manifesting as the significantly different vegetation distribution in different landform types. Grassland is the main vegetation type in the erosion and denudation of Nakayama; cultivated vegetation and meadows have a larger coverage in the alluvial flood plain and alluvial plain; and the distribution of vegetation in the Tianshan economic zone is characterized by obvious vertical zoning with the geomorphology. (2) The landform type and morphological types are the strongest driving factors for vegetation coverage with q values of 0.433 and 0.295, respectively, which effectually fill the gap caused by only using two terrain indicators, slope and elevation, to study the relationship between landforms and vegetation. (3) In addition, the improved nonlinear interaction resulting from the double factor of landform type and slope is 0.486, which has a stronger control on vegetation coverage than the single factor of landform type. These findings are conducive to enhancing the supply services of vegetation to the ecosystem in arid areas as well as providing important scientific guidance for the construction of ecological civilization and sustainable development in Xinjiang.
]]>Remote Sensing doi: 10.3390/rs16061061
Authors: Qiang Wu Liang Huang Bo-Hui Tang Jiapei Cheng Meiqi Wang Zixuan Zhang
Dynamic monitoring of cropland using high spatial resolution remote sensing images is a powerful means to protect cropland resources. However, when a change detection method based on a convolutional neural network employs a large number of convolution and pooling operations to mine the deep features of cropland, the accumulation of irrelevant features and the loss of key features will lead to poor detection results. To effectively solve this problem, a novel cropland change detection network (CroplandCDNet) is proposed in this paper; this network combines an adaptive receptive field and multiscale feature transmission fusion to achieve accurate detection of cropland change information. CroplandCDNet first effectively extracts the multiscale features of cropland from bitemporal remote sensing images through the feature extraction module and subsequently embeds the receptive field adaptive SK attention (SKA) module to emphasize cropland change. Moreover, the SKA module effectively uses spatial context information for the dynamic adjustment of the convolution kernel size of cropland features at different scales. Finally, multiscale features and difference features are transmitted and fused layer by layer to obtain the content of cropland change. In the experiments, the proposed method is compared with six advanced change detection methods using the cropland change detection dataset (CLCD). The experimental results show that CroplandCDNet achieves the best F1 and OA at 76.04% and 94.47%, respectively. Its precision and recall are second best of all models at 76.46% and 75.63%, respectively. Moreover, a generalization experiment was carried out using the Jilin-1 dataset, which effectively verified the reliability of CroplandCDNet in cropland change detection.
]]>Remote Sensing doi: 10.3390/rs16061060
Authors: Yuanqi Li Ronghai Hu Yuzhen Xing Zhe Pang Zhi Chen Haishan Niu
Aboveground biomass (AGB) of shrubs and low-statured trees constitutes a substantial portion of the total carbon pool in temperate forest ecosystems, contributing much to local biodiversity, altering tree-regeneration growth rates, and determining above- and belowground food webs. Accurate quantification of AGB at the shrub layer is crucial for ecological modeling and still remains a challenge. Several methods for estimating understory biomass, including inventory and remote sensing-based methods, need to be evaluated against measured datasets. In this study, we acquired 158 individual terrestrial laser scans (TLS) across 45 sites in the Yanshan Mountains and generated metrics including leaf area and stem volume from TLS data using voxel- and non-voxel-based approaches in both leaf-on and leaf-off scenarios. Allometric equations were applied using field-measured parameters as an inventory approach. The results indicated that allometric equations using crown area and height yielded results with higher accuracy than other inventory approach parameters (R2 and RMSE ranging from 0.47 to 0.91 and 12.38 to 38.11 g, respectively). The voxel-based approach using TLS data provided results with R2 and RMSE ranging from 0.86 to 0.96 and 6.43 to 21.03 g. Additionally, the non-voxel-based approach provided similar or slightly better results compared to the voxel-based approach (R2 and RMSE ranging from 0.93 to 0.96 and 4.23 to 11.27 g, respectively) while avoiding the complexity of selecting the optimal voxel size that arises during voxelization.
]]>Remote Sensing doi: 10.3390/rs16061057
Authors: Ruaridh A. Clark Ciara N. McGrath Astrid A. Werkmeister Christopher J. Lowe Gwilym Gibbons Malcolm Macdonald
Tidal flats are some of the most dynamic coastal environments in the world, where traditional coastal mapping and monitoring provide insufficient temporal resolution to reliably map channels and sand flats. Satellite-based Synthetic Aperture Radar (SAR) enables regular cloud-penetrating detection of water flowing through channels within the tidal flats, referred to as tidal channels. This paper presents a method for detecting a path through tidal channels, using satellite imagery, that supports our understanding and safe exploitation of this valuable coastal environment. This approach is the first proposed to identify navigable paths in all conditions, with SAR images susceptible to variation due to weather and tidal conditions. Tidal channels are known to vary in SAR presentation, and we find that tidal flat presentation is also influenced by conditions. The most influential factor is the wind, with high winds causing an inversion in how both tidal flats and tidal channels present in SAR images. The presented method for the automatic detection of tidal channels accounts for this variability by using previous channel paths as a reference to reliably correct imagery and detect the latest path. The final algorithm produces paths with minor errors in 17.6% of images; the error rate increases to 71.7%, with an almost tenfold increase in errors, when the SAR image and paths are not adjusted to account for conditions. This capability has been used to support the Nith Inshore Rescue in attending call-outs from their base in Glencaple, UK, while the insights from monitoring tidal channels for a year demonstrate how periods of high river flow preceded major changes in the channel path.
]]>Remote Sensing doi: 10.3390/rs16061059
Authors: Cristiano Fidani Serena D’Arcangelo Angelo De Santis Loredana Perrone Maurizio Soldani
On 4 March 2021, a devastating M8.1 earthquake struck the Kermadec Islands of New Zealand. Given the tremendous energy released during the event, we sought to investigate the event’s potential impact on the ionosphere and the inner Van Allen Belt using data from the high-energy electron detectors on board the NOAA-18 satellite. The survey was also extended to the strongest shallow M6.5+ earthquakes occurring between 150° and 190° in longitude, and between −5° and −35° in latitude over the previous ten years. In nearly all cases, evident electron fluxes entering the loss cone were observed. To explore the possibility of a connection between ionospheric signals and tectonic events in this intensely active region, we analyzed electron losses from the inner Van Allen Belt, taking into account latitude, longitude, day/night times, and proximity to the South Atlantic Anomaly. Compared to previous studies, here only the most significant loss phenomena persistent in the ionosphere were considered. Particular interest was reserved for the intense electron loss events that had a duration spanning from a few to several minutes and occurred several hours before and after strong seismic events. Thereafter, time series of electron counting rates and strong Southern Pacific earthquakes were transformed into binary series, and the series multiplication was investigated. The results suggest four peaks of association, including a first couple between electron perturbations detected for ascending semi-orbits and seismic events and a second one between electron perturbations detected in the southern ionosphere and seismic events. They both anticipated the occurrence of earthquakes, occurring around 4 h before them. Other couples were observed between electron perturbations detected for descending semi-orbits and seismic events and between electron perturbations detected in the northern ionosphere and seismic events. They both occurred around 3 h after the occurrence of earthquakes. The case of perturbations anticipating seismic events has the intriguing properties of sustaining the hypothesis that a physical interaction occurred around 6 h before seismic events as in the West Pacific case. A physical model of electrons detected far several thousands of km from the earthquake epicenters was also presented. However, a simulation of random seismic events suggested that the null hypothesis cannot be fully rejected for these associations, prompting many more analyses and case studies.
]]>Remote Sensing doi: 10.3390/rs16061058
Authors: Xiaomao Chen Shanshan Zhang Xiaofeng Qin Jinfeng Lin
Two-dimensional phase unwrapping (2-D PU) is vital for reconstructing Earth’s surface topography and displacement from interferometric synthetic aperture radar (InSAR) data. Conventional algorithms rely on the postulate, but this assumption is often insufficient due to abrupt topographic changes and severe noise. To address this challenge, our research proposes a novel approach utilizing deep convolutional neural networks inspired by the U-Net architecture to estimate phase gradient information. Our approach involves downsampling the input data to extract crucial features, followed by upsampling to restore spatial resolution. We incorporate two attention mechanisms—feature pyramid attention (FPA) and global attention upsample (GAU)—and a residual structure in the network’s structure. Thus, we construct ResDANet (residual and dual attention net). We rigorously train ResDANet utilizing simulated datasets and employ an L1-norm objective function to minimize the disparity between unwrapped phase gradients and those calculated by ResDANet, yielding the final 2-D PU results. The network is rigorously trained using two distinct training strategies and encompassing three types of simulated datasets. ResDANet exhibits excellent robust performance and efficiency on simulated data and real data, such as China’s Three Gorges and an Italian volcano.
]]>Remote Sensing doi: 10.3390/rs16061055
Authors: Wei Zhang Xuesong Wang Haoyu Wang Yuhu Cheng
Multimodal remote sensing data classification can enhance a model’s ability to distinguish land features through multimodal data fusion. In this context, how to help models understand the relationship between multimodal data and target tasks has become the focus of researchers. Inspired by the human feedback learning mechanism, causal reasoning mechanism, and knowledge induction mechanism, this paper integrates causal learning, reinforcement learning, and meta learning into a unified remote sensing data classification framework and proposes causal meta-reinforcement learning (CMRL). First, based on the feedback learning mechanism, we overcame the limitations of traditional implicit optimization of fusion features and customized a reinforcement learning environment for multimodal remote sensing data classification tasks. Through feedback interactive learning between agents and the environment, we helped the agents understand the complex relationships between multimodal data and labels, thereby achieving full mining of multimodal complementary information.Second, based on the causal inference mechanism, we designed causal distribution prediction actions, classification rewards, and causal intervention rewards, capturing pure causal factors in multimodal data and preventing false statistical associations between non-causal factors and class labels. Finally, based on the knowledge induction mechanism, we designed a bi-layer optimization mechanism based on meta-learning. By constructing a meta training task and meta validation task simulation model in the generalization scenario of unseen data, we helped the model induce cross-task shared knowledge, thereby improving its generalization ability for unseen multimodal data. The experimental results on multiple sets of multimodal datasets showed that the proposed method achieved state-of-the-art performance in multimodal remote sensing data classification tasks.
]]>Remote Sensing doi: 10.3390/rs16061056
Authors: Fabien H. Wagner Samuel Favrichon Ricardo Dalagnol Mayumi C. M. Hirye Adugna Mullissa Sassan Saatchi
The Amazon, the world’s largest rainforest, faces a severe historic drought. The Rio Negro River, one of the major Amazon River tributaries, reached its lowest level in a century in October 2023. Here, we used a U-net deep learning model to map water surfaces in the Rio Negro River basin every 12 days in 2022 and 2023 using 10 m spatial resolution Sentinel-1 satellite radar images. The accuracy of the water surface model was high, with an F1-score of 0.93. A 12-day mosaic time series of the water surface was generated from the Sentinel-1 prediction. The water surface mask demonstrated relatively consistent agreement with the global surface water (GSW) product from the Joint Research Centre (F1-score: 0.708) and with the Brazilian MapBiomas Water initiative (F1-score: 0.686). The main errors of the map were omission errors in flooded woodland, in flooded shrub, and because of clouds. Rio Negro water surfaces reached their lowest level around the 25th of November 2023 and were reduced to 68.1% (9559.9 km2) of the maximum water surfaces observed in the period 2022–2023 (14,036.3 km2). Synthetic aperture radar (SAR) data, in conjunction with deep learning techniques, can significantly improve near-real-time mapping of water surfaces in tropical regions.
]]>Remote Sensing doi: 10.3390/rs16061054
Authors: Juan C. Casas-Rosa Pablo Navarro Rafael J. Segura-Sánchez Antonio J. Rueda-Ruiz Alfonso López-Ruiz José M. Fuertes Claudio Delrieux Carlos J. Ogayar-Anguita
The management of large point clouds obtained by LiDAR sensors is an important topic in recent years due to the widespread use of this technology in a wide variety of applications and the increasing volume of data captured. One of the main applications of LIDAR systems is the study of the temporal evolution of the real environment. In open environments, it is important to know the evolution of erosive processes or landscape transformation. In the context of civil engineering and urban environments, it is useful for monitoring urban dynamics and growth, and changes during the construction of buildings or infrastructure facilities. The main problem with change detection (CD) methods is erroneous detection due to precision errors or the use of different capture devices at different times. This work presents a method to compare large point clouds, based on the study of the local fractal dimension of point clouds at multiple scales. Our method is robust in the presence of environmental and sensor factors that produce abnormal results with other methods. Furthermore, it is more stable than others in cases where there is no significant displacement of points but there is a local alteration of the structure of the point cloud. Furthermore, the precision can be adapted to the complexity and density of the point cloud. Finally, our solution is faster than other CD methods such as distance-based methods and can run at O(1) under some conditions, which is important when working with large datasets. All these improvements make the proposed method more suitable than the others to solve complex problems with LiDAR data, such as storage, time series data management, visualization, etc.
]]>Remote Sensing doi: 10.3390/rs16061053
Authors: Ivan Ghezzi Jacek Kościuk Warren Church Parker VanValkenburgh Bartłomiej Ćmielewski Matthias Kucera Paweł B. Dąbek Jeff Contreras Nilsson Mori Giovanni Righetti Stefano Serafini Carol Rojas
We combined datasets from multiple research projects and remote sensing technologies to evaluate conservation conditions at La Fortaleza de Kuelap, a pre-Hispanic site in Peru that suffered significant damage under heavy seasonal rains in April 2022. To identify the causes of the collapse and where the monument is at further risk, we modeled surface hydrology using a DTM derived from drone LiDAR data, reconstructed a history of collapses, and calculated the volume of the most recent by fusing terrestrial LiDAR and photogrammetric datasets. In addition, we examined subsurface water accumulation with electrical resistivity, reconstructed the stratification of the monument with seismic refraction, and analyzed vegetation loss and ground moisture accumulation using satellite imagery. Our results point to rainwater infiltration as the most significant source of risk for La Fortaleza’s perimeter walls. Combined with other adverse natural conditions and contemporary conservation interventions, this led to the 2022 collapse. Specialists need to consider these factors when tasked with conserving monuments located in comparable high-altitude perhumid environments. This integration of analytical results demonstrates how multi-scalar and multi-instrumental approaches provide comprehensive and timely assessments of conservation needs.
]]>Remote Sensing doi: 10.3390/rs16061052
Authors: Yuqiao Long Jing Sun Joost Wellens Gilles Colinet Wenbin Wu Jeroen Meersmans
Whether China can achieve the United Nations’ Sustainable Development Goals (SDGs) largely depends on the ability of main food-producing areas to cope with multiple land use change challenges. Despite the fact that the Yangtze River basin is one of the key regions for China’s food security, the spatiotemporal dynamics of cropland abandonment and recultivation remain largely unexplored in this region. The present study assesses the evolution of the agricultural system within the Yangtze River basin between 2000 and 2020 by mapping cropland abandonment and recultivation using MODIS time series and multiple land cover products. The results highlight a widespread cropland abandonment process (i.e., 10.5% of the total study area between 2000 and 2020), predominantly in Western Sichuan, Eastern Yunnan, and Central Jiangxi. Although 70% of abandoned cropland is situated in areas with slopes less than 5°, the highest rates of abandonment are in mountainous regions. However, by 2020, 74% of this abandoned cropland had been recultivated at least once, whereas half of the abandoned croplands got recultivated within three years of their initial abandonment. Hence, as this is one of the first studies that unravels the complex interaction between cropland abandonment and recultivation in a spatiotemporal explicit context, it offers (i) scientists a novel methodological framework to assess agricultural land use issues across large geographical entities, and (ii) policy-makers new insights to support the sustainable transition of the agricultural sector.
]]>Remote Sensing doi: 10.3390/rs16061051
Authors: Wenwen Xu Jiankang Xiao Dalong Xu Hao Wang Jianyin Cao
A pulse-Doppler (PD) radar has the advantage of strong anti-interference ability, and it is often used as a solution for maneuvering target tracking. In the application of target monitoring and tracking in PD radars, the interacting multiple model algorithm (IMM) has become the main and preferred choice due to its flexibility and high accuracy. However, the probability transfer matrix in classical IMM algorithms generally depends on constant prior knowledge, and if a PD radar is tracking a strong maneuvering target, it is inevitable to encounter some limitations, such as the possibility of target tracking trajectory deviation, and even a loss of the target. The Markov probability transfer matrix is proposed with an adaptive modification ability in real time to overcome the above problems in this paper. Additionally, for improving the speed of switching between the models, the fuzzy control system for secondary updating of model probability is adopted. By this means, the tracking accuracy of maneuvering targets is enhanced. Compared with the classical IMM algorithm, the corresponding simulation results for the PD radar indicate that the overall tracking accuracy of the proposed adaptive IMM algorithm is improved by 19.6%. In conclusion, the continuity and accuracy of the target trajectory can be effectively improved with the proposed adaptive IMM algorithm in PD radar cases.
]]>Remote Sensing doi: 10.3390/rs16061050
Authors: Michael S. Watt Honey Jane C. Estarija Michael Bartlett Russell Main Dalila Pasquini Warren Yorston Emily McLay Maria Zhulanov Kiryn Dobbie Katherine Wardhaugh Zulfikar Hossain Stuart Fraser Henning Buddenbaum
Myrtle rust is a very damaging disease, caused by the fungus Austropuccinia psidii, which has recently arrived in New Zealand and threatens the iconic tree species pōhutukawa (Metrosideros excelsa). Canopy-level hyperspectral and thermal images were taken repeatedly within a controlled environment, from 49 inoculated (MR treatment) and 26 uninoculated (control treatment) pōhutukawa plants. Measurements were taken prior to inoculation and six times post-inoculation over a 14-day period. Using indices extracted from these data, the objectives were to (i) identify the key thermal and narrow-band hyperspectral indices (NBHIs) associated with the pre-visual and early expression of myrtle rust and (ii) develop a classification model to detect the disease. The number of symptomatic plants increased rapidly from three plants at 3 days after inoculation (DAI) to all 49 MR plants at 8 DAI. NBHIs were most effective for pre-visual and early disease detection from 3 to 6 DAI, while thermal indices were more effective for detection of disease following symptom expression from 7 to 14 DAI. Using results compiled from an independent test dataset, model performance using the best thermal indices and NBHIs was excellent from 3 DAI to 6 DAI (F1 score 0.81–0.85; accuracy 73–80%) and outstanding from 7 to 14 DAI (F1 score 0.92–0.93; accuracy 89–91%).
]]>Remote Sensing doi: 10.3390/rs16061049
Authors: Gregory S. Norris Armand LaRocque Brigitte Leblon Myriam A. Barbeau Alan R. Hanson
Monitoring salt marshes with remote sensing is necessary to evaluate their state and restoration. Determining appropriate techniques for this can be overwhelming. Our study provides insight into whether a pixel- or object-based Random Forest classification approach is best for mapping vegetation in north temperate salt marshes. We used input variables from drone images (raw reflectances, vegetation indices, and textural features) acquired in June, July, and August 2021 of a salt marsh restoration and reference site in Aulac, New Brunswick, Canada. We also investigated the importance of input variables and whether using landcover classes representing areas of change was a practical way to evaluate variation in the monthly images. Our results indicated that (1) the classifiers achieved overall validation accuracies of 91.1–95.2%; (2) pixel-based classifiers outperformed object-based classifiers by 1.3–2.0%; (3) input variables extracted from the August images were more important than those extracted from the June and July images; (4) certain raw reflectances, vegetation indices, and textural features were among the most important variables; and (5) classes that changed temporally were mapped with user’s and producer’s validation accuracies of 86.7–100.0%. Knowledge gained during this study will inform assessments of salt marsh restoration trajectories spanning multiple years.
]]>Remote Sensing doi: 10.3390/rs16061048
Authors: Jinwei Tong Zhen Shi Jiashuang Jiao Bing Yang Zhen Tian
The southeastern Tibetan Plateau (SETP), which hosts the most extensive marine glaciers on the Tibetan Plateau (TP), exhibits enhanced sensitivity to climatic fluctuations. Under global warming, persistent glacier mass depletion within the SETP poses a risk to water resource security and sustainability in adjacent nations and regions. This study deployed a high-precision ICESat-2 satellite altimetry technique to evaluate SETP glacier thickness changes from 2018 to 2022. Our results show that the average change rate in glacier thickness in the SETP is −0.91 ± 0.18 m/yr, and the corresponding glacier mass change is −7.61 ± 1.52 Gt/yr. In the SETP, the glacier mass loss obtained via ICESat-2 data is larger than the mass change in total land water storage observed by the Gravity Recovery and Climate Experiment follow-on satellite (GRACE-FO), −5.13 ± 2.55 Gt/yr, which underscores the changes occurring in other land water components, including snow (−0.44 ± 0.09 Gt/yr), lakes (−0.06 ± 0.02 Gt/yr), soil moisture (1.88 ± 1.83 Gt/yr), and groundwater (1.45 ± 0.70 Gt/yr), with a closure error of −0.35 Gt/yr. This demonstrates that this dramatic glacier mass loss is the main reason for the decrease in total land water storage in the SETP. Generally, there are decreasing trends in solid water storage (glacier and snow) against stable or increasing trends in liquid water storage (lakes, soil moisture, and groundwater) in the SETP. This persistent decrease in solid water is linked to the enhanced melting induced by rising temperatures. Given the decreasing trend in summer precipitation, the surge in liquid water in the SETP should be principally ascribed to the increased melting of solid water.
]]>Remote Sensing doi: 10.3390/rs16061046
Authors: Tao Tao Keming Han Xin Yao Ximing Chen Zuoqi Wu Chuangchuang Yao Xuwen Tian Zhenkai Zhou Kaiyu Ren
The occurrence of surface strata movement in underground coal mining leads to the generation of numerous ground fissures, which not only damage the ecological environment but also disrupt building facilities, lead to airflow and easily trigger coal spontaneous combustion, induce geological disasters, posing a serious threat to people’s lives, property, and mining production. Therefore, it is particularly important to quickly and accurately obtain the information of ground fissures and then study their distribution patterns and the law of spatial-temporal evolution. The traditional field investigation methods for identifying fissures have low efficiency. The rapid development of UAVs has brought an opportunity to address this issue. However, it also poses new questions, such as how to interpret numerous fissures and the distribution law of fissures with underground mining. Taking a mine in the Shenfu coalfield on the semi-desert aeolian sand surface as the research area, this paper studies the fissure recognition from UAV images by deep learning, fissure development law, as well as the mutual feed of surface condition corresponding to the under-ground mining progress. The results show that the DRs-UNet deep learning method can identify more than 85% of the fissures; however, due to the influence of seasonal vegetation changes and different fissure development stages, the continuity and integrity of fissure recognition methods need to be improved. Four fissure distribution patterns were found. In open-cut areas, arc-shaped fissures are frequently observed, displaying significant dimensions in terms of depth, length, and width. Within subsidence basins, central collapse areas exhibit fissures that form perpendicular to the direction of the working face. Along roadways, parallel or oblique fissures tend to develop at specific angles. In regions characterized by weak roof strata and depressed basins, abnormal reverse-“C”-shaped fissures emerge along the mining direction. The research results comprehensively demonstrate the process of automatically identifying ground fissures from UAV images as well as the spatial distribution patterns of fissures, which can provide technical support for the prediction of ground fissures, monitoring of geological hazards in mining areas, control of land environmental damage, and land ecological restoration. In the future, it is suggested that this method be applied to different mining areas and geotechnical contexts to enhance its applicability and effectiveness.
]]>Remote Sensing doi: 10.3390/rs16061047
Authors: Kun Sun Weiwei Yu
As a highly productive and biologically diverse ecosystem, wetlands provide unique habitat for a wide array of plant and animal species. Owing to the strong disturbance by human activities and climate change, wetland degradation and fragmentation have become a common phenomenon across the globe. The Guangdong–Hong Kong–Macao Greater Bay Area (GBA) is a typical case. The GBA has experienced explosive growth in the population and economy since the early 1980s, which has resulted in complicated transitions between wetlands and non-wetlands. However, our knowledge about the transformation paths, associated drivers, and ecological influence of the GBA’s wetlands is still very limited. Taking advantage of the land use maps generated from Landsat observations over the period of 1980–2020, here, we quantified the spatiotemporal transformation paths of the GBA’s wetlands and analyzed the associated drivers and ecological influence. We found that the dominant transformation path between wetland and non-wetland was from wetland to built-up land, which accounted for 98.4% of total wetland loss. The primary transformation path among different wetland types was from coastal shallow water and paddy land to reservoir/pond, with the strongest transformation intensity in the 1980s. The driving forces behind the wetland change were found to vary by region. Anthropogenic factors (i.e., population growth and urbanization) dominated in highly developed cities, while climate factors and aquaculture had a greater influence in underdeveloped cities. The findings presented in this study will provide a reference for wetland management and planning in the GBA.
]]>Remote Sensing doi: 10.3390/rs16061045
Authors: Yangyang Li Zejun Ou Guangyuan Liu Zichen Yang Yanqiao Chen Ronghua Shang Licheng Jiao
With the continuous emergence and development of 3D sensors in recent years, it has become increasingly convenient to collect point cloud data for 3D object detection tasks, such as the field of autonomous driving. But when using these existing methods, there are two problems that cannot be ignored: (1) The bird’s eye view (BEV) is a widely used method in 3D objective detection; however, the BEV usually compresses dimensions by combined height, dimension, and channels, which makes the process of feature extraction in feature fusion more difficult. (2) Light detection and ranging (LiDAR) has a much larger effective scanning depth, which causes the sector to become sparse in deep space and the uneven distribution of point cloud data. This results in few features in the distribution of neighboring points around the key points of interest. The following is the solution proposed in this paper: (1) This paper proposes multi-scale feature fusion composed of feature maps at different levels made of Deep Layer Aggregation (DLA) and a feature fusion module for the BEV. (2) A point completion network is used to improve the prediction results by completing the feature points inside the candidate boxes in the second stage, thereby strengthening their position features. Supervised contrastive learning is applied to enhance the segmentation results, improving the discrimination capability between the foreground and background. Experiments show these new additions can achieve improvements of 2.7%, 2.4%, and 2.5%, respectively, on KITTI easy, moderate, and hard tasks. Further ablation experiments show that each addition has promising improvement over the baseline.
]]>Remote Sensing doi: 10.3390/rs16061044
Authors: Qian Sun Yu Sun Chengsheng Pan
Despite notable advancements achieved on Hyperspectral (HS) pansharpening tasks through deep learning techniques, previous methods are inherently constrained by convolution or self-attention intrinsic defects, leading to limited performance. In this paper, we proposed an Attention-Interactive Dual-Branch Convolutional Neural Network (AIDB-Net) for HS pansharpening. Our model purely consists of convolutional layers and simultaneously inherits the strengths of both convolution and self-attention, especially the modeling of short- and long-range dependencies. Specially, we first extract, tokenize, and align the hyperspectral image (HSI) and panchromatic image (PAN) by Overlapping Patch Embedding Blocks. Then, we specialize a novel Spectral-Spatial Interactive Attention which is able to globally interact and fuse the cross-modality features. The resultant token-global similarity scores can guide the refinement and renewal of the textural details and spectral characteristics within HSI features. By deeply combined these two paradigms, our AIDB-Net significantly improve the pansharpening performance. Moreover, with the acceleration by the convolution inductive bias, our interactive attention can be trained without large scale dataset and achieves competitive time cost with its counterparts. Compared with the state-of-the-art methods, our AIDB-Net makes 5.2%, 3.1%, and 2.2% improvement on PSNR metric on three public datasets, respectively. Comprehensive experiments quantitatively and qualitatively demonstrate the effectiveness and superiority of our AIDB-Net.
]]>Remote Sensing doi: 10.3390/rs16061042
Authors: Xiaoli Zhang Liang Xi Haijin Zhou Wei Wang Zhen Chang Fuqi Si Yu Wang
The pollution caused by nitrogen dioxide is a major environmental problem in China. This study introduces a new type of atmospheric trace gas remote-sensing instrument, an airborne fiber imaging spectrometer. This spectrometer has a spectral range of 300–410 nm and works in push-broom mode with a 30° field of view on a flight path. Flight experiments were conducted on 30 December 2022 and 5 January 2023, covering heavily polluted areas east of Beijing and Tangshan. This equipment obtained the density distribution of NO2 over the flight area. The results showed that pollution was mainly concentrated in the Caofeidian area and at the power station in the north, and the main source of pollution was anthropogenic. Satellite and airborne data near the pollution points were compared, and the two datasets showed a positive correlation with a correlation coefficient of 0.78 and 0.7, on the two days, respectively. This study demonstrates the capability of an airborne fiber imaging spectrometer for NO2 regional emission remote sensing and identifying the pollution points.
]]>Remote Sensing doi: 10.3390/rs16061043
Authors: Yun Lin Jiachun Wang Deyun Ma Yanping Wang Shengbo Ye
Ground-penetrating radar (GPR) is a widely used technology for pipeline detection due to its fast detection speed and high resolution. However, the presence of complex underground media often results in strong ground clutter interference in the collected B-scan echoes, significantly impacting detection performance. To address this issue, this paper proposes an improved clutter suppression network based on a cycle-consistency generative adversarial network (CycleGAN). By employing the concept of style transfer, the network aims to convert clutter images into clutter-free images. This paper introduces multiple residual blocks into the generator and discriminator, respectively, to improve the feature expression ability of the deep learning model. Additionally, the discriminator incorporates the squeeze and excitation (SE) module, a channel attention mechanism, to further enhance the model’s ability to extract features from clutter-free images. To evaluate the effectiveness of the proposed network in clutter suppression, both simulation and measurement data are utilized to compare and analyze its performance against traditional clutter suppression methods and deep learning-based methods, respectively. From the result of the measured data, it can be found that the improvement factor (Im) of the proposed method has reached 40.68 dB, which is a significant improvement compared to the previous network.
]]>Remote Sensing doi: 10.3390/rs16061041
Authors: Valerio Pampanoni Fabio Fascetti Luca Cenci Giovanni Laneve Carla Santella Valentina Boccia
Assessing the performance of optical imaging systems is crucial to evaluate their capability to satisfy the product requirements for an Earth Observation (EO) mission. In particular, the evaluation of image quality is undoubtedly one of the most important, critical and problematic aspects of remote sensing. It involves not only pre-flight analyses, but also continuous monitoring throughout the operational lifetime of the observing system. The Ground Sampling Distance (GSD) of the imaging system is often the only parameter used to quantify its spatial resolution, i.e., its capability to resolve objects on the ground. In practice, this feature is also heavily influenced by other image quality parameters such as the image sharpness and Signal-to-Noise Ratio (SNR). However, these last two aspects are often analysed separately, using unrelated methodologies, complicating the image quality assessment and posing standardisation issues. To this end, we expanded the features of our Automatic Edge Method (AEM), which was originally developed to simplify and automate the estimate of sharpness metrics, to also extract the image SNR. In this paper we applied the AEM to a wide range of optical satellite images characterised by different GSD and Pixel Size (PS) with the objective to explore the nature of the relationship between the components of overall image quality (image sharpness, SNR) and product geometric resampling (expressed in terms of GSD/PS ratio). Our main objective is to quantify how the sharpness and the radiometric quality of an image product are affected by different product geometric resampling strategies, i.e., by distributing imagery with a PS larger or smaller than the GSD of the imaging system. The AEM allowed us to explore this relationship by relying on a vast amount of data points, which provide a robust statistical significance to the results expressed in terms of sharpness metrics and SNR means. The results indicate the existence of a direct relationship between the product geometric resampling and the overall image quality, and also highlight a good degree of correlation between the image sharpness and SNR.
]]>Remote Sensing doi: 10.3390/rs16061040
Authors: Jiahao Wen Tianbao Huang Xihong Cui Yaling Zhang Jinfeng Shi Yanjia Jiang Xiangjie Li Li Guo
Ground-penetrating radar (GPR) is a rapid and non-destructive geophysical technique widely employed to detect and quantify subsurface structures and characteristics. Its capability for time lapse (TL) detection provides essential insights into subsurface hydrological dynamics, including lateral flow and soil water distribution. However, during TL-GPR surveys, field conditions often create discrepancies in surface geometry, which introduces mismatches across sequential TL-GPR images. These discrepancies may generate spurious signal variations that impede the accurate interpretation of TL-GPR data when assessing subsurface hydrological processes. In responding to this issue, this study introduces a TL-GPR image alignment method by employing the dynamic time warping (DTW) algorithm. The purpose of the proposed method, namely TLIAM–DTW, is to correct for geometric mismatch in TL-GPR images collected from the identical survey line in the field. We validated the efficacy of the TLIAM–DTW method using both synthetic data from gprMax V3.0 simulations and actual field data collected from a hilly, forested area post-infiltration experiment. Analyses of the aligned TL-GPR images revealed that the TLIAM–DTW method effectively eliminates the influence of geometric mismatch while preserving the integrity of signal variations due to actual subsurface hydrological processes. Quantitative assessments of the proposed methods, measured by mean absolute error (MAE) and root mean square error (RMSE), showed significant improvements. After performing the TLIAM–DTW method, the MAE and RMSE between processed TL-GPR images and background images were reduced by 96% and 78%, respectively, in simple simulation scenarios; in more complex simulations, MAE declined by 27–31% and RMSE by 17–43%. Field data yielded reductions in MAE and RMSE of >82% and 69%, respectively. With these substantial improvements, the processed TL-GPR images successfully depict the spatial and temporal transitions associated with subsurface lateral flows, thereby enhancing the accuracy of monitoring subsurface hydrological processes under field conditions.
]]>Remote Sensing doi: 10.3390/rs16061039
Authors: Estrella Trincado Jose María Vindel
The selection of a certain location for the placement of a solar facility depends on the solar resource availability, which is generally assessed though exceedance probabilities. However, the choice of the specific exceedance probability is arbitrary and the assessment will be different depending on the choice taken. Furthermore, exceedance probabilities do not reflect seasonal variability, which affects radiation availability. Therefore, in this work we present a new index, the suitability index based on Theil (SIT), which allows us to assess with a single value the degree of suitability of a site for installing a solar plant. Obtained from the Theil index, it considers the availability of the resource and its seasonal variability, based as it is on the proportion of the given radiation in each month. As we will see, the new index is clearly more sensitive to the amount of radiation expressed in terms of the 50th percentile than to the variability, as given by the interquartile range. This is a quality to be pondered since scarcity of radiation will always be a greater disadvantage for a solar installation than high variability. The results obtained in the study, grounded in the application of satellite images, show that the index adequately reflects the radiation characteristics in the study area. The territory is broken into areas associated with such characteristics through a cluster analysis, so that geographical and economic elements can be considered when choosing the final location for a solar installation. Furthermore, the new index may include the effects of energy storage during the months in which a certain demand is exceeded.
]]>Remote Sensing doi: 10.3390/rs16061038
Authors: Gao Zuo Ji Zhou Yizhen Meng Tao Zhang Zhiyong Long
Efficient night-time vessel detection is of significant importance for maritime traffic management, fishery activity monitoring, and environmental protection. With the advancement in object-detection approaches, the method of night-time vessel detection has gradually shifted from traditional threshold segmentation to deep learning that balances efficiency and accuracy. However, the restricted spatial resolution of night-time light (NTL) remote sensing data (e.g., VIIRS/DNB images) results in fewer discernible features and insufficient training performance when detecting vessels that are considered small targets. To address this, we establish an Enhanced Dense Nested-Attention Network (DNA-net) to improve the detection of small vessel targets under low-light conditions. This approach effectively integrates the original VIIRS/DNB, spike median index (SMI), and spike height index (SHI) images to maintain deep-level features and enhance feature extraction. On this basis, we performed vessel detection based on the Enhanced DNA-net using VIIRS/DNB images of the Japan Sea, the South China Sea, and the Java Sea. It is noteworthy that the VIIRS Boat Detection (VBD) observations and the Automatic Identification System (AIS) data were cross-matched as the actual status of the vessels (VBD-AIS). The results show that the proposed Enhanced DNA-net achieves significant improvements in the evaluation metrics (e.g., IOU, Pd, Fa, and MPD) compared to the original DNA-net, achieving performance of 87.81%, 96.72%, 5.42%, and 0.36 Wpx, respectively. Meanwhile, we validated the detection performance of Enhanced DNA-net and strong VBD detection against VBD-AIS, showing that the Enhanced DNA-net achieves 1% better accuracy than strong VBD detection.
]]>Remote Sensing doi: 10.3390/rs16061036
Authors: Lei Hu Xun Zhou Jiachen Ruan Supeng Li
Semantic segmentation of remote sensing (RS) images is a pivotal branch in the realm of RS image processing, which plays a significant role in urban planning, building extraction, vegetation extraction, etc. With the continuous advancement of remote sensing technology, the spatial resolution of remote sensing images is progressively improving. This escalation in resolution gives rise to challenges like imbalanced class distributions among ground objects in RS images, the significant variations of ground object scales, as well as the presence of redundant information and noise interference. In this paper, we propose a multi-scale context extraction network, ASPP+-LANet, based on the LANet for semantic segmentation of high-resolution RS images. Firstly, we design an ASPP+ module, expanding upon the ASPP module by incorporating an additional feature extraction channel, redesigning the dilation rates, and introducing the Coordinate Attention (CA) mechanism so that it can effectively improve the segmentation performance of ground object targets at different scales. Secondly, we introduce the Funnel ReLU (FReLU) activation function for enhancing the segmentation effect of slender ground object targets and refining the segmentation edges. The experimental results show that our network model demonstrates superior segmentation performance on both Potsdam and Vaihingen datasets, outperforming other state-of-the-art (SOTA) methods.
]]>Remote Sensing doi: 10.3390/rs16061037
Authors: Rui Gong Ling Wang Bin Wu Gong Zhang Daiyin Zhu
The Inverse Synthetic Aperture Radar (ISAR) has been proven to be an effective tool for space target sensing due to its capability of performing high-resolution imaging. Since the component information of the spacecraft is key to the identification of the target and diagnosis of its status, ISAR images with a clear and complete representation of the typical components are much desired. This requires a selection of the imaging time, during which a certain spacecraft component has a good projection on the ISAR image plane with the shape feature well conserved and a high resolution. In addition, a fully automated implementation with a high computational efficiency is also highly preferred for on-orbit operations so as to improve the intelligence level of the space-borne system. We propose a bicriterion-based automated optimal imaging time-selection method for the space-borne ISAR, which is seeking the slow time section of the data that result in the best image. A good image means a high azimuth resolution and the best presentation of the solar panels. One criterion is the Maximum Doppler Spread (MDS), which indicates the maximum Effective Rotational Velocity (ERV) leading to high image resolution, but it is influenced by the satellite attitude. of the spacecraft. The other is the Maximum Component Area (MCA), which is defined to indicate the completeness of the component considered. The radar echoes are processed sequentially by way of a sliding window. The interval with the co-maximization of the DS and CA is selected, and fine processing is performed further to obtain the best images. The results of the simulation experiments show that the proposed method can achieve spacecraft images with the solar panels presented the best. The computational complexity is low.
]]>Remote Sensing doi: 10.3390/rs16061035
Authors: Gang Chen Colleen Hammelman Sutee Anantsuksomsri Nij Tontisirin Amelia R. Todd William W. Hicks Harris M. Robinson Miles G. Calloway Grace M. Bell John E. Kinsey
This study aims to understand the spatiotemporal changes in patterns of tropical crop cultivation in Eastern Thailand, encompassing the periods before, during, and after the COVID-19 pandemic. Our approach involved assessing the efficacy of high-resolution (10 m) Sentinel-2 dense image time series for mapping smallholder farmlands. We integrated harmonic regression and random forest to map a diverse array of tropical crop types between summer 2017 and summer 2023, including durian, rice, rubber, eucalyptus, oil palm, pineapple, sugarcane, cassava, mangosteen, coconut, and other crops. The results revealed an overall mapping accuracy of 85.6%, with several crop types exceeding 90%. High-resolution imagery demonstrated particular effectiveness in situations involving intercropping, a popular practice of simultaneously growing two or more plant species in the same patch of land. However, we observed overestimation in the majority of the studied cash crops, primarily those located in young plantations with open tree canopies and grass-covered ground surfaces. The adverse effects of the COVID-19 pandemic were observed in specific labor-intensive crops, including rubber and durian, but were limited to the short term. No discernible impact was noted across the entirety of the study timeframe. In comparison, financial gain and climate change appeared to be more pivotal in influencing farmers’ decisions regarding crop cultivation. Traditionally dominant crops such as rice and oil palm have witnessed a discernible decline in cultivation, reflecting a decade-long trend of price drops preceding the pandemic. Conversely, Thai durian has seen a significant upswing even over the pandemic, which ironically served as a catalyst prompting Thai farmers to adopt e-commerce to meet the surging demand, particularly from China.
]]>Remote Sensing doi: 10.3390/rs16061034
Authors: Mengmeng Zhang Guijun Han Xiaobo Wu Chaoliang Li Qi Shao Wei Li Lige Cao Xuan Wang Wanqiu Dong Zenghua Ji
We explore to what extent data-driven prediction models have skills in forecasting daily sea-surface temperature (SST), which are comparable to or perform better than current physics-based operational systems over long-range forecast horizons. Three hybrid deep learning-based models are developed within the South China Sea (SCS) basin by integrating deep neural networks (back propagation, long short-term memory, and gated recurrent unit) with traditional empirical orthogonal function analysis and empirical mode decomposition. Utilizing a 40-year (1982–2021) satellite-based daily SST time series on a 0.25° grid, we train these models on the first 32 years (1982–2013) of detrended SST anomaly (SSTA) data. Their predictive accuracies are then validated using data from 2014 and tested over the subsequent seven years (2015–2021). The models’ forecast skills are assessed using spatial anomaly correlation coefficient (ACC) and root-mean-square error (RMSE), with ACC proving to be a stricter metric. A forecast skill horizon, defined as the lead time before ACC drops below 0.6, is determined to be 50 days. The models are equally capable of achieving a basin-wide average ACC of ~0.62 and an RMSE of ~0.48 °C at this horizon, indicating a 36% improvement in RMSE over climatology. This implies that on average the forecast skill horizon for these models is beyond the available forecast length. Analysis of one model, the BP neural network, reveals a variable forecast skill horizon (5 to 50 days) for each individual day, showing that it can adapt to different time scales. This adaptability seems to be influenced by a number of mechanisms arising from the evident regional and global atmosphere–ocean coupling variations on time scales ranging from intraseasonal to decadal in the SSTA of the SCS basin.
]]>Remote Sensing doi: 10.3390/rs16061033
Authors: Qing Cheng Ruixiang Xie Jingan Wu Fan Ye
Medium- to high-resolution imagery is indispensable for various applications. Combining images from Landsat 8 and Sentinel-2 can improve the accuracy of observing dynamic changes on the Earth’s surface. Many researchers use Sentinel-2 10 m resolution data in conjunction with Landsat 8 30 m resolution data to generate 10 m resolution data series. However, current fusion techniques have some algorithmic weaknesses, such as simple processing of coarse or fine images, which fail to extract image features to the fullest extent, especially in rapidly changing land cover areas. Facing the aforementioned limitations, we proposed a multiscale and attention mechanism-based residual spatiotemporal fusion network (MARSTFN) that utilizes Sentinel-2 10 m resolution data and Landsat 8 15 m resolution data as auxiliary data to upgrade Landsat 8 30 m resolution data to 10 m resolution. In this network, we utilized multiscale and attention mechanisms to extract features from coarse and fine images separately. Subsequently, the features outputted from all input branches are combined and further feature information is extracted through residual networks and skip connections. Finally, the features obtained from the residual network are merged with the feature information of the coarsely processed images from the multiscale mechanism to generate accurate prediction images. To assess the efficacy of our model, we compared it with existing models on two datasets. Results demonstrated that our fusion model outperformed baseline methods across various evaluation indicators, highlighting its ability to integrate Sentinel-2 and Landsat 8 data to produce 10 m resolution data.
]]>Remote Sensing doi: 10.3390/rs16061032
Authors: Giuseppe Ciccarese Melissa Tondo Marco Mulas Giovanni Bertolini Alessandro Corsini
The combined use of Uncrewed Aerial Vehicles (UAVs) with an integrated Real Time Kinematic (RTK) Global Navigation Satellite System (GNSS) module and an external GNSS base station allows photogrammetric surveys with centimeter accuracy to be obtained without the use of ground control points. This greatly reduces acquisition and processing time, making it possible to perform rapid monitoring of landslides by installing permanent and clearly recognizable optical targets on the ground. In this contribution, we show the results obtained in the Ca’ Lita landslide (Northern Apennines, Italy) by performing multi-temporal RTK-aided UAV surveys. The landslide is a large-scale roto-translational rockslide evolving downslope into an earthslide–earthflow. The test area extends 60 × 103 m2 in the upper track zone, which has recently experienced two major reactivations in May 2022 and March 2023. A catastrophic event took place in May 2023, but it goes beyond the purpose of the present study. A total of eight UAV surveys were carried out from October 2020 to March 2023. A total of eight targets were installed transversally to the movement direction. The results, in the active portion of the landslide, show that between October 2020 and March 2023, the planimetric displacement of targets ranged from 0.09 m (in the lateral zone) to 71.61 m (in the central zone). The vertical displacement values ranged from −2.05 to 5.94 m, respectively. The estimated positioning errors are 0.01 (planimetric) and 0.03 m (vertical). The validation, performed by using data from a permanent GNSS receiver, shows maximum differences of 0.18 m (planimetric) and 0.21 m (vertical). These results, together with the rapidity of image acquisition and data processing, highlight the advantages of using this rapid method to follow the evolution of relatively rapid landslides such as the Ca’ Lita landslide.
]]>Remote Sensing doi: 10.3390/rs16061030
Authors: Xiaofang Guo Zongru Yang Gang Ma Yi Yu Peng Zhang Banglin Zhang
The higher the atmosphere is, the larger the deviations in atmospheric temperature and humidity are between the vertical column atmosphere above the cross-section of a satellite instrument and a ray’s trajectory from the cross-section to the satellite. In general, satellite instruments that observe using cross-orbit scanning result in the difference between the observed radiance and the simulations using this method becoming incrementally larger and larger as the cross-section moves to the edge of the satellite’s orbit. The deviations depend on the distance from the column to the ray trajectory and on the horizontal gradient of variables in the distance. In fact, the horizontal gradient of water vapour is larger than the gradient of temperature in clear scenarios, which could introduce an impact of temperature and water vapour on the simulated radiance of a satellite. In this study, a new method to simulate upgoing and downgoing radiation synchronously was developed, using the observing path tracking method. The conventional vertical initial atmospheric profile (Exp.1) and the profiles along the upgoing and downgoing rays of the satellite’s observation (Exp.2) were established, in order to simulate the observed radiance of MWHS-II of FY-3D using global numerical forecasts with resolutions of 15 km and 25 km. The results showed that, for channels in the oxygen and water vapour absorption line on the microwave spectrum, deviations of the two atmospheric profiles were larger at the scan edge (0.01 K) than those at the nadir (0.001 K), and were larger in the upper atmosphere than in the lower atmosphere. The deviation was usually negative in low-latitude regions and was positive in southern high-latitude regions. Such results were obtained in experiments using both the numerical forecast method with 15 km grids and the forecast method with 25 km grids. Deviations were analysed for representative channels at 118 GHz and 183 GHz. Then, the results indicated that bigger deviations between the two experiments were observed in the water vapour absorption line than in the oxygen absorption line in the microwave spectrum. In conclusion, this indicates that, because of the greater horizontal gradient of water vapour, the stronger localisation of water vapour makes the atmospheric profile along the satellite’s observing ray have more increments in the simulated radiance at the scan edge, compared to the atmospheric column profile.
]]>Remote Sensing doi: 10.3390/rs16061031
Authors: Qifan Tan Xuqi Yang Cheng Qiu Yanhuan Jiang Jinze He Jingshuo Liu Yahui Wu
Onboard, real-time object detection in unmaned aerial vehicle remote sensing (UAV-RS) has always been a prominent challenge due to the higher image resolution required and the limited computing resources available. Due to the trade-off between accuracy and efficiency, the advantages of UAV-RS are difficult to fully exploit. Current sparse-convolution-based detectors only convolve some of the meaningful features in order to accelerate the inference speed. However, the best approach to the selection of meaningful features, which ultimately determines the performance, is an open question. This study proposes the use of adaptive sparse convolutional networks based on class maps for real-time onboard detection in UAV-RS images (SCCMDet) to solve this problem. For data pre-processing, SCCMDet obtains the real class maps as labels from the ground truth to supervise the feature selection process. In addition, a generate class map network (GCMN), equipped with a newly designed loss function, identifies the importance of features to generate a binary class map which filters the image for its more meaningful sparse features. Comparative experiments were conducted on the VisDrone dataset, and the experimental results show that our method accelerates YOLOv8 by 41.94% at most and increases the performance by 2.52%. Moreover, ablation experiments demonstrate the effectiveness of the proposed model.
]]>Remote Sensing doi: 10.3390/rs16061028
Authors: Weiwei Zhang Zixi Liu Kun Qin Shaoqing Dai Huiyuan Lu Miao Lu Jianwan Ji Zhaohui Yang Chao Chen Peng Jia
Accurate assessments of the historical and current status of eco-environmental quality (EEQ) are essential for governments to have a comprehensive understanding of regional ecological conditions, formulate scientific policies, and achieve the United Nations Sustainable Development Goals (SDGs). While various approaches to EEQ monitoring exist, they each have limitations and cannot be used universally. Moreover, previous studies lack detailed examinations of EEQ dynamics and its driving factors at national and local levels. Therefore, this study utilized a remote sensing ecological index (RSEI) to assess the EEQ of China from 2001 to 2021. Additionally, an emerging hot-spot analysis was conducted to study the spatial and temporal dynamics of the EEQ of China. The degree of influence of eight major drivers affecting EEQ was evaluated by a GeoDetector model. The results show that from 2001 to 2021, the mean RSEI values in China showed a fluctuating upward trend; the EEQ varied significantly in different regions of China, with a lower EEQ in the north and west and a higher EEQ in the northeast, east, and south in general. The spatio-temporal patterns of hot/cold spots in China were dominated by intensifying hot spots, persistent cold spots, and diminishing cold spots, with an area coverage of over 90%. The hot spots were concentrated to the east of the Hu Huanyong Line, while the cold spots were concentrated to its west. The oscillating hot/cold spots were located in the ecologically fragile agro-pastoral zone, next to the upper part of the Hu Huanyong Line. Natural forces have become the main driving force for changes in China’s EEQ, and precipitation and soil sand content were key variables affecting the EEQ. The interaction between these factors had a greater impact on the EEQ than individual factors.
]]>Remote Sensing doi: 10.3390/rs16061029
Authors: Pengfei Ma Ying Zhuo Genda Chen Joel G. Burken
Remote sensing detection of natural gas leaks remains challenging when using ground vegetation stress to detect underground pipeline leaks. Other natural stressors may co-present and complicate gas leak detection. This study explores the feasibility of identifying and distinguishing gas-induced stress from other natural stresses by analyzing the hyperspectral reflectance of vegetation. The effectiveness of this discrimination is assessed across three distinct spectral ranges (VNIR, SWIR, and Full spectra). Greenhouse experiments subjected three plant species to controlled environmental stressors, including gas leakage, salinity impact, heavy-metal contamination, and drought exposure. Spectral curves obtained from the experiments underwent preprocessing techniques such as standard normal variate, first-order derivative, and second-order derivative. Principal component analysis was then employed to reduce dimensionality in the spectral feature space, facilitating input for linear/quadratic discriminant analysis (LDA/QDA) to identify and discriminate gas leaks. Results demonstrate an average accuracy of 80% in identifying gas-stressed plants from unstressed ones using LDA. Gas leakage can be discriminated from scenarios involving a single distracting stressor with an accuracy ranging from 76.4% to 84.6%, with drought treatment proving the most successful. Notably, first-order derivative processing of VNIR spectra yields the highest accuracy in gas leakage detection.
]]>Remote Sensing doi: 10.3390/rs16061026
Authors: Sina Mohammadi Mariana Belgiu Alfred Stein
Recently, deep learning methods have achieved promising crop mapping results. Yet, their classification performance is constrained by the scarcity of labeled samples. Therefore, the development of methods capable of exploiting label-rich environments to classify crops in label-scarce environments using only a few labeled samples per class is required. Few-shot learning (FSL) methods have achieved this goal in computer vision for natural images, but they remain largely unexplored in crop mapping from time series data. In order to address this gap, we adapted eight FSL methods to map infrequent crops cultivated in the selected study areas from France and a large diversity of crops from a complex agricultural area situated in Ghana. The FSL methods are commonly evaluated using class-balanced unlabeled sets from the target domain data (query sets), leading to overestimated classification results. This is unrealistic since these sets can have an arbitrary number of samples per class. In our work, we used the Dirichlet distribution to model the class proportions in few-shot query sets as random variables. We demonstrated that transductive information maximization based on α-divergence (α-TIM) performs better than the competing methods, including dynamic time warping (DTW), which is commonly used to tackle the lack of labeled samples. α-TIM achieved, for example, a macro F1-score of 59.6% in Ghana in a 24-way 20-shot setting (i.e., 20 labeled samples from each of the 24 crop types) and a macro F1-score of 75.9% in a seven-way 20-shot setting in France, outperforming the second best-performing methods by 2.7% and 5.7%, respectively. Moreover, α-TIM outperformed a baseline deep learning model, highlighting the benefits of effectively integrating the query sets into the learning process.
]]>Remote Sensing doi: 10.3390/rs16061025
Authors: Nigenare Amantai Yuanyuan Meng Shanshan Song Zihui Li Bowen Hou Zhiyao Tang
There was an error in the original publication [...]
]]>Remote Sensing doi: 10.3390/rs16061027
Authors: Yichen Wu Junwei Qi Ying-Zhen Wang Yingsong Li
In mixed-field source localization, the physical properties of a sensor array, such as the degrees of freedom (DOFs), aperture, and coupling leakage, directly affect the accuracy of estimating the direction of arrival (DOA). Compared to conventional symmetric uniform linear arrays, symmetric non-uniform linear arrays (SNLAs) have a greater advantage in mixed-field source localization due to their larger aperture and higher DOF. However, current SNLAs require improvements in their physical properties through modifications to the array structure in order to achieve more accurate source localization estimates. Therefore, this study proposes a symmetric double-supplemented nested array (SDSNA), which translates nested subarrays based on symmetric nested arrays to increase the aperture and inserts two symmetric supplemented subarrays to fill the holes created by the translation. This method results in longer consecutive difference coarray lags and larger apertures. The SDSNA is compared to existing advanced SNLAs in terms of their physical properties and DOA estimation. The results show that, with the same number of sensors, the SDSNA has a higher DOF, a larger aperture, and smaller coupling, indicating the advantages of the SDSNA in terms of its physical properties. Under the same experimental conditions, the SDSNA has a lower root-mean-square error of source location, thus indicating better performance in terms of both DOA and distance estimation.
]]>Remote Sensing doi: 10.3390/rs16061024
Authors: Chen Chen Yuwei Chen Jianliang Zhu Changhui Jiang Jianxin Jia Yuming Bo Xuanzhi Liu Haojie Dai Eetu Puttonen Juha Hyyppä
Indoor positioning plays a crucial role in various domains. It is employed in various applications, such as navigation, asset tracking, and location-based services (LBS), in Global Navigation Satellite System (GNSS) denied or degraded areas. The visual-based positioning technique is a promising solution for high-accuracy indoor positioning. However, most visual positioning research uses the side-view perspective, which is susceptible to interferences and may cause concerns about privacy and public security. Therefore, this paper innovatively proposes an up-view visual-based indoor positioning algorithm. It uses the up-view images to realize indoor positioning. Firstly, we utilize a well-trained YOLO V7 model to realize landmark detection and gross extraction. Then, we use edge detection operators to realize the precision landmark extraction, obtaining the landmark pixel size. The target position is calculated based on the landmark detection and extraction results and the pre-labeled landmark sequence via the Similar Triangle Principle. Additionally, we also propose an inertial navigation system (INS)-based landmark matching method to match the landmark within an up-view image with a landmark in the pre-labeled landmark sequence. This is necessary for kinematic indoor positioning. Finally, we conduct static and kinematic experiments to verify the feasibility and performance of the up-view-based indoor positioning method. The results demonstrate that the up-view visual-based positioning is prospective and worthy of research.
]]>Remote Sensing doi: 10.3390/rs16061023
Authors: Hongzhou Wang Xiangtao Fan Hongdeng Jian Fuli Yan
Existing research indicates that detecting near-surface methane point sources using Sentinel-2 satellite imagery can offer crucial data support for mitigating climate change. However, current retrieval methods necessitate the identification of reference images unaffected by methane, which presents certain limitations. This study introduces the use of a matched filter, developing a novel methane detection algorithm for Sentinel-2 imagery. Compared to existing algorithms, this algorithm does not require selecting methane-free images from historical imagery in methane-sensitive bands, but estimates the background spectral information across the entire scene to extract methane gas signals. We tested the algorithm using simulated Sentinel-2 datasets. The results indicated that the newly proposed algorithm effectively reduced artifacts and noise. It was then validated in a known methane emission point source event and a controlled release experiment for its ability to quantify point source emission rates. The average estimated difference between the new algorithm and other algorithms was about 34%. Compared to the actual measured values in the controlled release experiment, the average estimated values ranged from −48% to 42% of the measurements. These estimates had a detection limit ranging from approximately 1.4 to 1.7 t/h and an average error percentage of 19%, with no instances of false positives reported. Finally, in a real case scenario, we demonstrated the algorithm’s ability to precisely locate the source position and identify, as well as quantify, methane point source emissions.
]]>Remote Sensing doi: 10.3390/rs16061022
Authors: Qiyu Li Xin Yao Renjiang Li Zhenkai Zhou Chuangchuang Yao Kaiyu Ren
The present study proposes a preliminary analysis method for rock mass joint acquisition, analysis, and slope stability assessment based on unmanned aerial vehicle (UAV) photogrammetry to extract the joint surface attitude in Geographic Information Systems (GIS). The method effectively solves the difficulties associated with the above issues. By combining terrain-following photogrammetry (TFP) and perpendicular and slope surface photogrammetry (PSSP), the three-dimensional (3D) information can be efficiently obtained along the slope characteristics’ surface, which avoids the information loss involved in traditional single-lens aerial photography and the information redundancy of the five-eye aerial photography. Then, a semi-automatic geoprocessing tool was developed within the ArcGIS Pro 3.0 environment, using Python for the extraction of joint surfaces. Multi-point fitting was used to calculate the joint surface attitude. The corresponding attitude symbols are generated at the same time. Finally, the joint surface attitude information is used to perform stereographic projection and kinematic analysis. The former can determine the dominant joint group, and the latter can obtain the probability of four types of failure, including planar sliding, wedge sliding, flexural toppling, and direct toppling. The integrated stability evaluation method studied in this paper, which combines a 3D interpretation of UAV and GIS stereographic projection statistical analysis, has the advantages of being efficient and user-friendly, and requires minimal prior knowledge. The results can aid in the geological surveys of slopes and guide engineering practices.
]]>Remote Sensing doi: 10.3390/rs16061021
Authors: Moonis Ali Bharat Lohani Markus Hollaus Norbert Pfeifer
Terrestrial LiDAR scanning (TLS) has the potential to revolutionize forestry by enabling the precise estimation of aboveground biomass, vital for forest carbon management. This study addresses the lack of comprehensive benchmarking for leaf-filtering algorithms used in TLS data processing and evaluates four widely recognized geometry-based leaf-filtering algorithms (LeWoS, TLSeparation, CANUPO, and a novel random forest model) across openly accessible TLS datasets from diverse global locations. Multiple evaluation dimensions are considered, including pointwise classification accuracy, volume comparisons using a quantitative structure model applied to wood points, computational efficiency, and visual validation. The random forest model outperformed the other algorithms in pointwise classification accuracy (overall accuracy = 0.95 ± 0.04), volume comparison (R-squared = 0.96, slope value of 0.98 compared to destructive volume), and resilience to reduced point cloud density. In contrast, TLSeparation exhibits the lowest pointwise classification accuracy (overall accuracy = 0.81 ± 0.10), while LeWoS struggles with volume comparisons (mean absolute percentage deviation ranging from 32.14 ± 29.45% to 49.14 ± 25.06%) and point cloud density variations. All algorithms show decreased performance as data density decreases. LeWoS is the fastest in terms of processing time. This study provides valuable insights for researchers to choose appropriate leaf-filtering algorithms based on their research objectives and forest conditions. It also hints at future possibilities for improved algorithm design, potentially combining radiometry and geometry to enhance forest parameter estimation accuracy.
]]>Remote Sensing doi: 10.3390/rs16061020
Authors: Luhao Wang Yabo Liu Qingxin Chen Xiaojie Zhou Shuang Zhu Shilong Chen
For the challenges of high-precision mapping in complex terrain, a novel airborne Interferometric Synthetic Aperture Radar (InSAR) system is designed. This system, named ASMIS (Airborne Short-Baseline Millimeter-Wave InSAR System), adopts the coplanar antenna and a pod-type structure. This design makes the system lightweight and highly integrated. It can be compatible with small general aviation flight platforms. The baseline is millimeters in size, which greatly simplifies the unwrapping process. The coplanar antennas have two advantages: they maximize the baseline utilization and minimize the Doppler decorrelation and the motion error inconsistency. Acquisition campaigns of the system have been carried out in Boao, Bayannur, and Chengde, China. In the Chengde experimental area, we designed an antiparallel flight experiment to account for the topographic relief. High-precision Digital Orthophoto Maps (DOMs) and Digital Surface Models (DSMs) at a scale of 1:5000 were obtained. The coordinate Root Mean Square Error (RMSE) of the checkpoints within the obtained DSM is less than 0.82 m in altitude and 3 m horizontally. The RMSE of the Sparse Ground Control Points (GCPs) within the obtained DSM is less than 0.3 m in altitude. Experimental results from different areas, including plains, mountains, and coastlines, demonstrate the system’s performance.
]]>Remote Sensing doi: 10.3390/rs16061019
Authors: Jules Mabon Mathias Ortner Josiane Zerubia
Convolutional neural networks (CNN) have shown great results for object-detection tasks by learning texture and pattern-extraction filters. However, object-level interactions are harder to grasp without increasing the complexity of the architectures. On the other hand, Point Process models propose to solve the detection of the configuration of objects as a whole, allowing the factoring in of the image data and the objects’ prior interactions. In this paper, we propose combining the information extracted by a CNN with priors on objects within a Markov Marked Point Process framework. We also propose a method to learn the parameters of this Energy-Based Model. We apply this model to the detection of small vehicles in optical satellite imagery, where the image information needs to be complemented with object interaction priors because of noise and small object sizes.
]]>Remote Sensing doi: 10.3390/rs16061018
Authors: Masanobu Kii Kunihiko Matsumoto Satoru Sugita
As of 2018, approximately 55% of the world’s population resides in cities, and it is projected that this proportion will reach 68% by 2050. Population growth in urban areas leads to various impacts on society and the environment. In this study, we have developed a method for generating future scenarios of nighttime lights. What makes this method unique is its ability to (1) generate future gridded nighttime light intensity scenarios for cities, (2) generate future scenarios that preserve the distribution pattern of nighttime light intensity, and (3) generate scenarios that reflect urban policies. By applying this developed method, we have estimated nighttime light data for 555 cities worldwide and predicted future urban expansion and changes in carbon emissions for each SSP scenario. Consequently, both urban areas and carbon emissions are estimated to increase for the entire set of target cities, with patterns varying among cities and scenarios. This study contributes to the advancement of urban scenario research, including the estimation of future urban area expansion and carbon emissions.
]]>Remote Sensing doi: 10.3390/rs16061017
Authors: Tianyu Wang Meng Xiang Fei Liu Jinpeng Liu Xue Dong Sen Wang Gang Li Xiaopeng Shao
High-resolution infrared remote sensing imaging is critical in planetary exploration, especially under demanding engineering conditions. However, due to diffraction, the spatial resolution of conventional methods is relatively low, and the spatial bandwidth product limits imaging systems’ design. Extensive research has been conducted with the aim of enhancing spatial resolution in remote sensing using a multi-aperture structure, but obtaining high-precision co-phase results using a sub-aperture remains challenging. A new high-resolution imaging method utilizing multi-aperture joint-encoding Fourier ptychography (JEFP) is proposed as a practical means to achieve super-resolution infrared imaging using distributed platforms. We demonstrated that the JEFP approach achieves pixel super-resolution with high efficiency, without requiring subsystems to perform mechanical scanning in space or to have high position accuracy. Our JEFP approach extends the application scope of Fourier ptychographic imaging, especially in distributed platforms for planetary exploration applications.
]]>Remote Sensing doi: 10.3390/rs16061016
Authors: Neda Rojhani George Shaker
Unmanned aerial vehicles (UAVs) are increasing in popularity in various sectors, simultaneously rasing the challenge of detecting those with low radar cross sections (RCS). This review paper aims to assess the current state-of-the-art in radar technology, focusing on multiple-input multiple-output (MIMO) and beamforming techniques, to address this growing concern. It explores the challenges associated with detecting UAVs in urban settings and adverse weather conditions, where traditional radar systems often do not succeed. This paper examines the existing literature and technological advancements to understand how these methodologies can significantly boost detection capabilities under the constraints of low RCS. In particular, MIMO technology, renowned for its spatial multiplexing, and beamforming, with its directional signal enhancement, are evaluated for their efficacy in the context of UAV surveillance and defense strategies. Ultimately, a comprehensive comparison is presented, drawing on a variety of studies to illustrate the combined potential of integrating these technologies, providing the way for future developments in radar system design and UAV detection.
]]>Remote Sensing doi: 10.3390/rs16061015
Authors: Pingping Huang Baoyu Li Xiujuan Li Weixian Tan Wei Xu Yuejuan Chen
Polarimetric target decomposition algorithms have played an important role in extracting the scattering characteristics of buildings, crops, and other fields. However, there is limited research on the scattering characteristics of grasslands and a lack of volume scattering models established for grasslands. To improve the accuracy of the polarimetric target decomposition algorithm applicable to grassland environments, this paper proposes an adaptive polarimetric target decomposition algorithm (APD) based on the anisotropy degree (A). The adaptive volume scattering model is used in APD to model volume scattering in forest and grassland regions separately by adjusting the value of A. When A > 1, the particle shape becomes a disk, and the grassland canopy is approximated as a cloud layer composed of randomly oriented disk particles; when A < 1, the particle shape is a needle, simulating the scattering mechanism of forests. APD is applied to an L-band AirSAR dataset from San Francisco, a C-band AirSAR dataset from Hunshandak grassland in Inner Mongolia Autonomous Region, and an X-band COSMO-SkyMed dataset from Xiwuqi grassland in Inner Mongolia Autonomous Region to verify the effectiveness of this method. Comparison studies are carried out to test the performance of APD over several target decomposition algorithms. The experimental results show that APD outperforms the algorithms tested in terms of this study in decomposition accuracy for grasslands and forests on different bands of data.
]]>Remote Sensing doi: 10.3390/rs16061013
Authors: Fuping Fang Yuanrong Tian Dahai Dai Shiqi Xing
Synthetic Aperture Radar (SAR) is a high-resolution imaging sensor commonly mounted on platforms such as airplanes and satellites for widespread use. In complex electromagnetic environments, radio frequency interference (RFI) severely degrades the quality of SAR images due to its widely varying bandwidth and numerous unknown emission sources. Although traditional deep learning-based methods have achieved remarkable results by directly processing SAR images as visual ones, there is still considerable room for improvement in their performance due to the wide coverage and high intensity of RFI. To address these issues, this paper proposes the fusion of segmentation and inpainting networks (FuSINet) to suppress SAR RFI in the time-frequency domain. Firstly, to weaken the dominance of RFI in SAR images caused by high-intensity interference, a simple CCN-based network is employed to learn and segment the RFI. This results in the removal of most of the original interference, leaving blanks that allow the targets to regain dominance in the overall image. Secondly, considering the wide coverage characteristic of RFI, a U-former network with global information capture capabilities is utilized to learn the content covered by the interference and fill in the blanks created by the segmentation network. Compared to the traditional Transformer, this paper enhances its global information capture capabilities through shift-windows and down-sampling layers. Finally, the segmentation and inpainting networks are fused together through a weighted parameter for joint training. This not only accelerates the learning speed but also enables better coordination between the two networks, leading to improved RFI suppression performance. Extensive experimental results demonstrate the substantial performance enhancement of the proposed FuSINet. Compared to the PISNet+, the proposed attention mechanism achieves a 2.49 dB improvement in peak signal-to-noise ratio (PSNR). Furthermore, compared to Uformer, the FuSINet achieves an additional 4.16 dB improvement in PSNR.
]]>Remote Sensing doi: 10.3390/rs16061014
Authors: Tianyu Liu Jinghua Chen Yuanjie Zhang Zhiqiu Gao
The Indian Summer Monsoon (ISM) can profoundly influence the summer precipitation patterns of the Tibetan Plateau (TP) and indirectly affect the TP’s soil humidity. This study investigates the responses of TP’s precipitation and soil moisture to the ISM in the monsoon season (June to September, JJAS) from 1979 to 2019. Precipitation in the TP and the ISM intensity generally exhibit a positive correlation in the west and a negative correlation in the east. The response of TP soil moisture to the ISM generally aligns with precipitation patterns, albeit with noted inconsistencies in certain TP regions. A region exhibiting these inconsistencies (30°–32°N, 80°–90°E) is selected as the study area, hereafter referred to as IRR. In periods of strong ISM, precipitation in IRR increases, yet soil moisture decreases. Conversely, in years with a weak ISM, the pattern is reversed. During strong ISM years, the rainfall increase in IRR is modest, and the soil remains drier compared to other TP regions. Under the combined effects of a marginal increase in precipitation and relatively rapid evaporation, soil moisture in the IRR decreased during years of strong ISM. During weak ISM years, the surface temperature in the IRR is higher compared to strong ISM years, potentially accelerating the melting of surface permafrost and snow in this region. Additionally, glacier meltwater, resulting from warmer temperatures in the northwest edge of the TP, may also result in the humidification of the soil in the IRR.
]]>Remote Sensing doi: 10.3390/rs16061012
Authors: Edson Costa-Filho José L. Chávez Huihui Zhang
This study focused on developing a novel semi-empirical model for maize’s light extinction coefficient (kp) by integrating multiple remotely sensed vegetation features from several different remote sensing platforms. The proposed kp model’s performance was independently evaluated using Campbell’s (1986) original and simplified kp approaches. The Limited Irrigation Research Farm (LIRF) in Greeley, Colorado, and the Irrigation Innovation Consortium (IIC) in Fort Collins, Colorado, USA, served as experimental sites for developing and evaluating the novel maize kp model. Data collection involved multiple remote sensing platforms, including Landsat-8, Sentinel-2, Planet CubeSat, a Multispectral Handheld Radiometer, and an unmanned aerial system (UAS). Ground measurements of leaf area index (LAI) and fractional vegetation canopy cover (fc) were included. The study evaluated the novel kp model through a comprehensive analysis using statistical error metrics and Sobol global sensitivity indices to assess the performance and sensitivity of the models developed for predicting maize kp. Results indicated that the novel kp model showed strong statistical regression fitting results with a coefficient of determination or R2 of 0.95. Individual remote sensor analysis confirmed consistent regression calibration results among Landsat-8, Sentinel-2, Planet CubeSat, the MSR, and UAS. A comparison with Campbell’s (1986) kp models reveals a 44% improvement in accuracy. A global sensitivity analysis identified the role of the normalized difference vegetation index (NDVI) as a critical input variable to predict kp across sensors, emphasizing the model’s robustness and potential practical environmental applications. Further research should address sensor-specific variations and expand the kp model’s applicability to a diverse set of environmental and microclimate conditions.
]]>Remote Sensing doi: 10.3390/rs16061011
Authors: Bernd Arendt Michael Schneider Winfried Mayer Thomas Walter
A tremendous number of landmines has been buried during the last decade. In recent years, various autonomous platforms equipped with ground-penetrating radars (GPRs) have been proposed for the detection of landmines. These systems have already demonstrated their performance in controlled environments with known ground truth. However, it has been observed that the influence of surface conditions in the form of vegetation and roughness as well as soil moisture content significantly reduce the detection probability. The influence of these individual factors on a ground-offset GPR is presented and discussed in this work. Each of these factors significantly degrades the backscattered signal. With increasing soil moisture, the signal gets attenuated more strongly; however, the signature is maintained in the phase of the C-Scans. An increase in surface roughness deteriorates the target pattern making it difficult to detect buried objects unambiguously. Vegetation, especially with irregular leaf structures, can appear as a ghost target and scatter the electromagnetic waves. In most cases, the target is easier to detect in the phase of the B- or C-Scan.
]]>Remote Sensing doi: 10.3390/rs16061010
Authors: Heting Sun Liguo Wang Haitao Liu Yinbang Sun
Hyperspectral image classification plays a crucial role in remote sensing image analysis by classifying pixels. However, the existing methods require more spatial–global information interaction and feature extraction capabilities. To overcome these challenges, this paper proposes a novel model for hyperspectral image classification using an orthogonal self-attention ResNet and a two-step support vector machine (OSANet-TSSVM). The OSANet-TSSVM model comprises two essential components: a deep feature extraction network and an improved support vector machine (SVM) classification module. The deep feature extraction network incorporates an orthogonal self-attention module (OSM) and a channel attention module (CAM) to enhance the spatial–spectral feature extraction. The OSM focuses on computing 2D self-attention weights for the orthogonal dimensions of an image, resulting in a reduced number of parameters while capturing comprehensive global contextual information. In contrast, the CAM independently learns attention weights along the channel dimension. The CAM autonomously learns attention weights along the channel dimension, enabling the deep network to emphasise crucial channel information and enhance the spectral feature extraction capability. In addition to the feature extraction network, the OSANet-TSSVM model leverages an improved SVM classification module known as the two-step support vector machine (TSSVM) model. This module preserves the discriminative outcomes of the first-level SVM subclassifier and remaps them as new features for the TSSVM training. By integrating the results of the two classifiers, the deficiencies of the individual classifiers were effectively compensated, resulting in significantly enhanced classification accuracy. The performance of the proposed OSANet-TSSVM model was thoroughly evaluated using public datasets. The experimental results demonstrated that the model performed well in both subjective and objective evaluation metrics. The superiority of this model highlights its potential for advancing hyperspectral image classification in remote sensing applications.
]]>Remote Sensing doi: 10.3390/rs16061009
Authors: Hongjian Jiao Xiaoxuan Tao Liang Chen Xin Zhou Zhanghai Ju
The Global Navigation Satellite System (GNSS) is widely used for its high accuracy, wide coverage, and strong real-time performance. However, limited by the navigation signal mechanism, satellite signals in urban canyons, bridges, tunnels, and other environments are seriously affected by non-line-of-sight and multipath effects, which greatly reduce positioning accuracy and positioning continuity. In order to meet the positioning requirements of human and vehicle navigation in complex environments, it was necessary to carry out this research on the integration of multiple signal sources. The Fifth Generation (5G) signal possesses key attributes, such as low latency, high bandwidth, and substantial capacity. Simultaneously, 5G Base Stations (BSs), serving as a fundamental mobile communication infrastructure, extend their coverage into areas traditionally challenging for GNSS technology, including indoor environments, tunnels, and urban canyons. Based on the actual needs, this paper proposes a system algorithm based on 5G and GNSS joint positioning, aiming at the situation that the User Equipment (UE) only establishes the connection with the 5G base station with the strongest signal. Considering the inherent nonlinear problem of user position and angle measurements in 5G observation, an angle cosine solution is proposed. Furthermore, enhancements to the Sage–Husa Adaptive Kalman Filter (SHAKF) algorithm are introduced to tackle issues related to observation weight distribution and adaptive updates of observation noise in multi-system joint positioning, particularly when there is a lack of prior information. This paper also introduces dual gross error detection adaptive correction of the forgetting factor based on innovation in the iterative Kalman filter to enhance accuracy and robustness. Finally, a series of simulation experiments and semi-physical experiments were conducted. The numerical results show that compared with the traditional method, the angle cosine method reduces the average number of iterations from 9.17 to 3 with higher accuracy, which greatly improves the efficiency of the algorithm. Meanwhile, compared with the standard Extended Kalman Filter (EKF), the proposed algorithm improved 48.66%, 35.17%, and 38.23% at 1σ/2σ/3σ, respectively.
]]>Remote Sensing doi: 10.3390/rs16061008
Authors: Yu Li Xiaoran Shi Xiaoning Wang Yongqiang Lu Peipei Cheng Feng Zhou
In complex electromagnetic environments, satellite telemetry, tracking, and command (TT&C) signals often become submerged in background noise. Traditional TT&C signal detection algorithms suffer a significant performance degradation or can even be difficult to execute when phase information is absent. Currently, deep-learning-based detection algorithms often rely on expert-experience-driven post-processing steps, failing to achieve end-to-end signal detection. To address the aforementioned limitations of existing algorithms, we propose an intelligent satellite TT&C signal detection method based on triplet attention and Transformer (TATR). TATR introduces the residual triplet attention (ResTA) backbone network, which effectively combines spectral feature channels, frequency, and amplitude dimensions almost without introducing additional parameters. In signal detection, TATR employs a multi-head self-attention mechanism to effectively address the long-range dependency issue in spectral information. Moreover, the prediction-box-matching module based on the Hungarian algorithm eliminates the need for non-maximum suppression (NMS) post-processing steps, transforming the signal detection problem into a set prediction problem and enabling parallel output of the detection results. TATR combines the global attention capability of ResTA with the local self-attention capability of Transformer. Experimental results demonstrate that utilizing only the signal spectrum amplitude information, TATR achieves accurate detection of weak TT&C signals with signal-to-noise ratios (SNRs) of −15 dB and above (mAP@0.5 > 90%), with parameter estimation errors below 3%, which outperforms typical target detection methods.
]]>Remote Sensing doi: 10.3390/rs16061007
Authors: Xingyuan Xiao Jing Zhang Yaqun Liu
Northeast China (NEC) is one of the most important national agricultural production bases, and its agricultural water dynamics are essential for food security and sustainable agricultural development. However, the dynamics of long-term annual crop-specific agricultural water and its crop type and climate impacts remain largely unknown, compromising water-saving practices and water-efficiency agricultural management in this vital area. Thus, this study used multi-source data of the crop type, climate factors, and the digital elevation model (DEM), and multiple digital agriculture technologies of remote sensing (RS), the geographic information system (GIS), the Soil Conservation Service of the United States Department of Agriculture (USDA-SCS) model, the Food and Agriculture Organization of the United Nations Penman–Monteith (FAO P-M) model, and the water supply–demand index (M) to map the annual spatiotemporal distribution of effective precipitation (Pe), crop water requirement (ETc), irrigation water requirement (IWR), and the supply–demand situation in the NEC from 2000 to 2020. The study further analyzed the impacts of the crop type and climate changes on agricultural water dynamics and revealed the reasons and policy implications for their spatiotemporal heterogeneity. The results indicated that the annual average Pe, ETc, IWR, and M increased by 1.56%/a, 0.74%/a, 0.42%/a, and 0.83%/a in the NEC, respectively. Crop-specifically, the annual average Pe increased by 1.15%/a, 2.04%/a, and 2.09%/a, ETc decreased by 0.46%/a, 0.79%/a, and 0.89%/a, IWR decreased by 1.03%/a, 1.32%/a, and 3.42%/a, and M increased by 1.48%/a, 2.67%/a, and 2.87%/a for maize, rice, and soybean, respectively. Although the ETc and IWR for all crops decreased, regional averages still increased due to the expansion of water-intensive maize and rice. The crop type and climate changes jointly influenced agricultural water dynamics. Crop type transfer contributed 39.28% and 41.25% of the total IWR increase, and the remaining 60.72% and 58.75% were caused by cropland expansion in the NEC from 2000 to 2010 and 2010 to 2020, respectively. ETc and IWR increased with increasing temperature and solar radiation, and increasing precipitation led to decreasing IWR in the NEC. The adjustment of crop planting structure and the implementation of water-saving practices need to comprehensively consider the spatiotemporally heterogeneous impacts of crop and climate changes on agricultural water dynamics. The findings of this study can aid RS-GIS-based agricultural water simulations and applications and support the scientific basis for agricultural water management and sustainable agricultural development.
]]>Remote Sensing doi: 10.3390/rs16061006
Authors: Chengkai Tang Jiawei Ding Lingling Zhang
Due to their low orbit, low-Earth-orbit (LEO) satellites possess advantages such as minimal transmission delay, low link loss, flexible deployment, diverse application scenarios, and low manufacturing costs. Moreover, by increasing the number of satellites, the system capacity can be enhanced, making them the core of future communication systems. However, there have been instances where malicious actors used LEO satellite communication equipment to illegally broadcast events in large sports stadiums or engage in unauthorized leakage of military secrets in sensitive military areas. This has become an urgent issue in the field of communication security. To combat and prevent abnormal and illegal communication activities using LEO satellites, this study proposes a LEO satellite downlink distributed jamming optimization method using a non-dominated sorting genetic algorithm. Firstly, a distributed jamming system model for the LEO satellite downlink is established. Then, using a non-dominated sorting genetic algorithm, the jamming parameters are optimized in the power, time, and frequency domains. Field jamming experiments were conducted in the southwest outskirts of Xi’an, China, targeting the LEO constellation of the China Satellite Network. The results indicate that under the condition that the jamming coverage rate is no less than 90%, the proposed method maximizes jamming power, minimizes time delay, and minimizes frequency compensation compared to existing jamming optimization methods, effectively improving the real-time jamming performance and success rate.
]]>Remote Sensing doi: 10.3390/rs16061005
Authors: Charlie Schrader-Patton Nancy E. Grulke Paul D. Anderson Jamieson Chaitman Jeremy Webb
The health of coniferous forests in the western U.S. is under threat from mega-drought events, increasing vulnerability to insects, disease, and mortality. Forest densification resulting from fire exclusion increases these susceptibilities. Silvicultural treatments to reduce stand density and promote resilience to both fire and drought have been used to reduce these threats but there are few quantitative evaluations of treatment effectiveness. This proof-of-concept study focused on such an evaluation, using field and remote sensing metrics of mature ponderosa pine (Pinus ponderosa Doug. Laws) in central Oregon. Ground metrics included direct measures of transpiration (sapflow), branch and needle measures and chlorosis; drone imagery included thermal (TIR) and five-band spectra (R, G, B, Re, NIR). Thermal satellite imagery was derived from ECOSTRESS, a space-borne thermal sensor that is on-board the International Space Station (ISS). All metrics were compared over 2 days at a time of maximum seasonal drought stress (August). Tree water status in unthinned, light, and heavy thinning from below density reduction treatments was evaluated. Tree crowns in the heavy thin site had greater transpiration and were cooler than those in the unthinned site, while the light thin site was not significantly cooler than either unthinned or the heavy thin site. There was a poor correlation (Adj. R2 0.10–0.13) between remotely sensed stand temperature and stand-averaged transpiration, and tree level temperature and transpiration (Adj. R2 0.04–0.19). Morphological attributes such as greater needle chlorosis and reduced elongation growth supported transpirational indicators of tree drought stress. The multispectral indices CCI and NDRE, along with the NIR and B bands, show promise as proxies for crown temperature and transpiration, and may serve as a proof of concept for an approach to evaluate forest treatment effectiveness in reducing tree drought stress.
]]>Remote Sensing doi: 10.3390/rs16061004
Authors: Chaofeng Yuan Jinghui Pan Zhaoxiang Zhang Min Qi Yuelei Xu
In the field of 3D point cloud data, the 3D representation of objects is often affected by factors such as lighting, occlusion, and noise, leading to issues of information loss and incompleteness in the collected point cloud data. Point cloud completion algorithms aim to generate complete object point cloud data using partial or local point cloud data as input. Despite promising results achieved by existing methods, current point cloud completion approaches often lack smooth and structural consistency, resulting in a messy overall structure. To address these shortcomings in point cloud completion, we propose a point cloud generative method based on surface consistency and scale rendering. In addition, to solve the limitation of existing methods that mainly focus on geometric features in 3D point cloud completion and do not make full use of color information, we introduce an object reconstruction method based on texture and geometric features. Extensive experiments demonstrate that our proposed methods exhibit superior performance in terms of local details and overall object structure.
]]>Remote Sensing doi: 10.3390/rs16061003
Authors: Feng Yu Ming Wang Jun Xiao Qian Zhang Jinmeng Zhang Xin Liu Yang Ping Rupeng Luan
Yield calculation is an important link in modern precision agriculture that is an effective means to improve breeding efficiency and to adjust planting and marketing plans. With the continuous progress of artificial intelligence and sensing technology, yield-calculation schemes based on image-processing technology have many advantages such as high accuracy, low cost, and non-destructive calculation, and they have been favored by a large number of researchers. This article reviews the research progress of crop-yield calculation based on remote sensing images and visible light images, describes the technical characteristics and applicable objects of different schemes, and focuses on detailed explanations of data acquisition, independent variable screening, algorithm selection, and optimization. Common issues are also discussed and summarized. Finally, solutions are proposed for the main problems that have arisen so far, and future research directions are predicted, with the aim of achieving more progress and wider popularization of yield-calculation solutions based on image technology.
]]>Remote Sensing doi: 10.3390/rs16061002
Authors: Dewei Zhao Faming Shao Qiang Liu Li Yang Heng Zhang Zihan Zhang
Due to the broad usage and widespread popularity of drones, the demand for a more accurate object detection algorithm for images captured by drone platforms has become increasingly urgent. This article addresses this issue by first analyzing the unique characteristics of datasets related to drones. We then select the widely used YOLOv7 algorithm as the foundation and conduct a comprehensive analysis of its limitations, proposing a targeted solution. In order to enhance the network’s ability to extract features from small objects, we introduce non-strided convolution modules and integrate modules that utilize attention mechanism principles into the baseline network. Additionally, we improve the semantic information expression for small targets by optimizing the feature fusion process in the network. During training, we adopt the latest Lion optimizer and MPDIoU loss to further boost the overall performance of the network. The improved network achieves impressive results, with mAP50 scores of 56.8% and 94.6% on the VisDrone2019 and NWPU VHR-10 datasets, respectively, particularly in detecting small objects.
]]>Remote Sensing doi: 10.3390/rs16061001
Authors: Kun Wu Zhijian Zhang Zeyu Chen Guohua Liu
Synthetic aperture radar (SAR) enables precise object localization and imaging, which has propelled the rapid development of algorithms for maritime ship identification and detection. However, most current deep learning-based algorithms tend to increase network depth to improve detection accuracy, which may result in the loss of effective features of the target. In response to this challenge, this paper innovatively proposes an object-enhanced network, OE-YOLO, designed specifically for SAR ship detection. Firstly, we input the original image into an improved CFAR detector, which enhances the network’s ability to localize and perform object extraction by providing more information through an additional channel. Additionally, the Coordinate Attention mechanism (CA) is introduced into the backbone of YOLOv7-tiny to improve the model’s ability to capture spatial and positional information in the image, thereby alleviating the problem of losing the position of small objects. Furthermore, to enhance the model’s detection capability for multi-scale objects, we optimize the neck part of the original model to integrate the Asymptotic Feature Fusion (AFF) network. Finally, the proposed network model is thoroughly tested and evaluated using publicly available SAR image datasets, including the SAR-Ship-Dataset and HRSID dataset. In comparison to the baseline method YOLOv7-tiny, OE-YOLO exhibits superior performance with a lower parameter count. When compared with other commonly used deep learning-based detection methods, OE-YOLO demonstrates optimal performance and more accurate detection results.
]]>Remote Sensing doi: 10.3390/rs16060998
Authors: Georgios Anagnostopoulos Anastasios Karkanis Athanasios Kampatagis Panagiotis Marhavilas Sofia-Anna Menesidou Dimitrios Efthymiadis Stefanos Keskinis Dimitar Ouzounov Nick Hatzigeorgiu Michael Danikas
In a recent paper, we extended a previous study on the solar solar influence to the generation of the March 2012 heatwave in the northeastern USA. In the present study we check the possible relationship of solar activity with the early March 2012 bad weather in northeast Thrace, Greece. To this end, we examined data from various remote sensing instrumentation monitoring the Sun (SDO satellite), Interplanetary space (ACE satellite), the Earth’s magnetosphere (Earth-based measurements, NOAA-19 satellite), the top of the clouds (Terra and Aqua satellites), and the near ground atmosphere. Our comparative data analysis suggests that: (i) the winter-like weather (rainfall, fast winds, decreased temperature) in Thrace started on 6 March 2012, the same day as the heatwave started in USA, (ii) during the March 2012 winter-like event in Thrace (6–15 March), the ACE satellite recorded enhanced fluxes of solar energetic particles (SEPs), while SOHO and PAMELA recorded solar protons at very high energies (>500 MeV), (iii) Between 3–31 March, the temperature in Alexandoupoli and the ACE/EPAM solar high energy (1.88–4.70 MeV) proton flux were strongly anticorelated (r = −0.75, p = 0.5). (iv) Thrace experienced particularly intense cyclonic circulation, during periods of magnetic storms on 8–10 and 12–13 March, which occurred after the arrival at ACE of two interplanetary shock waves, on March 8 and March 11, respectively, (v) at the beginning of the two above mentioned periods large atmospheric electric fields were recorded, with values ranging between ~−2000 V/m and ~1800 V/m on 8 March, (vi) the winter-like weather on 8–10 March 2012 occurred after the detection of the main SEP event related with a coronal mass ejection released in interplanetary space as a result of intense solar flare activity observed by SDO on 7 March 2012, (vi) the 8–10 March weather was related with a deep drop of ~63 °C in the cloud top temperature measured by MODIS/Terra, which favors strong precipitation. Finally, we analyzed data from the electric power network in Thrace (~41°N) and we found, for the first time sudden voltage changes of ~3.5 kV in the electric grid in Greece, during the decay phase of the March 2012 storm series. We discuss the winter-like March 2012 event in Thrace regarding the influence of solar cosmic rays on the low troposphere mediated by positive North Atlantic Oscillation (NAO). Finally, we infer that the novel finding of the geomagnetic effects on the electric power grid in Thrace may open a new window into space weather applications research.
]]>Remote Sensing doi: 10.3390/rs16061000
Authors: Ying Wang Xiaozhong Ding Jian Chen Kunying Han Chenglong Shi Ming Jin Liwei Liu Xinbao Liu Jiayin Deng
The Tsiolkovsky crater is located on the farside of the Moon. It formed in the late Imbrian epoch and was filled with a large area of mare basalts. Multisource remote sensing data are used to interpret the geological features of the Tsiolkovsky area. Compared with previous studies, new remote sensing data and a chronological model based on crater size–frequency distribution are used to further refine the stratigraphic units and determine the absolute ages of the mare basalt units. The evolution of volcanic activity in this crater is discussed. The results are as follows: Abundances of major elements, Th, and silicate minerals suggest that the mare basalt in the crater floor is not a uniform unit but rather nine units with different compositions. The nine basalt units are divided into two episodes of volcanic activity: The first occurred at 3.5–3.7 Ga, when highly evolved lava erupted at the crater floor at a large scale; the second occurred at ~3.4 Ga, when a small area of more primitive lava extended to the northern portion of the crater floor.
]]>Remote Sensing doi: 10.3390/rs16060999
Authors: Dariusz Gościewski Małgorzata Gerus-Gościewska Agnieszka Szczepańska
Due to the continuous increase in the volume of spatially located information, the current requirements imposed on the Spatial Information System (SIS) concern increasing data mining capabilities. Modern measurement systems, based on devices which enable the automatic recording of observation results on a mass scale (LiDAR—Light Detection and Ranging, MBES—Multi Beam Echo Sounder, etc.), allow for a very large volume of information on the surface to be measured and acquired in a relatively short time. One of the methods to reduce the volume of data enabling the generation of a model surface is to convert unevenly distributed measurement points into a regular network of squares (GRID). However, the generation of a complete grid is not always possible. In the measurement spectrum, there may be areas where measurement points have not been recorded. Measurement points can also be eliminated by either filtering the erroneously recorded data or eliminating the measured vegetation or the utilities in the area. To address these problems, the current article proposes a method for complementing the missing internal nodes in a regular network of squares using polynomial interpolation algorithms. Moreover, the paper demonstrates the possibilities of using the presented method for adding additional points between the already existing nodes of the network of squares. The application of the methodology presented in this article enables the effective elimination of (or a reduction in) the gaps in the GRID structure, which, in turn, allows such a network of squares to be used to generate a more accurate Digital Terrain Model.
]]>Remote Sensing doi: 10.3390/rs16060997
Authors: Jiale Duan Linyao Qiu Guangjun He Ling Zhao Zhenshi Zhang Haifeng Li
In synthetic aperture radar (SAR) imaging, intelligent object detection methods are facing significant challenges in terms of model robustness and application security, which are posed by adversarial examples. The existing adversarial example generation methods for SAR object detection can be divided into two main types: global perturbation attacks and local perturbation attacks. Due to the dynamic changes and irregular spatial distribution of SAR coherent speckle backgrounds, the attack effectiveness of global perturbation attacks is significantly reduced by coherent speckle. In contrast, by focusing on the image objects, local perturbation attacks achieve targeted and effective advantages over global perturbations by minimizing interference from the SAR coherent speckle background. However, the adaptability of conventional local perturbations is limited because they employ a fixed size without considering the diverse sizes and shapes of SAR objects under various conditions. This paper presents a framework for region-adaptive local perturbations (RaLP) specifically designed for SAR object detection tasks. The framework consists of two modules. To address the issue of coherent speckle noise interference in SAR imagery, we develop a local perturbation generator (LPG) module. By filtering the original image, this module reduces the speckle features introduced during perturbation generation. It then superimposes adversarial perturbations in the form of local perturbations on areas of the object with weaker speckles, thereby reducing the mutual interference between coherent speckles and adversarial perturbation. To address the issue of insufficient adaptability in terms of the size variation in local adversarial perturbations, we propose an adaptive perturbation optimizer (APO) module. This optimizer adapts the size of the adversarial perturbations based on the size and shape of the object, effectively solving the problem of adaptive perturbation size and enhancing the universality of the attack. The experimental results show that RaLP reduces the detection accuracy of the YOLOv3 detector by 29.0%, 29.9%, and 32.3% on the SSDD, SAR-Ship, and AIR-SARShip datasets, respectively, and the model-to-model and dataset-to-dataset transferability of RaLP attacks are verified.
]]>Remote Sensing doi: 10.3390/rs16060996
Authors: John Waczak Adam Aker Lakitha O. H. Wijeratne Shawhin Talebi Ashen Fernando Prabuddha M. H. Dewage Mazhar Iqbal Matthew Lary David Schaefer David J. Lary
Inland waters pose a unique challenge for water quality monitoring by remote sensing techniques due to their complicated spectral features and small-scale variability. At the same time, collecting the reference data needed to calibrate remote sensing data products is both time consuming and expensive. In this study, we present the further development of a robotic team composed of an uncrewed surface vessel (USV) providing in situ reference measurements and an unmanned aerial vehicle (UAV) equipped with a hyperspectral imager. Together, this team is able to address the limitations of existing approaches by enabling the simultaneous collection of hyperspectral imagery with precisely collocated in situ data. We showcase the capabilities of this team using data collected in a northern Texas pond across three days in 2020. Machine learning models for 13 variables are trained using the dataset of paired in situ measurements and coincident reflectance spectra. These models successfully estimate physical variables including temperature, conductivity, pH, and turbidity as well as the concentrations of blue–green algae, colored dissolved organic matter (CDOM), chlorophyll-a, crude oil, optical brighteners, and the ions Ca2+, Cl−, and Na+. We extend the training procedure to utilize conformal prediction to estimate 90% confidence intervals for the output of each trained model. Maps generated by applying the models to the collected images reveal small-scale spatial variability within the pond. This study highlights the value of combining real-time, in situ measurements together with hyperspectral imaging for the rapid characterization of water composition.
]]>Remote Sensing doi: 10.3390/rs16060995
Authors: Shuai Zhou Yue Wei Pengyu Lu Guangrui Yu Shuqi Wang Jian Jiao Ping Yu Jianwei Zhao
Gravity inversion can be used to obtain the spatial structure and physical properties of subsurface anomalies through gravity observation data. With the continuous development of machine learning, geophysical inversion methods based on deep learning have achieved good results. Geophysical inversion methods based on deep learning often employ large-scale data sets to obtain inversion networks with strong generalization. They are widely used but face a problem of lacking information constraints. Therefore, a self-constrained network is proposed to optimize the inversion results, composed of two networks with similar structures but different functions. At the same time, a fine-tuning strategy is also introduced. On the basis of data-driven deep learning, we further optimized the results by controlling the self-constrained network and optimizing fine-tuning strategy. The results of model testing show that the method proposed in this study can effectively improve inversion precision and obtain more reliable and accurate inversion results. Finally, the method is applied to the field data of Gonghe Basin, Qinghai Province, and the 3D inversion results are used to effectively delineate the geothermal storage area.
]]>Remote Sensing doi: 10.3390/rs16060993
Authors: Nianbin Zhang Yunjia Wang Feng Zhao Teng Wang Kewei Zhang Hongdong Fan Dawei Zhou Leixin Zhang Shiyong Yan Xinpeng Diao Rui Song
The collapse of open-pit coal mine slopes is a kind of severe geological hazard that may cause resource waste, economic loss, and casualties. On 22 February 2023, a large-scale collapse occurred at the Xinjing Open-Pit Mine in Inner Mongolia, China, leading to the loss of 53 lives. Thus, monitoring of the slope stability is important for preventing similar potential damage. It is difficult to fully obtain the temporal and spatial information of the whole mining area using conventional ground monitoring technologies. Therefore, in this study, multi-source remote sensing methods, combined with local geological conditions, are employed to monitor the open-pit mine and analyze the causes of the accident. Firstly, based on GF-2 data, remote sensing interpretation methods are used to locate and analyze the collapse area. The results indicate that high-resolution remote sensing can delineate the collapse boundary, supporting the post-disaster rescue. Subsequently, multi-temporal Radarsat-2 and Sentinel-1A satellite data, covering the period from mining to collapse, are integrated with D-InSAR and DS-InSAR technologies to monitor the deformation of both the collapse areas and the potential risk to dump slopes. The D-InSAR result suggests that high-intensity open-pit mining may be the dominant factor affecting deformation. Furthermore, the boundary between the collapse trailing edge and the non-collapse area could be found in the DS-InSAR result. Moreover, various data sources, including DEM and geological data, are combined to analyze the causes and trends of the deformation. The results suggest that the dump slopes are stable. Meanwhile, the deformation trends of the collapse slope indicate that there may be faults or joint surfaces of the collapse trailing edge boundary. The slope angle exceeding the designed value during the mining is the main cause of the collapse. In addition, the thawing of soil moisture caused by the increase in temperature and the reduction in the mechanical properties of the rock and soil due to underground voids and coal fires also contributed to the accident. This study demonstrates that multi-source remote sensing technologies can quickly and accurately identify potential high-risk areas, which is of great significance for pre-disaster warning and post-disaster rescue.
]]>Remote Sensing doi: 10.3390/rs16060994
Authors: Jiaqi Wang Rongcong Wang Dalin Li Tianran Sun Xiaodong Peng
Imaging has been an important strategy for exploring space weather. The Solar wind Magnetosphere Ionosphere Link Explorer (SMILE) is a joint Chinese Academy of Sciences (CAS) and European Space Agency (ESA) mission, aiming at studying the interaction between Earth’s magnetosphere and solar wind near the subsolar point via soft X-ray imaging. As the boundary of Earth’s magnetosphere, magnetopause is a significant detection target to mirror solar wind’s change for the SMILE mission. In preparation for inverting three-dimensional magnetopause, we proposed an OESA-UNet model to detect the magnetopause position. The model obtains magnetopause with a U-shaped structure, in an end-to-end manner. Inspired by attention mechanisms, these blocks are integrated into ours. OESA-UNet captures low and high-level feature maps by adjusting the receptive field for precise localization. Adaptively pre-processing the image provides a prior for the network. Availability metrics are designed to determine whether it can serve three-dimensional inversion. Lastly, we provided ablation and comparison experiments by qualitative and quantitative analysis. Our recall, precision, and f1 score are 93.8%, 92.1%, and 92.9%, respectively, with an average angle deviation of 0.005 under the availability metrics. Results indicate that OESA-UNet outperforms other methods. It can better serve the purpose of magnetopause tracing from an X-ray image.
]]>Remote Sensing doi: 10.3390/rs16060992
Authors: Zhihai Li Anchi Shi Xinran Li Jie Dou Sijia Li Tingxuan Chen Tao Chen
Landslide disasters pose a significant threat, with their highly destructive nature underscoring the critical importance of timely and accurate recognition for effective early warning systems and emergency response efforts. In recent years, substantial advancements have been made in the realm of landslide recognition (LR) based on remote sensing data, leveraging deep learning techniques. However, the intricate and varied environments in which landslides occur often present challenges in detecting subtle changes, especially when relying solely on optical remote sensing images. InSAR (Interferometric Synthetic Aperture Radar) technology emerges as a valuable tool for LR, providing more detailed ground deformation data and enhancing the theoretical foundation. To harness the slow deformation characteristics of landslides, we developed the FCADenseNet model. This model is designed to learn features and patterns within ground deformation data, with a specific focus on improving LR. A noteworthy aspect of our model is the integration of an attention mechanism, which considers various monitoring factors. This holistic approach enables the comprehensive detection of landslide disasters across entire watersheds, providing valuable information on landslide hazards. Our experimental results demonstrate the effectiveness of the FCADenseNet model, with an F1-score of 0.7611, which is 9.53% higher than that of FC_DenseNet. This study substantiates the feasibility and efficacy of combining InSAR with deep learning methods for LR. The insights gained from this research contribute to the advancement of regional landslide geological hazard monitoring, identification, and prevention strategies.
]]>Remote Sensing doi: 10.3390/rs16060991
Authors: Maurin Vidal Paul Jarrin Lucie Rolland Jean-Mathieu Nocquet Mathilde Vergnolle Pierre Sakic
GNSS is a standard tool for monitoring and studying the Earth’s dynamic environment. However, the development of dense GNSS measurements remains limited in many experiments by the cost of high-class geodetic equipment to achieve the high precision required by many applications. Recently, multi-constellation, multi-frequency, low-power and, above all, less expensive GNSS electronic chips have become available. We present a prototype of a low-cost, open-source multi-GNSS station. Our prototype comprises a dual-frequency GNSS chip, a calibrated antenna, a Raspberry Pi card and a 4G key for data transmission. The system is easy to deploy in the field and allows precise positioning in real-time and post-processing. We assess the performance of our prototype in terms of raw data quality, and quality of the obtained high rate and daily position one-year-long time series. Our results demonstrate a quality equivalent to high-class geodetic equipment and better quality than other low-cost systems proposed so far.
]]>Remote Sensing doi: 10.3390/rs16060989
Authors: Teng Ma Ye Yu Longxiang Dong Guo Zhao Tong Zhang Xuewei Wang Suping Zhao
Wind profiling within operating wind farms is important for both wind resource assessment and wind power prediction. With increasing wind turbine size, it is getting difficult to obtain wind profiles covering the turbine-affecting area due to the limited height of wind towers. In this study, a stepwise quality control and optimizing process for deriving high-quality near-surface wind profiles within wind farms is proposed. The method is based on the radial wind speed obtained by the Doppler Wind Lidar velocity-azimuth display (VAD) technique. The method is used to obtain the whole wind profile from ground level to the height affected by wind turbines within a utility-scale onshore wind farm, in northern China. Compared with the traditional carrier-to-noise ratio (CNR) filter-based quality control method, the proposed data processing method can significantly improve the accuracy of the derived wind. For a 10 m wind speed, an increase in coefficient of determination (R2) from 0.826 to 0.932, and a decrease in mean absolute error (MAE) from 1.231% to 0.927% are obtained; while for 70 m wind speed, R2 increased from 0.926 to 0.958, and MAE decreased from 1.023% to 0.771%. For wind direction, R2 increased from 0.978 to 0.992 at 10 m, and increased from 0.983 to 0.995 at 70 m. The optimized method also presents advantages in improving the accuracy of derived wind under complex wind environments, e.g., inside a wind farm, and increasing the data availability during clear nights. The proposed method could be used to derive wind profiles from below the minimum range of a vertically operating scanning Doppler Lidar to a height affected by wind turbines. Combined with Doppler beam-swinging (DBS) scanning data, the method could be used to obtain the complete wind profile in the boundary layer. These wind profiles could be further used to predict wind power and evaluate the climate and environmental effects of wind farms.
]]>Remote Sensing doi: 10.3390/rs16060990
Authors: Jinghui Yang Jia Qin Jinxi Qian Anqi Li Liguo Wang
In hyperspectral image (HSI) classification scenarios, deep learning-based methods have achieved excellent classification performance, but often rely on large-scale training datasets to ensure accuracy. However, in practical applications, the acquisition of hyperspectral labeled samples is time consuming, labor intensive and costly, which leads to a scarcity of obtained labeled samples. Suffering from insufficient training samples, few-shot sample conditions limit model training and ultimately affect HSI classification performance. To solve the above issues, an active learning (AL)-based multipath residual involution Siamese network for few-shot HSI classification (AL-MRIS) is proposed. First, an AL-based Siamese network framework is constructed. The Siamese network, which has relatively low demand for sample data, is adopted for classification, and the AL strategy is integrated to select more representative samples to improve the model’s discriminative ability and reduce the costs of labeling samples in practice. Then, the multipath residual involution (MRIN) module is designed for the Siamese subnetwork to obtain the comprehensive features of the HSI. The involution operation was used to capture the fine-grained features and effectively aggregate the contextual semantic information of the HSI through dynamic weights. The MRIN module comprehensively considers the local features, dynamic features and global features through multipath residual connections, which improves the representation ability of HSIs. Moreover, a cosine distance-based contrastive loss is proposed for the Siamese network. By utilizing the directional similarity of high-dimensional HSI data, the discriminability of the Siamese classification network is improved. A large number of experimental results show that the proposed AL-MRIS method can achieve excellent classification performance with few-shot training samples, and compared with several state-of-the-art classification methods, the AL-MRIS method obtains the highest classification accuracy.
]]>Remote Sensing doi: 10.3390/rs16060988
Authors: Nafees Ali Jian Chen Xiaodong Fu Rashid Ali Muhammad Afaq Hussain Hamza Daud Javid Hussain Ali Altalbe
Natural disasters, notably landslides, pose significant threats to communities and infrastructure. Landslide susceptibility mapping (LSM) has been globally deemed as an effective tool to mitigate such threats. In this regard, this study considers the northern region of Pakistan, which is primarily susceptible to landslides amid rugged topography, frequent seismic events, and seasonal rainfall, to carry out LSM. To achieve this goal, this study pioneered the fusion of baseline models (logistic regression (LR), K-nearest neighbors (KNN), and support vector machine (SVM)) with ensembled algorithms (Cascade Generalization (CG), random forest (RF), Light Gradient-Boosting Machine (LightGBM), AdaBoost, Dagging, and XGBoost). With a dataset comprising 228 landslide inventory maps, this study employed a random forest classifier and a correlation-based feature selection (CFS) approach to identify the twelve most significant parameters instigating landslides. The evaluated parameters included slope angle, elevation, aspect, geological features, and proximity to faults, roads, and streams, and slope was revealed as the primary factor influencing landslide distribution, followed by aspect and rainfall with a minute margin. The models, validated with an AUC of 0.784, ACC of 0.912, and K of 0.394 for logistic regression (LR), as well as an AUC of 0.907, ACC of 0.927, and K of 0.620 for XGBoost, highlight the practical effectiveness and potency of LSM. The results revealed the superior performance of LR among the baseline models and XGBoost among the ensembles, which contributed to the development of precise LSM for the study area. LSM may serve as a valuable tool for guiding precise risk-mitigation strategies and policies in geohazard-prone regions at national and global scales.
]]>Remote Sensing doi: 10.3390/rs16060987
Authors: Fengjia Sun Jungang Yang Wei Cui
Doppler mis-registrations in azimuth can lead to ocean waves shorter than a specific wavelength being undetectable by SAR. In order to evaluate the actual ocean wave observation ability, the accuracy of Sentinel-1 SAR ocean wave spectra from January 2016 to December 2021 is evaluated by comparisons to NDBC buoys, ERA5 wave height, and CMEMS buoys. The results compared with NDBC show that the spectral shape of Sentinel-1 SAR ocean wave spectra is accurate, while the spectral values need to be improved. The wave spectra of Sentinel-1 have the best observations in season autumn. The comparison results of total wave height show the RMSE and bias are 0.91 m and −0.52 m for the comparisons to NDBC buoy wave spectra data, 0.93 m and −0.68 m for the comparison to ERA5 wave height data, and 0.9 m and −0.35 m for the comparisons to CMEMS buoy data. The comparison results of wave height in different wind speeds and areas shows that the accuracy of Sentinel-1 wave mode data is relatively good in the open ocean located in middle and low latitude area under the medium wind speed, while those are relatively poor in high latitude areas or the areas with excessively high or low wind speed.
]]>Remote Sensing doi: 10.3390/rs16060986
Authors: Haoyuan Zhang Ning Chen Mei Li Shanjun Mao
Pavement crack detection is of significant importance in ensuring road safety and smooth traffic flow. However, pavement cracks come in various shapes and forms which exhibit spatial continuity, and algorithms need to adapt to different types of cracks while preserving their continuity. To address these challenges, an innovative crack detection framework, CrackDiff, based on the generative diffusion model, is proposed. It leverages the learning capabilities of the generative diffusion model for the data distribution and latent spatial relationships of cracks across different sample timesteps and generates more accurate and continuous crack segmentation results. CrackDiff uses crack images as guidance for the diffusion model and employs a multi-task UNet architecture to predict mask and noise simultaneously at each sampling step, enhancing the robustness of generations. Compared to other models, CrackDiff generates more accurate and stable results. Through experiments on the Crack500 and DeepCrack pavement datasets, CrackDiff achieves the best performance (F1 = 0.818 and mIoU = 0.841 on Crack500, and F1 = 0.841 and mIoU = 0.862 on DeepCrack).
]]>Remote Sensing doi: 10.3390/rs16060985
Authors: Mateusz Nijak Piotr Skrzypczyński Krzysztof Ćwian Michał Zawada Sebastian Szymczyk Jacek Wojciechowski
The precision of agro-technical operations is one of the main hallmarks of a modern approach to agriculture. However, ensuring the precise application of plant protection products or the performance of mechanical field operations entails significant costs for sophisticated positioning systems. This paper explores the integration of precision positioning based on the global navigation satellite system (GNSS) in agriculture, particularly in fieldwork operations, seeking solutions of moderate cost with sufficient precision. This study examines the impact of GNSSs on automation and robotisation in agriculture, with a focus on intelligent agricultural guidance. It also discusses commercial devices that enable the automatic guidance of self-propelled machinery and the benefits that they provide. This paper investigates GNSS-based precision localisation devices under real field conditions. A comparison of commercial and low-cost GNSS solutions, along with the integration of satellite navigation with advanced visual odometry for improved positioning accuracy, is presented. The research demonstrates that affordable solutions based on the common differential GNSS infrastructure can be applied for accurate localisation under real field conditions. It also underscores the potential of GNSS-based automation and robotisation in transforming agriculture into a more efficient and sustainable industry.
]]>Remote Sensing doi: 10.3390/rs16060981
Authors: Julia A. Barsi Eric Donley Michelle Goldman Thomas Kampe Brian L. Markham Brendan McAndrew Joel McCorkel Eric Morland Jeffrey A. Pedelty James Pharr Michael R. Rodriguez Timothy M. Shuman Cameron Stutheit Andrei B. Sushkov
The Landsat-9 satellite, launched in September 2021, carries the Operational Land Imager-2 (OLI-2) as one of its payloads. This instrument is a clone of the Landsat-8 OLI and its mission is to continue the operational land imaging of the Landsat program. The OLI-2 instrument is not significantly different from OLI though the instrument-level pre-launch spectral characterization process was much improved. The focal plane modules used on OLI-2 were manufactured as spares for OLI and much of the spectral characterization of the components was performed for OLI. However, while the spectral response of the fully assembled OLI was characterized by a double monochromator system, the OLI-2 spectral characterization made use of the Goddard Laser for Absolute Measurement of Radiance (GLAMR). GLAMR is a system of tunable lasers that cover 350–2500 nm which are fiber-coupled to a 30 in integrating sphere permanently monitored by NIST-traceable radiometers. GLAMR allowed the spectral characterization of every detector of the OLI-2 focal plane in nominal imaging conditions. The spectral performance of the OLI-2 was, in general, much better than requirements. The final relative spectral responses (RSRs) represent the best characterization any Landsat instrument spectral response. This paper will cover the results of the spectral characterization from the component-level to the instrument-level of the Landsat-9 OLI-2.
]]>Remote Sensing doi: 10.3390/rs16060983
Authors: Hongzhi Xiao Jinjie Wang Jianli Ding Xiang Li Keyu Chen
Soil moisture content is an important measure of soil health, and high-precision soil moisture trend analysis is essential for understanding regional ecological quality in the context of climate change, flood monitoring, and water cycle processes. However, in the arid regions of Central Asia, where data are severely lacking, obtaining high-spatial-resolution, continuous soil moisture data is difficult due to the scarcity of stations. Moreover, because soil moisture is easily affected by evaporation time, surface morphology, and anthropogenic factors, mature theoretical models or empirical or semiempirical models to measure soil moisture are also lacking. To investigate the distribution and trend of soil moisture in the Ebinur Lake water, in this study, microwave remote sensing and visible remote sensing data were selected as inputs, and the Global Land Data Assimilation System (GLDAS-2.2) data products were downscaled using the GTWR model, which increased the spatial scale from 27,830 m × 27,830 m to 30 m × 30 m. The phenomena involved in the soil moisture change cycle, spatial distribution, temporal variation, and internal randomness distance were analyzed in the study area through wavelet analysis, Theil–Sen trend analysis, the Mann–Kendall (MK) test, and a variogram. This study obtained high-resolution continuous soil moisture data in the arid and data-scarce region in Central Asia, thus broadening the field of multisource remote sensing analysis and providing a theoretical basis for the construction of precision agriculture in northwest China.
]]>Remote Sensing doi: 10.3390/rs16060984
Authors: Wei Tian Ping Song Yuanyuan Chen Haifeng Xu Cheng Jin Kenny Thiam Choy Lim Kam Sian
Tropical cyclones (TCs) can cause significant economic damage and loss of life in coastal areas. Therefore, TC prediction has become a crucial topic in current research. In recent years, TC track prediction has progressed considerably, and intensity prediction remains a challenge due to the complex mechanism of TC structure. In this study, we propose a model for short-term intensity prediction based on adaptive weight learning (AWL-Net) for the evolution of the TC’s structure as well as intensity changes, exploring the multidimensional fusion of features including TC morphology, structure, and scale. Furthermore, in addition to using satellite imageries, we construct a dataset that can more comprehensively explore the degree of TC cloud organization and structure evolution. Considering the information difference between multi-source data, a multi-branch structure is constructed and adaptive weight learning (AWL) is designed. In addition, according to the three-dimensional dynamic features of TC, 3D Convolutional Gated Recurrent (3D ConvGRU) is used to achieve feature enhancement, and then 3D Convolutional Neural Network (CNN) is used to capture and learn TC temporal and spatial features. Experiments on a sample of northwest Pacific TCs and official agency TC intensity prediction records are used to validate the effectiveness of our proposed model, and the results show that our model is able to focus well on the spatial and temporal features associated with TC intensity changes, with a root mean square error (RMSE) of 10.62 kt for the TC 24 h intensity forecast.
]]>Remote Sensing doi: 10.3390/rs16060982
Authors: Hui Li Jun Huang Zhezhen Xu Kunde Yang Jixing Qin
This paper introduces a model-independent passive source localization method, employing asynchronous distributed hydrophones in shallow water. Based on the frequency invariability of the acoustic field, assuming the correct source range information, the warped spectra of received signals at distributed hydrophones exhibit identical shapes. Subsequently, a cost function is formulated to mutually align the warped spectra, with its maximum point indicating the source location. The proposed method can locate the source in two-dimensional horizontal space without requiring either angle- or time-synchronization information. Numerical simulations are conducted to demonstrate the performance of the proposed method.
]]>Remote Sensing doi: 10.3390/rs16060980
Authors: Rui Yuan Ruiyang Xu Hezhenjia Zhang Cheng Qiu Jianrong Zhu
Estuarine reservoirs are critical for freshwater supply and security, especially for regions facing water scarcity challenges due to climate change and population growth. Conventional methods for assessing drought severity or monitoring reservoir water level and storage are often limited by data availability, accessibility and quality. We present an approach for monitoring estuarine reservoir water levels, storage and extreme drought via satellite remote sensing and waterline detection. Based on the CoastSat algorithm, Landsat-8 and Sentinel-2 images from 2013 to 2022 were adopted to extract the waterline of Qingcaosha Reservoir, the largest estuarine reservoir in the world and a key source of freshwater for Shanghai, China. This study confirmed the accuracy of the satellite-extracted results through two main methods: (1) calculating the angle of the central shoal slope in the reservoir using the extracted waterline data and measured water levels and (2) inverting the time series of water levels for comparison with measured data. The correlation coefficient of the estimated water level reached ~0.86, and the root mean square error (RMSE) of the estimated shoal slope was ~0.2°, indicating that the approach had high accuracy and reliability. We analyzed the temporal and spatial patterns of waterline changes and identified two dates (21 February 2014 and 15 October 2022) when the reservoir reached the lowest water levels, coinciding with periods of severe saltwater intrusions in the estuary. The extreme drought occurrences in the Qingcaosha Reservoir were firstly documented through the utilization of remote sensing data. The results also indicate a strong resilience of the Qingcaosha Reservoir and demonstrate that the feasibility and utility of using satellite remote sensing and waterline detection for estuarine reservoir storage can provide timely and accurate information for water resource assessment, management and planning.
]]>Remote Sensing doi: 10.3390/rs16060978
Authors: Wendi Liu Xiao Zhang Hong Xu Tingting Zhao Jinqing Wang Zhehua Li Liangyun Liu
Previous studies on global carbon emissions from forest loss have been marked by great discrepancies due to uncertainties regarding the lost area and the densities of different carbon pools. In this study, we employed a new global 30 m land cover dynamic dataset (GLC_FCS30D) to improve the assessment of forest loss areas; then, we combined multi-sourced carbon stock products to enhance the information on carbon density. Afterwards, we estimated the global carbon emissions from forest loss over the period of 1985–2020 based on the method recommended by the Intergovernmental Panel on Climate Change Guidelines (IPCC). The results indicate that global forest loss continued to accelerate over the past 35 years, totaling about 582.17 Mha and leading to total committed carbon emissions of 35.22 ± 9.38 PgC. Tropical zones dominated global carbon emissions (~2/3) due to their higher carbon density and greater forest loss. Furthermore, global emissions more than doubled in the period of 2015–2020 (1.77 ± 0.44 PgC/yr) compared to those in 1985–2000 (0.69 ± 0.21 PgC/yr). Notably, the forest loss at high altitudes (i.e., above 1000 m) more than tripled in mountainous regions, resulting in more pronounced carbon emissions in these areas. Therefore, the accelerating trend of global carbon emissions from forest loss indicates that great challenges still remain for achieving the COP 26 Declaration to halt forest loss by 2030.
]]>Remote Sensing doi: 10.3390/rs16060979
Authors: Shaohua Wang Xiao Li Liming Lin Hao Lu Ying Jiang Ning Zhang Wenda Wang Jianwei Yue Ziqiong Li
In the automated modeling generated by oblique photography, various terrains cannot be physically distinguished individually within the triangulated irregular network (TIN). To utilize the data representing individual features, such as a single building, a process of building monomer construction is required to identify and extract these distinct parts. This approach aids subsequent analyses by focusing on specific entities, mitigating interference from complex scenes. A deep convolutional neural network is constructed, combining U-Net and ResNeXt architectures. The network takes as input both digital orthophoto map (DOM) and oblique photography data, effectively extracting the polygonal footprints of buildings. Extraction accuracy among different algorithms is compared, with results indicating that the ResNeXt-based network achieves the highest intersection over union (IOU) for building segmentation, reaching 0.8255. The proposed “dynamic virtual monomer” technique binds the extracted vector footprints dynamically to the original oblique photography surface through rendering. This enables the selective representation and querying of individual buildings. Empirical evidence demonstrates the effectiveness of this technique in interactive queries and spatial analysis. The high level of automation and excellent accuracy of this method can further advance the application of oblique photography data in 3D urban modeling and geographic information system (GIS) analysis.
]]>Remote Sensing doi: 10.3390/rs16060977
Authors: Guokun Chen Jingjing Zhao Xingwu Duan Bohui Tang Lijun Zuo Xiao Wang Qiankun Guo
The mapping and dynamic monitoring of large-scale cropland erosion rates are critical for agricultural planning but extremely challenging. In this study, using field investigation data collected from 20,155 land parcels in 2817 sample units in the National Soil Erosion Survey, as well as land use change data for two decades from the National Land Use/Cover Database of China (NLUD-C), we proposed a new point-to-surface approach to quantitatively assess long-term cropland erosion based on the CSLE model and non-homologous data voting. The results show that cropland in Yunnan suffers from serious problems, with an unsustainable mean soil erosion rate of 40.47 t/(ha·a) and an erosion ratio of 70.11%, which are significantly higher than those of other land types. Engineering control measures (ECMS) have a profound impact on reducing soil erosion; the soil erosion rates of cropland with and without ECMs differ more than five-fold. Over the past two decades, the cropland area in Yunnan has continued to decrease, with a net reduction of 7461.83 km2 and a ratio of −10.55%, causing a corresponding 0.32 × 108 t (12.12%) reduction in cropland soil loss. We also quantified the impact of different LUCC scenarios on cropland erosion, and extraordinarily high variability was found in soil loss in different basins and periods. Conversion from cropland to forest contributes the most to cropland erosion reduction, while conversion from grassland to cropland contributes 56.18% of the increase in soil erosion. Considering the current speed of cropland regulation, it is the sharp reduction in land area that leads to cropland erosion reduction rather than treatments. The choice between the Grain for Green Policy and Cropland Protecting Strategy in mountainous areas should be made carefully, with understanding and collaboration between different roles.
]]>Remote Sensing doi: 10.3390/rs16060976
Authors: Aihong Cui Jianfeng Li Qiming Zhou Honglin Zhu Huizeng Liu Chao Yang Guofeng Wu Qingquan Li
Gaining a comprehensive understanding of the characteristics and propagation of precipitation-based meteorological drought to terrestrial water storage (TWS)-derived hydrological drought is of the utmost importance. This study aims to disentangle the frequency–time relationship between precipitation-derived meteorological and TWS-based hydrological drought from June 2002 to June 2017 based on the Standardized Precipitation Index (SPI) and Standardized Terrestrial Water Storage Index (STI) by employing wavelet coherence rather than a traditional correlation coefficient. The possible influencing factors on drought propagation in 28 regions across the world are examined. The results show that the number of drought months detected by the STI is higher than that detected by the SPI worldwide, especially for slight and moderate drought. Generally, TWS-derived hydrological drought is triggered by and occurs later than precipitation-based meteorological drought. The propagation characteristics between meteorological and hydrological droughts vary by region across the globe. Apparent intra-annual and interannual scales are detected by wavelet analysis in most regions, but not in the polar climate region. Drought propagation differs in phase lags in different regions. The phase lag between hydrological and meteorological drought ranges from 0.5 to 4 months on the intra-annual scale and from 1 to 16 months on the interannual scale. Drought propagation is influenced by multiple factors, among which the El Niño–Southern Oscillation, North Atlantic Oscillation, and potential evapotranspiration are the most influential when considering one, two, or three factors, respectively. The findings of this study improve scientific understanding of drought propagation mechanisms over a global scale and provide support for water management in different subregions.
]]>Remote Sensing doi: 10.3390/rs16060975
Authors: Yun Zhou Sensen Wang Haohao Ren Junyi Hu Lin Zou Xuegang Wang
Deep learning-based ship-detection methods have recently achieved impressive results in the synthetic aperture radar (SAR) community. However, numerous challenging issues affecting ship detection, such as multi-scale characteristics of the ship, clutter interference, and densely arranged ships in complex inshore, have not been well solved so far. Therefore, this article puts forward a novel SAR ship-detection method called multi-level feature-refinement anchor-free framework with a consistent label-assignment mechanism, which is capable of boosting ship-detection performance in complex scenes. First, considering that SAR ship detection is susceptible to complex background interference, we develop a stepwise feature-refinement backbone network to refine the position and contour of the ship object. Next, we devise an adjacent feature-refined pyramid network following the backbone network. The adjacent feature-refined pyramid network consists of the sub-pixel sampling-based adjacent feature-fusion sub-module and adjacent feature-localization enhancement sub-module, which can improve the detection capability of multi-scale objects by mitigating multi-scale high-level semantic loss and enhancing low-level localization features. Finally, to solve the problems of unbalanced positive and negative samples and densely arranged ship detection, we propose a consistent label-assignment mechanism based on consistent feature scale constraints to assign more appropriate and consistent labels to samples. Extensive qualitative and quantitative experiments on three public datasets, i.e., SAR Ship-Detection Dataset (SSDD), High-Resolution SAR Image Dataset (HRSID), and SAR-Ship-Dataset illustrate that the proposed method is superior to many state-of-the-art SAR ship-detection methods.
]]>Remote Sensing doi: 10.3390/rs16060973
Authors: Chengjuan Gong Ranyu Yin Tengfei Long Weili Jiao Guojin He Guizhou Wang
Clouds often cause challenges during the application of optical satellite images. Masking clouds and cloud shadows is a crucial step in the image preprocessing workflow. The absence of a thermal band in products of the Sentinel-2 series complicates cloud detection. Additionally, most existing cloud detection methods provide binary results (cloud or non-cloud), which lack information on thin clouds and cloud shadows. This study attempted to use end-to-end supervised spatial–temporal deep learning (STDL) models to enhance cloud detection in Sentinel-2 imagery for China. To support this workflow, a new dataset for time-series cloud detection featuring high-quality labels for thin clouds and haze was constructed through time-series interpretation. A classification system consisting of six categories was employed to obtain more detailed results and reduce intra-class variance. Considering the balance of accuracy and computational efficiency, we constructed four STDL models based on shared-weight convolution modules and different classification modules (dense, long short-term memory (LSTM), bidirectional LSTM (Bi-LSTM), and transformer). The results indicated that spatial and temporal features were crucial for high-quality cloud detection. The STDL models with simple architectures that were trained on our dataset achieved excellent accuracy performance and detailed detection of clouds and cloud shadows, although only four bands with a resolution of 10 m were used. The STDL models that used the Bi-LSTM and that used the transformer as the classifier showed high and close overall accuracies. While the transformer classifier exhibited slightly lower accuracy than that of Bi-LSTM, it offered greater computational efficiency. Comparative experiments also demonstrated that the usable data labels and cloud detection results obtained with our workflow outperformed the results of the existing s2cloudless, MAJA, and CS+ methods.
]]>