Remote Sensing

Monitoring shoreline movements is essential for understanding the impact of anthropogenic activities and climate change on the coastal zone dynamics. The use of remote sensing allows for large-scale spatial and temporal studies to better comprehend current trends. This study used Landsat 5 (TM), Landsat 8 (OLI), and Sentinel-2 (MSI) remote sensing images, together with the Otsu algorithm, marching squares algorithm, and tidal correction algorithm, to extract and correct the coastline positions of the east coast of Laizhou Bay in China from 1984 to 2022. The results indicate that 89.63% of the extracted shoreline segments have an error less than 30 m compared to the manually drawn coastline. The total length of the coastline increased from 166.90 km to 364.20 km, throughout the observation period, with a length change intensity (LCI) of 3.11% due to the development of coastal protection and engineering structures for human activities. The anthropization led to a decrease in the natural coastline from 83.33% to 13.89% and a continuous increase in the diversity and human use of the coastline. In particular, the index of coastline diversity (ICTD) and the index of coastline utilization degree (ICUD) increased from 0.39 to 0.79, and from 153.30 to 390.37, respectively. Over 70% of the sandy beaches experienced erosional processes. The shoreline erosion calculated using the end point rate (EPR) and the linear regression rate (LRR) is 79.54% and 85.58%, respectively. The fractal dimension of the coastline shows an increasing trend and is positively correlated with human activities. Coastline changes are primarily attributed to interventions such as land reclamation, aquaculture development, and port construction resulting in the creation of 10,000.20 hectares of new coastal areas. Finally, the use of Kalman filtering for the first time made it possible to predict that approximately 84.58% of the sandy coastline will be eroded to varying degrees by 2032. The research results can provide valuable reference for the scientific planning and rational utilization of resources on the eastern coast of Laizhou Bay. Full article

The increasing availability and quality of remote sensing data are changing the methods used in fluvial geomorphology applications, allowing the observation of hydro-morpho-biodynamics processes and their spatial and temporal variations at broader and more refined scales. With the advent of cloud-based computing, it is nowadays possible to reduce data processing time and increase code sharing, facilitating the development of reproducible analyses at regional and global scales. The consolidation of Earth Observation mission data into a single repository such as Google Earth Engine (GEE) offers the opportunity to standardize various methods found in literature, in particular those related to the identification of key geomorphological parameters. This work investigates different computational techniques and timeframes (e.g., seasonal, annual) for the automatic detection of the active river channel and its multi-temporal aggregation, proposing a rational integration of remote sensing tools into river monitoring and management. In particular, we propose a quantitative analysis of different approaches to obtain a synthetic representative image of river corridors, where each pixel is computed as a percentile of the bands (or a combination of bands) of all available images in a given time span. Synthetic images have the advantage of limiting the variability of individual images, thus providing more robust results in terms of the classification of the main components of the riverine ecosystem (sediments, water, and riparian vegetation). We apply the analysis to a set of rivers with analogous bioclimatic conditions and different levels of anthropic pressure, using a combination of Landsat and Sentinel-2 data. The results show that synthetic images derived from multispectral indexes (such as NDVI and MDWI) are more accurate than synthetic images derived from single bands. In addition, different temporal reduction statistics affect the detection of the active channel, and we suggest using the 90th percentile instead of the median to improve the detection of vegetated areas. Individual representative images are then aggregated into multitemporal maps to define a systematic and easily replicable approach for extracting active river corridors and their inherent spatial and temporal dynamics. Finally, the proposed procedure has the potential to be easily implemented and automated as a tool to provide relevant data to river managers. Full article

Accurate atmospheric correction (AC) is one fundamental and essential step for successful ocean colour remote-sensing applications. Currently, most ACs and the associated ocean colour remote-sensing applications are restricted to solar zenith angles (SZAs) lower than 70°. The ACs under high SZAs present degraded accuracy or even failure problems, rendering the satellite retrievals of water quality parameters more challenging. Additionally, the complexity of the bio-optical properties of the coastal waters and the presence of complex aerosols add to the difficulty of AC. To address this challenge, this study proposed an AC algorithm based on extreme gradient boosting (XGBoost) for optically complex waters under high SZAs. The algorithm presented in this research has been developed using pairs of Geostationary Ocean Colour Imager (GOCI) high-quality noontime remote-sensing reflectance (Rrs) and the Rayleigh-corrected reflectance (ρ_rc) derived from the Ocean Colour–Simultaneous Marine and Aerosol Retrieval Tool (OC-SMART) in the morning (08:55 LT) and at dusk (15:55 LT). The algorithm was further examined using the daily GOCI images acquired in the morning and at dusk, and the hourly (total suspended sediment) TSS concentration was also obtained based on the atmospherically corrected GOCI data. The results showed that: (i) the model produced an accurate fitting performance (R² ≥ 0.90, RMSD ≤ 0.0034 sr⁻¹); (ii) the model had a high validation accuracy with an independent dataset (R² = 0.92–0.97, MAPD = 8.2–26.81% and quality assurance (QA) score = 0.9–1); and (iii) the model successfully retrieved more valid Rrs for GOCI images under high SZAs and enhanced the accuracy and coverage of TSS mapping. This algorithm has great potential to be applied to AC for optically complex waters under high SZAs, thus increasing the frequency of available observations in a day. Full article

When natural disasters occur, timely and accurate building damage assessment maps are vital for disaster management responders to organize their resources efficiently. Pairs of pre- and post-disaster remote sensing imagery have been recognized as invaluable data sources that provide useful information for building damage identification. Recently, deep learning-based semantic segmentation models have been widely and successfully applied to remote sensing imagery for building damage assessment tasks. In this study, a two-stage, dual-branch, UNet architecture, with shared weights between two branches, is proposed to address the inaccuracies in building footprint localization and per-building damage level classification. A newly introduced selective kernel module improves the performance of the model by enhancing the extracted features and applying adaptive receptive field variations. The xBD dataset is used to train, validate, and test the proposed model based on widely used evaluation metrics such as F1-score and Intersection over Union (IoU). Overall, the experiments and comparisons demonstrate the superior performance of the proposed model. In addition, the results are further confirmed by evaluating the geographical transferability of the proposed model on a completely unseen dataset from a new region (Bam city earthquake in 2003). Full article

Global navigation satellite systems (GNSSs) applied to intelligent transport systems in urban areas suffer from multipath and non-line-of-sight (NLOS) effects due to the signal reflections from high-rise buildings, which seriously degrade the accuracy and reliability of vehicles in real-time applications. Accordingly, the integration between GNSS and inertial navigation systems (INSs) could be utilized to improve positioning performance. However, the fixed GNSS solution uncertainty of the conventional integration method cannot determine the fluctuating GNSS reliability in fast-changing urban environments. This weakness becomes solvable using a deep learning model for sensing the ambient environment intelligently, and it can be further mitigated using factor graph optimization (FGO), which is capable of generating robust solutions based on historical data. This paper mainly develops the adaptive GNSS/INS loosely coupled system on FGO, along with the fixed-gain Kalman filter (KF) and adaptive KF (AKF) being taken as comparisons. The adaptation is aided by a convolutional neural network (CNN), and the feasibility is verified using data from different grades of receivers. Compared with the integration using fixed-gain KF, the proposed adaptive FGO (AFGO) maintains the 100% positioning availability and reduces the overall 2D positioning error by up to 70% in the aspects of both root mean square error (RMSE) and standard deviation (STD). Full article

Hyperspectral images (HSIs) are widely used to identify and characterize objects in scenes of interest, but they are associated with high acquisition costs and low spatial resolutions. With the development of deep learning, HSI reconstruction from low-cost and high-spatial-resolution RGB images has attracted widespread attention. It is an inexpensive way to obtain HSIs via the spectral reconstruction (SR) of RGB data. However, due to a lack of consideration of outdoor solar illumination variation in existing reconstruction methods, the accuracy of outdoor SR remains limited. In this paper, we present an attention neural network based on an adaptive weighted attention network (AWAN), which considers outdoor solar illumination variation by prior illumination information being introduced into the network through a basic 2D block. To verify our network, we conduct experiments on our Variational Illumination Hyperspectral (VIHS) dataset, which is composed of natural HSIs and corresponding RGB and illumination data. The raw HSIs are taken on a portable HS camera, and RGB images are resampled directly from the corresponding HSIs, which are not affected by illumination under CIE-1964 Standard Illuminant. Illumination data are acquired with an outdoor illumination measuring device (IMD). Compared to other methods and the reconstructed results not considering solar illumination variation, our reconstruction results have higher accuracy and perform well in similarity evaluations and classifications using supervised and unsupervised methods. Full article

The Cartagena Bay in Colombia has vital economic and environmental importance, playing a fundamental role in both the port and tourism sectors. Unfortunately, the water quality of the bay is undergoing a deterioration process due to the significant influx of sediment from the artificial channel known as Canal del Dique. Although field campaigns are carried out semiannually with 12 monitoring stations to evaluate these impacts, understanding the spatial dynamics of suspended solids in the bay remains a challenge. This article presents a spatial analysis of water turbidity in the Cartagena Bay during the years 2018 to 2022, using Sentinel-2 images. To achieve this objective, an empirical algorithm was developed through the Monte Carlo simulation. The validation of the algorithm demonstrated an R-squared value of 0.83, with an RMSE of 2.72 and a MAPE of 24.93%. The results showed the seasonal variability, with higher turbidity levels during the rainy season, reaching up to 35 FNU, and lower turbidities during the dry season, dropping to 1 FNU. Furthermore, these findings indicated that the southern area of the bay presents the most significant turbidity variations. This research enhances our understanding of the bay’s turbidity dynamics and suggests an additional tool for its monitoring. Full article

In polarimetric synthetic aperture radar (POLSAR), it is of great significance for civil and military applications to find novel model-based decomposition methods suitable for ship detection in different detection backgrounds. Based on the physical interpretation of polarimetric decomposition theory and the Lasso rule for sparse features, we propose a four-component decomposition model, which is composed of surface scattering (Odd), double-bounce scattering (Dbl), volume scattering (Vol), and ±45° oriented dipole (Od). In principle, the Od component can describe the compounded scattering structure of a ship consisting of odd-bounce and even-bounce reflectors. Moreover, the pocket perceptron learning algorithm (PPLA) and support vector machine (SVM) are utilized to solve the linear inseparable problems in this study. Using large amounts of RADARSAT-2 (RS-2) fully polarized SAR data and AIRSAR data, our experimental results show that the Od component can make a great contribution to ship detection. Compared with other conventional decomposition methods used in the experiments, the proposed four-component decomposition method has better performance and is more effective and feasible to detect ships. Full article

Gravitational processes on cut slopes located close to infrastructure are a high concern in mountainous regions. There are many techniques for survey, assessment, and prognosis of hazardous exogenous geological processes. The given research describes using UAV data and GIS morphometric analysis for delineation of hazardous rockfall zones and 3D modelling to obtain an enhanced, detailed evaluation of slope characteristics. Besides the slope geomorphometric data, we integrated discontinuity layers, including rock plains orientation and fracture network density. Cloud Compare software 2.12 was utilised for facet extraction. Fracture discontinuity analysis was performed in QGIS using the Network GT plugin. The presented research uses an Analytical Hierarchy Process (AHP) to determine the weight of each contributing factor. GIS overlay of weighted factors is applied for rockfall susceptibility mapping. This integrated approach allows for a more comprehensive GIS-based rockfall susceptibility mapping by considering both the structural characteristics of the outcrop and the geomorphological features of the slope. By combining UAV data, GIS-based morphometric analysis, and discontinuity analysis, we are able to delineate hazardous rockfall zones effectively. Full article

The optical complexity of coastal waters is mostly caused by the water discharged from land carrying optical components (such as dissolved and particulate matter) into coastal bays and estuaries, and increasing the attenuation of light. This paper aims to investigate the links between in-water optical properties in four Swedish bays (from the northern Baltic proper up to the Bothnian bay) and the land use and land cover (LULC) in the respective catchment of each bay. The optical properties were measured in situ over the last decade by various research and monitoring groups while the LULC in each bay was classified using the Copernicus Land Monitoring Service based on Landsat 8/OLI data. The absorption coefficient of colored dissolve organic matter (CDOM) at 440 nm, a_CDOM (440), was significantly correlated to Wetlands which may act as sources of CDOM, while Developed areas (Agricultural and Urban classes) were negatively correlated. The Agriculture class was also negatively related to suspended particulate organic matter (SPOM), whilst Coniferous Forests and Mixed Forests as well as Meadows were positively correlated. SPOM seems thus to mostly originate from Natural classes, possibly due to the release of pollen and other organic matter. Overall, the methods applied here allow for a better understanding of effects of land use and land cover on the bio-optical properties, and thus coastal water quality, on a macroscopic scale. Full article

Remote sensing technology is widely used to obtain evapotranspiration (ET_a), but whether it can distinguish the differences in farmland energy balance components and ET_a under different irrigation methods has not been studied. We used Landsat 8 data as the primary dataset to drive the METRIC model and inverted the surface parameters and ET_a of the Shiyang River Basin from 2014 to 2018. After improving the METRIC model using T_a obtained by the regression method instead of interpolation to calculate the net radiation flux (R_n), R² was improved from 0.45 to 0.53, and the RMSE was reduced from 61 W/m² to 51 W/m². The ET_a estimation results on satellite overpass days performed well, with R² equal to 0.93 and RMSE equal to 0.48 mm when compared with the Eddy covariance method (EC) observations. Subsequently, the different growth stages and daily average ET_a estimates of maize were compared with three observations (water balance, WB; Bowen ratio and energy balance method, BREB; and EC). The daily estimates of ET_a correlate well with the observations of BREB (R²_BI = 0.82, R²_DI = 0.92; RMSE_BI = 0.46 mm/day, RMSE_DI = 0.32 mm/day) and EC (R²_BI = 0.85, R²_DI = 0.92; RMSE_BI = 0.45 mm/day, RMSE_DI = 0.34 mm/day), and the estimation for drip irrigation was found to be better than for border irrigation. The total accuracy of the ET_a estimation on the five-year overpass day of maize farmland reached R² = 0.93 and RMSE = 0.48 mm. With sufficient remote sensing data, the 4-year average ET_a of maize was 31 mm lower for DI than for BI, and the mean value of ET_a obtained from the three observation methods was 40 mm. The METRIC model can be used to distinguish ET_a differences between the two irrigation methods in maize farmlands. Full article

Indoor mobile robots can be localized by using scene classification methods. Recently, two-dimensional (2D) LiDAR has achieved good results in semantic classification with target categories such as room and corridor. However, it is difficult to achieve the classification of different rooms owing to the lack of feature extraction methods in complex environments. To address this issue, a scene classification method based on a multi-scale convolutional neural network (CNN) with long short-term memory (LSTM) and a whale optimization algorithm (WOA) is proposed. Firstly, the distance data obtained from the original LiDAR are converted into a data sequence. Secondly, a scene classification method integrating multi-scale CNN and LSTM is constructed. Finally, WOA is used to tune critical training parameters and optimize network performance. The actual scene data containing eight rooms are collected to conduct ablation experiments, highlighting the performance with the proposed algorithm with 98.87% classification accuracy. Furthermore, experiments with the FR079 public dataset are conducted to demonstrate that compared with advanced algorithms, the classification accuracy of the proposed algorithm achieves the highest of 94.35%. The proposed method can provide technical support for the precise positioning of robots. Full article

Riverbed materials serve multiple environmental functions as a habitat for aquatic invertebrates and fish. At the same time, the particle size of the bed material reflects the tractive force of the flow regime in a flood and provides useful information for flood control. The traditional riverbed particle size surveys, such as sieving, require time and labor to investigate riverbed materials. The authors of this study have proposed a method to classify aerial images taken by unmanned aerial vehicles (UAVs) using convolutional neural networks (CNNs). Our previous study showed that terrestrial riverbed materials could be classified with high accuracy. In this study, we attempted to classify riverbed materials of terrestrial and underwater samples including that which is distributed in shallow waters where the bottom can be seen using UAVs over the river segment. It was considered that the surface flow types taken overlapping the riverbed material on images disturb the accuracy of classification. By including photographs of various surface flow conditions in the training data, the classification focusing on the patterns of riverbed materials could be achieved. The total accuracy reached 90.3%. Moreover, the proposed method was applied to the river segments to determine the distribution of the particle size. In parallel, the microtopography was surveyed using a LiDAR UAV, and the relationship between the microtopography and particle size distribution was discussed. In the steep section, coarse particles were distributed and formed riffles. Fine particles were deposited on the upstream side of those riffles, where the slope had become gentler due to the dammed part. The good concordance between the microtopographical trends and the grain size distribution supports the validity of this method. Full article

This article provides insights into the optical signatures of plastic litter based on a published laboratory-scale reflectance data set (350–2500 $\mathrm{nm}$) of dry and wet plastic debris under clear and turbid waters using different band selection techniques, including sparse variable selection, density peak clustering, and hierarchical clustering. The variable selection method identifies important wavelengths by minimizing a reconstruction error metric, while clustering approaches rely on the strengths of the correlation and local density of the spectra. Analyses of the data reveal three distinct absorption lines at 560, 740, and 980 $\mathrm{nm}$ that produce relatively broad reflectance peaks in the measured spectra of wet plastics around 475–490, 635–650, 810–815, and 1070 $\mathrm{nm}$. The results of band selection consistently identify three important regions across 450–470, 650–690, and 1050–1100 $\mathrm{nm}$ that are close to the reflectance peaks of the mean of wet plastic spectra over clear and turbid waters. However, as the number of isolated important wavelengths increases, the results of the methodologies diverge. Density peak clustering identifies additional wavelengths in the short-wave infrared (SWIR) region of 1170–1180 $\mathrm{nm}$) as a result of a high local density of the reflectance points. In contrast, hierarchical clustering isolates more wavelengths in the visible range of 365–400 $\mathrm{nm}$ due to weak correlations of nearby wavelengths. The results of the clustering methods are not consistent with the visual inspection of the signatures as peaks and valleys in the spectra, which are effectively captured by the variable selection method. It is also found that the presence of suspended sediments can (i) shift the important wavelength towards higher values in the visible part of the spectrum by less than 50 $\mathrm{nm}$, (ii) attenuate the magnitude of wet plastic reflectance by up to 80% across the entire spectrum, and (iii) manifest a similar spectral signature with plastic litter from 1070 to 1100 $\mathrm{nm}$. Full article

Several satellite missions are currently available to provide thermal infrared data at different spatial resolutions and revisit time. Furthermore, new missions are planned thus enabling to keep a nearly continuous ‘eye’ on thermal volcanic activity around the world. This massive volume of data requires the development of artificial intelligence (AI) techniques for the automatic processing of satellite data in order to extract significant information about volcano conditions in a short time. Here, we propose a robust machine learning approach to accurately detect, recognize and quantify high-temperature volcanic features using Sentinel-2 MultiSpectral Instrument (S2-MSI) imagery. We use the entire archive of high spatial resolution satellite data containing more than 6000 S2-MSI scenes at ten different volcanoes around the world. Combining a ‘top-down’ cascading architecture, two different machine learning models, a scene classifier (SqueezeNet) and a pixel-based segmentation model (random forest), we achieved a very high accuracy, namely 95%. These results show that the cascading approach can be applied in near-real time to any available satellite image, providing a full description of the scene, with an important contribution to the monitoring, mapping and characterization of volcanic thermal features. Full article

Evapotranspiration (E) is one of the most uncertain components of the global water cycle (WC). Improving global E estimates is necessary to improve our understanding of climate and its impact on available surface water resources. This work presents a methodology for deriving monthly corrections to global E datasets at 0.25${}^{\circ }$ resolution. A principled approach is proposed to firstly use indirect information from the other water components to correct E estimates at the catchment level, and secondly to extend this sparse catchment-level information to global pixel-level corrections using machine learning (ML). Several E satellite products are available, each with its own errors (both random and systematic). Four such global E datasets are used to validate the proposed approach and highlight its ability to extract seasonal and regional systematic biases. The resulting E corrections are shown to accurately generalize WC closure constraints to unseen catchments. With an average deviation of 14% from the original E datasets, the proposed method achieves up to 20% WC residual reduction on the most favorable dataset. Full article

Building extraction refers to the automatic identification and separation of buildings from the background in remote sensing images. It plays a significant role in urban planning, land management, and disaster monitoring. Deep-learning methods have shown advantages in building extraction, but they still face challenges such as variations in building types, object occlusions, and complex backgrounds. To address these issues, SDSNet, a deep convolutional network that incorporates global multi-scale feature extraction and cross-level feature fusion, is proposed. SDSNet consists of three modules: semantic information extraction (SIE), multi-level merge (MLM), and semantic information fusion (SIF). The SIE module extracts contextual information and improves recognition of multi-scale buildings. The MLM module filters irrelevant details guided by high-level semantic information, aiding in the restoration of edge details for buildings. The SIF module combines filtered detail information with extracted semantic information for refined building extraction. A series of experiments conducted on two distinct public datasets for building extraction consistently demonstrate that SDSNet outperforms the state-of-the-art deep-learning models for building extraction tasks. On the WHU building dataset, the overall accuracy (OA) and intersection over union (IoU) achieved impressive scores of 98.86% and 90.17%, respectively. Meanwhile, on the Massachusetts dataset, SDSNet achieved OA and IoU scores of 94.05% and 71.6%, respectively. SDSNet exhibits a unique advantage in recovering fine details along building edges, enabling automated and intelligent building extraction. This capability effectively supports urban planning, resource management, and disaster monitoring. Full article

Due to their advantages of high measurement accuracy and wide coverage, global navigation satellite systems (GNSSs) can carry out long-distance time transfers, among which the precise point positioning (PPP) method is widely used. However, the accuracy and stability of PPP real-time time transfer are restricted by the real-time satellite clock offset products. In addition, the receiver clock offset is usually estimated using the white noise model, which ignores the correlation of the clock offsets between adjacent epochs and the stability of the atomic clock itself. In order to obtain higher performance time transfer results, we propose an interstation undifferenced time transfer method with refined modeling of the receiver clock. This method takes the satellite clock offset as the parameter to be estimated, which can avoid the influence of external satellite clock offset products. In addition, the refined modeling of the receiver clock can improve the strength of the model and the accuracy of time transfer. Based on the ultrarapid satellite orbit products provided by the International GNSS Service (IGS), time transfer experiments are carried out using data from IGS observatories and self-collected data. The results show that sub-nanosecond accuracy can be achieved in real-time time transfer using this method. Compared with the traditional PPP model, the accuracies of the four time links are increased by 88.4%, 92.9%, 88.6%, and 74.5%, respectively, and the stability is increased by approximately 66.4% on average. Moreover, after applying the clock offset constraint model, frequency stability is further improved, in which the short-term stability is improved significantly, with a maximum of 86.9% and an average improvement of approximately 66.8%. Full article

Underwater Sound Speed Profile (SSP) distribution is crucial for the propagation mode of acoustic signals, so fast and accurate estimation of SSP is of great importance in building underwater observation systems. The state-of-the-art SSP inversion methods include frameworks of matched field processing (MFP), compressive sensing (CS), and feed-forward neural networks (FNNs), among which the FNN shows better real-time performance while maintaining the same level of accuracy. However, the training of FNN needs quite a lot historical SSP samples, which is difficult to satisfy in many ocean areas. This situation is called few-shot learning. To tackle this issue, we propose a multi-task learning (MTL) model with partial parameter sharing among different training tasks. By MTL, common features could be extracted, which accelerates the learning process on given tasks, and reduces the demand for reference samples, enhancing the generalization ability in few-shot learning. To verify the feasibility and effectiveness of MTL, a deep-ocean experiment was held in April 2023 in the South China Sea. Results show that MTL outperforms the other mainstream methods in terms of accuracy for SSP inversion, while inheriting the real-time advantage of FNN during the inversion stage. Full article