Carbon dioxide (CO₂) fluxes and evapotranspiration (ET) during the non-growing season can contribute significantly to the annual carbon and water budgets of agroecosystems. Comparative studies of vegetation phenology and the dynamics of CO₂ fluxes and ET during the dormant season of native tallgrass prairies from different landscape positions under the same climatic regime are scarce. Thus, this study compared the dynamics of satellite-derived vegetation phenology (as captured by the enhanced vegetation index (EVI) and the normalized difference vegetation index (NDVI)) and eddy covariance (EC)-measured CO₂ fluxes and ET in six differently managed native tallgrass prairie pastures during dormant seasons (November through March). During December–February, vegetation phenology (EVI and NDVI) and the dynamics of eddy fluxes were comparable across all pastures in most years. Large discrepancies in fluxes were observed during March (the time of the initiation of growth of dominant warm-season grasses) across years and pastures due to the influence of weather conditions and management practices. The results illustrated the interactive effects between prescribed spring burns and rainfall on vegetation phenology (i.e., positive and negative impacts of prescribed spring burns under non-drought and drought conditions, respectively). The EVI better tracked the phenology of tallgrass prairie during the dormant season than did NDVI. Similar EVI and NDVI values for the periods when flux magnitudes were different among pastures and years, most likely due to the satellite sensors’ inability to fully observe the presence of some cool-season C₃ species under residues, necessitated a multi-level validation approach of using ground-truth observations of species composition, EC measurements, PhenoCam (digital) images, and finer-resolution satellite data to further validate the vegetation phenology derived from the Moderate Resolution Imaging Spectroradiometer (MODIS) during dormant seasons. This study provides novel insights into the dynamics of vegetation phenology, CO₂ fluxes, and ET of tallgrass prairie during the dormant season in the U.S. Southern Great Plains. Full article

The disposal of unexploded ordnance (UXOs) at sea is a global problem. The mapping and remediation of historic UXOs can be assisted by autonomous underwater vehicles (AUVs) carrying sensor payloads such as synthetic aperture sonar (SAS) and optical cameras. AUVs can image large areas of the seafloor in high resolution, motivating an automated approach to UXO detection. Modern methods commonly use supervised machine learning which requires labelled examples from which to learn. This work investigates the often-overlooked labelling process and resulting dataset using an example historic UXO dumpsite at Skagerrak. A counterintuitive finding of this work is that optical images cannot be relied on for ground truth as a significant number of UXOs visible in SAS images are not in optical images, presumed buried. Given the lack of ground truth, we use an ordinal labelling scheme to incorporate a measure of labeller uncertainty. We validate this labelling regime by quantifying label accuracy compared to optical labels with high confidence. Using this approach, we explore different taxonomies and conclude that grouping objects into shells, bombs, debris, and natural gave the best trade-off between accuracy and discrimination. Full article

Construction and protection of ecological networks (ENs) is considered to be an effective means to curb habitat fragmentation and strengthen landscape connectivity. In this study, a complete evaluation framework of ENs based on “quality–function–structure” was proposed to support the formulation of protection strategies for ENs. First, we built the ENs of Wuhan urban agglomeration (WUA) from 2000 to 2020 based on the advantages of circuit theory and remote sensing data of land use monitoring. The results showed that land development activities are an important driving force for the temporal and spatial evolution of global ENs. Forest fragmentation, transitional urban expansion, and agricultural reclamation were important inducements for the shrinkage of ecological sources. They may also increase the resistance of species migration, which will lead to qualitative change and even fracture of ecological corridors. Second, circuit theory, centrality index, and complex network theory were applied to evaluate the quality defects, functional connectivity, and topology characteristics of ENs in WUA, respectively, from 2000 to 2020. The results showed that the antagonism between ecological corridors and land development activities led to ecological quality defects (ecological barriers and pinchpoints). Different land development models had differential effects on centrality indexes. Moreover, the main trunk in the northern Dabie Mountains and the southern Mufu mountains was developed, while the secondary trunks were abundant in the middle of WUA. Finally, we proposed protection strategies for ENs based on the coupling of the “quality–function–structure” of WUA in 2020. It is suggested that all ecological sources must be included in nature reserves to prevent natural or manmade erosion. The key areas to be repaired were determined through the quality evaluation of ecological corridors. The priority of construction and protection of ecological corridors was determined by coupling two topological structures and functions. We argue that specific protection strategies and directions can be determined according to the construction objectives of local ENs. Full article

Satellite-derived rugged land surface temperature (LST) is an important parameter indicating the status of the Earth’s surface energy budget and its seasonal/temporal dynamic change. However, existing LST products from rugged areas are more prone to error when supporting applications in mountainous areas and Earth surface processes that occur at high spatial and temporal resolutions. This research aimed to develop a method for generating rugged LST with a high temporal and spatial resolution by using an improved ensemble LST model combining three regressors, including a random forest, a ridge, and a support vector machine. Different combinations of high-resolution input parameters were also considered in this study. The input datasets included Moderate Resolution Imaging Spectroradiometer (MODIS) LST datasets (MxD11A1) for nighttime, temporal Sentinel-2 Multispectral Instrument (MSI) datasets, and digital elevation model (DEM) datasets. The 30 m rugged LST datasets derived were compared against an in situ LST dataset obtained at Saihanba Forest Park (SFP) sites and an ASTER-derived 90 m LST, respectively. The results with in situ measurements demonstrated significant LST details, with an R² higher than 0.95 and RMSE around 3.00 K for both Terra/MOD- and Aqua/MYD-based LST datasets, and with slightly better results being obtained from the Aqua/MYD-based LST than that from Terra/MOD. The inter-comparison results with ASTER LST showed that over 80% of the pixels of the difference image for the two datasets were within 2 K. In light of the complex topography and distinct atmospheric conditions, these comparison results are encouraging. The 30 m LST from the method proposed in this study also depicts the seasonality of rugged surfaces. Full article

Due to imaging and lighting directions, shadows are inevitably formed in unmanned aerial vehicle (UAV) images. This causes shadowed regions with missed and occluded information, such as color and texture details. Shadow detection and compensation from remote sensing images is essential for recovering the missed information contained in these images. Current methods are mainly aimed at processing shadows with simple scenes. For UAV remote sensing images with a complex background and multiple shadows, problems inevitably occur, such as color distortion or texture information loss in the shadow compensation result. In this paper, we propose a novel shadow removal algorithm from UAV remote sensing images based on color and texture equalization compensation of local homogeneous regions. Firstly, the UAV imagery is split into blocks by selecting the size of the sliding window. The shadow was enhanced by a new shadow detection index (SDI) and threshold segmentation was applied to obtain the shadow mask. Then, the homogeneous regions are extracted with LiDAR intensity and elevation information. Finally, the information of the non-shadow objects of the homogeneous regions is used to restore the missed information in the shadow objects of the regions. The results revealed that the average overall accuracy of shadow detection is 98.23% and the average F1 score is 95.84%. The average color difference is 1.891, the average shadow standard deviation index is 15.419, and the average gradient similarity is 0.726. The results have shown that the proposed method performs well in both subjective and objective evaluations. Full article

The main objective of this research work was to study the accuracy of GNSS code receivers under poor sky visibility conditions based on measurements on three different objects (point, line, and surface) and additionally to test results on point positioning with good sky visibility conditions. The measurement was based on 3 smartphones (in the same mode to check repeatability) and 2 handheld receivers (working in GPS+GLONASS modes). The methodology was based on the RTK technique, whose coordinates were assumed as a reference. Based on the results, the significant influence of measuring in the vicinity of high trees on the obtained accuracy was observed for both the precise geodetic equipment and the tested code receivers. More favorable results of point positioning were observed when using mobile phones. On the other hand, in the case of measurement in motion, the handheld receivers guaranteed higher accuracy. Moreover, the study showed that handheld receivers might achieve a better accuracy than smartphones, and that position might be determined with a greater accuracy and reliability. Furthermore, handheld receivers were characterized by a smaller number of outliers. Full article

Phase filtering is a vital step for interferometric synthetic aperture radar (InSAR) terrain elevation measurements. Existing phase filtering methods can be divided into two categories: traditional model-based and deep learning (DL)-based. Previous studies have shown that DL-based methods are frequently superior to traditional ones. However, most of the existing DL-based methods are purely data-driven and neglect the filtering model, so that they often need to use a large-scale complex architecture to fit the huge training sets. The issue brings a challenge to improve the accuracy of interferometric phase filtering without sacrificing speed. Therefore, we propose a sparse-model-driven network (SMD-Net) for efficient and high-accuracy InSAR phase filtering by unrolling the sparse regularization (SR) algorithm to solve the filtering model into a network. Unlike the existing DL-based filtering methods, the SMD-Net models the physical process of filtering in the network and contains fewer layers and parameters. It is thus expected to ensure the accuracy of the filtering without sacrificing speed. In addition, unlike the traditional SR algorithm setting the spare transform by handcrafting, a convolutional neural network (CNN) module was established to adaptively learn such a transform, which significantly improved the filtering performance. Extensive experimental results on the simulated and measured data demonstrated that the proposed method outperformed several advanced InSAR phase filtering methods in both accuracy and speed. In addition, to verify the filtering performance of the proposed method under small training samples, the training samples were reduced to 10%. The results show that the performance of the proposed method was comparable on the simulated data and superior on the real data compared with another DL-based method, which demonstrates that our method is not constrained by the requirement of a huge number of training samples. Full article

Urban air quality mapping has been widely applied in urban planning, air pollution control and personal air pollution exposure assessment. Urban air quality maps are traditionally derived using measurements from fixed monitoring stations. Due to high cost, these stations are generally sparsely deployed in a few representative locations, leading to a highly generalized air quality map. In addition, urban air quality varies rapidly over short distances (<1 km) and is influenced by meteorological conditions, road network and traffic flow. These variations are not well represented in coarse-grained air quality maps generated by conventional fixed-site monitoring methods but have important implications for characterizing heterogeneous personal air pollution exposures and identifying localized air pollution hotspots. Therefore, fine-grained urban air quality mapping is indispensable. In this context, supplementary low-cost mobile sensors make mobile air quality monitoring a promising alternative. Using sparse air quality measurements collected by mobile sensors and various contextual factors, especially traffic flow, we propose a context-aware locally adapted deep forest (CLADF) model to infer the distribution of NO₂ by 100 m and 1 h resolution for fine-grained air quality mapping. The CLADF model exploits deep forest to construct a local model for each cluster consisting of nearest neighbor measurements in contextual feature space, and considers traffic flow as an important contextual feature. Extensive validation experiments were conducted using mobile NO₂ measurements collected by 17 postal vans equipped with low-cost sensors operating in Antwerp, Belgium. The experimental results demonstrate that the CLADF model achieves the lowest RMSE as well as advances in accuracy and correlation, compared with various benchmark models, including random forest, deep forest, extreme gradient boosting and support vector regression. Full article

Hyperspectral image (HSI) classification is one of the main research contents of hyperspectral technology. Existing HSI classification algorithms that are based on deep learning use a large number of labeled samples to train models to ensure excellent classification effects, but when the labeled samples are insufficient, the deep learning model is prone to overfitting. In practice, there are a large number of unlabeled samples that have not been effectively utilized, so it is meaningful to study a semi-supervised method. In this paper, an adversarial representation learning that is based on a generative adversarial networks (ARL-GAN) method is proposed to solve the small samples problem in hyperspectral image classification by applying GAN to the representation learning domain in a semi-supervised manner. The proposed method has the following distinctive advantages. First, we build a hyperspectral image block generator whose input is the feature vector that is extracted from the encoder and use the encoder as a feature extractor to extract more discriminant information. Second, the distance of the class probability output by the discriminator is used to measure the error between the generated image block and the real image instead of the root mean square error (MSE), so that the encoder can extract more useful information for classification. Third, GAN and conditional entropy are used to improve the utilization of unlabeled data and solve the small sample problem in hyperspectral image classification. Experiments on three public datasets show that the method achieved better classification accuracy with a small number of labeled samples compared to other state-of-the-art methods. Full article

Building extraction is a popular topic in remote sensing image processing. Efficient building extraction algorithms can identify and segment building areas to provide informative data for downstream tasks. Currently, building extraction is mainly achieved by deep convolutional neural networks (CNNs) based on the U-shaped encoder–decoder architecture. However, the local perceptive field of the convolutional operation poses a challenge for CNNs to fully capture the semantic information of large buildings, especially in high-resolution remote sensing images. Considering the recent success of the Transformer in computer vision tasks, in this paper, first we propose a shifted-window (swin) Transformer-based encoding booster. The proposed encoding booster includes a swin Transformer pyramid containing patch merging layers for down-sampling, which enables our encoding booster to extract semantics from multi-level features at different scales. Most importantly, the receptive field is significantly expanded by the global self-attention mechanism of the swin Transformer, allowing the encoding booster to capture the large-scale semantic information effectively and transcend the limitations of CNNs. Furthermore, we integrate the encoding booster in a specially designed U-shaped network through a novel manner, named the Swin Transformer-based Encoding Booster- U-shaped Network (STEB-UNet), to achieve the feature-level fusion of local and large-scale semantics. Remarkably, compared with other Transformer-included networks, the computational complexity and memory requirement of the STEB-UNet are significantly reduced due to the swin design, making the network training much easier. Experimental results show that the STEB-UNet can effectively discriminate and extract buildings of different scales and demonstrate higher accuracy than the state-of-the-art networks on public datasets. Full article

Synthetic aperture radar (SAR) signal can penetrate clouds and some vegetation canopies in all weather, and therefore, provides an important measurement tool for change detection and sustainable development of coastal wetland environments and ecosystems. However, there are a few quantitative estimations about the spatiotemporal coherence change with multi-band SAR images in complex coastal wetland ecosystems of the Yellow River Delta (YRD). In this study, C-band Sentinel-1 and L-band ALOS-2 PALSAR data were used to detect the spatiotemporal distribution and change pattern of interferometric coherence in the coastal wetlands of the YRD. The results show that the temporal baseline has a greater impact on the interferometric coherence than the perpendicular baseline, especially for short wavelength C-band SAR. Furthermore, the OTSU algorithm was proven to be able to distinguish the changing regions. The coherence mean and standard deviation values of different land cover types varied significantly in different seasons, while the minimum and maximum coherence changes occurred in February and August, respectively. In addition, considering three classical machine learning algorithms, namely naive Bayes (NB), random forest (RF), and multilayer perceptron (MLP), we proposed a method of synergetic classification with SAR coherence, backscatter intensity, and optical images for coastal wetland classification. The multilayer perceptron algorithm performs the best in synergetic classification with an overall accuracy of 98.3%, which is superior to a single data source or the other two algorithms. In this article, we provide an alternative cost-effective method for coastal wetland change detection, which contributes to more accurate dynamic land cover classification and to an understanding of the response mechanism of land features to climate change and human activities. Full article

Droughts and floods have occurred frequently in the Lower Mekong River Basin in recent years. Obtaining the evapotranspiration (ET) in the basin helps people to better understand water cycle and water resources. In this study, we retrieved and validated ET in the Lower Mekong Basin over multiple years (from 2008 to 2017) using remote sensing products. Based on the retrieval ET, we analyzed the spatial-temporal variation of ET and influencing factors at the monthly, seasonal, and inter-annual scale respectively. The results revealed that the overall variation trend of ET at annual scale slightly increased during 2008 to 2017, with the highest annual ET being 1198 mm/year in 2015 and the lowest annual ET being 949 mm/year in 2008. At the seasonal scale, ET in the rainy season was lower than the dry season; at the monthly scale, March had the highest monthly ET (101 mm/month) while July had the lowest monthly ET (73 mm/month). Spatial analyzing showed that ET in the margin of this region was higher (with on average about 1250 mm/year) and lower in the middle (with on average about 840 mm/year), and monthly ET changed mostly in forest areas with the difference of 60 mm/month. Influencing analyzing results showed that ET was mainly driven by solar radiation and near-surface temperature, and precipitation had an inhibitory effect on ET in the rainy season months. The study also showed that forests in the basin are very sensitive to solar radiation, with a correlation coefficient of 0.89 in March (the month with the highest ET) and 0.45 in July (the month with the lowest ET). Full article

One of the areas that show the most visible effects of human-induced land alterations is also the world’s most essential resource: water. Decision-makers in arid regions face considerable difficulties in providing and maintaining sustainable water resource management. However, developing appropriate and straightforward approaches for quantifying water use in arid/hyper-arid regions is still a formidable challenge. Meanwhile, a better knowledge of the effects of land use land cover (LULC) changes on natural resources and environmental systems is required. The purpose of this study was to quantify the water consumption in a hyper-arid region (New Valley, Egypt) using two different approaches—LULC based on optical remote sensing data and groundwater storage changes based on Gravity Recovery Climate Experiment (GRACE) satellite data—and to compare and contrast the quantitative results of the two approaches. The LULC of the study area was constructed from 1986 to 2021 to identify the land cover changes and investigate the primary water consumption patterns. The analysis of groundwater storage changes utilized two GRACE mascon solutions from 2002 to 2021 in New Valley. The results showed an increase in agricultural areas in New Valley’s oases. They also showed an increased in irrigation water usage and a continuous decrease in the groundwater storage of New Valley. The overall water usage in New Valley for domestic and irrigation was calculated as 18.62 km³ (0.93 km³/yr) based on the LULC estimates. Moreover, the groundwater storage changes of New Valley were extracted using GRACE and calculated to be 19.36 ± 7.96 km³ (0.97 ± 0.39 km³/yr). The results indicated that the water use calculated from LULC was consistent with the depletion in groundwater storage calculated by applying GRACE. This study provides an essential reference for regional sustainability and water resource management in arid/hyper-arid regions. Full article

The use of the conventional interferometric synthetic aperture radar (InSAR) to generate digital elevation models (DEMs) always encounters phase unwrapping (PU) errors in areas with a sizeable topographic gradient. Range split-spectrum interferometry (RSSI) can overcome this issue; however, it loses the spatial resolution of the SAR image. We propose the use of the RSSI-assisted In-SAR-derived DEM (RID) method to address this challenge. The proposed approach first applies the RSSI method to generate a prior DEM, used for simulating terrain phases. Then, the simulated terrain phases are subtracted from the wrapped InSAR phases to obtain wrapped residual phases. Finally, the residual phases are unwrapped by the minimum cost flow (MCF) method, and the unwrapped residual phases are added to the simulated phases. Both the simulated and TerraSAR-X data sets are used to verify the proposed method. Compared with the InSAR and RSSI methods, the proposed approach can effectively decrease the PU errors of large gradients, ensure data resolution, and guarantee the DEM’s accuracy. The root mean square error between the topographic phase simulated from the real DEM and the topographic phase generated from the proposed method is 2.22 rad, which is significantly lower than 6.60 rad for InSAR, and the improvement rate is about 66.36%. Full article

Feature matching is a key method of feature-based image registration, which refers to establishing reliable correspondence between feature points extracted from two images. In order to eliminate false matchings from the initial matchings, we propose a simple and efficient method. The key principle of our method is to maintain the topological and affine transformation consistency among the neighborhood matches. We formulate this problem as a mathematical model and derive a closed solution with linear time and space complexity. More specifically, our method can remove mismatches from thousands of hypothetical correspondences within a few milliseconds. We conduct qualitative and quantitative experiments on our method on different types of remote-sensing datasets. The experimental results show that our method is general, and it can deal with all kinds of remote-sensing image pairs, whether rigid or non-rigid image deformation or image pairs with various shadow, projection distortion, noise, and geometric distortion. Furthermore, it is two orders of magnitude faster and more accurate than state-of-the-art methods and can be used for real-time applications. Full article