Understanding the spatiotemporal characteristics of vegetation growth in the Yellow River basin and their influencing factors is crucial for the conservation and development of the ecology. However, existing studies rarely focus on the latest spatiotemporal characteristics of different vegetation types in the basin and their relationships with their influencing factors. Using the 2000-2020 time series remote sensing data of MODIS normalized difference vegetation index (NDVI), along with methods including trend analysis, correlation analysis, partial correlation analysis, and residual analysis, this study investigated the spatiotemporal characteristics of various vegetation types in the Yellow River basin. Accordingly, this study clarified the mechanisms behind the impacts of temperature and precipitation on annual and monthly scales and explored the influence of human activities on the spatiotemporal characteristics of different vegetation types. The results indicate that from 2000 to 2020, the NDVI of different vegetation types in the Yellow River basin trended upward overall, particularly in cultivated land and forest land. However, the increasing trends trended downward at different degrees with increasing elevation. Over the 21 years, various vegetation types were improved in most areas in the basin. However, a few areas exhibited degraded vegetation types, primarily including grassland and cultivated land. The proportion of areas with anti-continuous future trends in various vegetation types notably increased. Temperature and precipitation produced positive impacts on the growth of various vegetation types in the Yellow River basin. Nevertheless, various vegetation types exhibited greater responses to precipitation than to temperature, and the responses featured notable time lags. Furthermore, grassland and shrub growth were more sensitive to precipitation and temperature. Human activities had positive impacts on the vegetation of the Yellow River basin overall. However, some negative effects were also observed in grassland and cultivated land, warranting attention in future planning. Overall, most areas exhibited improved vegetation in the Yellow River basin in the 20 years. Given that partial grassland and cultivated land experienced degradation, it is necessary to protect typical degradation areas. The findings of this study will provide scientific data and theoretical support for ecological construction and economic development in the Yellow River basin.

The geological exploration in Qinghai Province is conducted in typical highland desert areas characterized by significant terrain cutting, low vegetation cover, extensive bedrock outcrops, and challenging surface investigations. To investigate the application of hyperspectral data from a satellite in altered mineral mapping and ore prospecting in desert areas along the northern margin of the Qaidam Basin, this study utilized hyperspectral remote sensing images with high spatial and spectral resolutions obtained from the domestic ZY1-02D satellite. Following fine-scale radiometric calibration, atmospheric correction, data restoration, and orthorectification, high-quality hyperspectral remote sensing images were acquired for desert areas, such as Saibagou, along the northern margin of the Qinghai Province. After comprehensive field survey sampling and spectral testing using a FieldSpec Pro FR spectrometer, a standard laboratory spectral dataset of the surveyed areas was established, containing 13 major altered minerals such as chlorite. Finally, the extraction of altered minerals and ore prospecting were conducted. The results indicate that the primary altered minerals in the areas include 13 types: epidote, chlorite, albite, sericite, silicification, kaolinite, carbonate, limonite, actinolite, serpentine, hematite, pyrite, and malachite. The distribution of these altered minerals is closely associated with the strata, lithology of intrusions, and ductile shear structures. The analysis of the alteration characteristics of typical mineral deposits such as Saibagou reveals that malachitization, limonitization, pyritization, sericitization, and silicification are closely related to mineralization, being indicative of ore prospecting. Partial potassium feldspathization, chloritization, epidotization, and sodium feldspathization are also somewhat related to mineralization, serving as a valuable reference for ore prospecting. As a result of applying the above methods, combined with the 1:25 000 geochemical survey data, one copper-gold mineralized point was discovered in the Tuomoerrite area. Therefore, hyperspectral data-based alteration mineral mapping compensates for the limitations of traditional geological surveys and ore prospecting methods in the western desert areas of China with harsh natural conditions. This allows for rapid assessment of the regional geological setting and mineralization conditions, enabling the extraction of mineral spectral information. The hyperspectral data-based alteration mineral mapping provides abundant, fine-scale information for large-scale geological prospecting, offering broad application potential.

During the melt season, supraglacial lakes are widely distributed across polar ice sheets, storing large amounts of surface meltwater. When some of these supraglacial lakes rupture at the bottom, the released meltwater infiltrates ice sheets, affecting their movement and stability. Therefore, accurate bathymetry retrieval of supraglacial lakes and estimating the volume of supraglacial lakes are significant for understanding the hydrological processes of polar ice sheets. However, field measurement of supraglacial lake depth is difficult, costly, and small-scale. Meanwhile, the bathymetry models derived from optical satellite images with low to medium spatial resolutions are insufficiently accurate. Given these, this study conducted the bathymetry retrieval of supraglacial lakes based on eight-band remote sensing images from the small-size optical satellite PlanetScope SuperDove (spatial resolution: 3 m) and ICESat-2 laser altimetry data. First, the ICESat-2 laser altimetry point clouds data for the lake surface and bottom were separated and modeled using adaptive kernel density estimation to derive lake depth observations. Second, Optimal Band Ratio Analysis (OBRA) was used to examine the correlations between various bands of PlanetScope images (and combinations thereof) and ICESat-2 bathymetry data, leading to the development of four kinds of empirical formulas for the bathymetry retrieval of supraglacial lakes: quadratic, exponential, power, and logarithmic functions. Then, four supraglacial lakes covered by concurrent PlanetScope and ICESat-2 data were selected to test the retrieval accuracy. The results indicate that the Green I band of PlanetScope is the most favorable for the bathymetry retrieval, demonstrating the strongest correlation with the ICESat-2 derived depths (R²=0.94) and the highest inversion accuracy (RMSE=1.0 m, RRMSE=0.15). The study reveals that integrating active and passive satellite data has great potential for analyzing hydrological processes in polar ice sheets.

Soil salinization is identified as a major cause of decreased soil fertility, productivity, vegetation coverage, and crop yield. Optical remote sensing monitoring enjoys advantages such as macro-scale, timeliness, dynamics, and low costs, rendering this technology significant for the dynamic monitoring of soil salinization. However, there is a lack of reviews of the systematic organization of multi-scale remote sensing data, multi-type remote sensing feature parameters, and inversion models. This study first organized the optical remote sensing data sources and summarized the remote sensing data sources and scale platforms utilized in current studies on saline soil monitoring. Accordingly, this study categorized multi-source remote sensing data into three different platforms: satellite, aerial, and ground. Second, this study organized the mainstream characteristic parameters for modeling and two typical inversion methods, i.e., statistical regression and machine learning, and analyzed the current status of research on both methods. Finally, this study explored the fusion of remote sensing data sources and compared the pros and cons of various modeling methods. Furthermore, in combination with current hot research topics, this study discussed the prospects for the application of data assimilation and deep learning to soil salinization monitoring.

In the context of the growing maturity of on-road navigation, this study proposed a cross-disciplinary research direction-off-road navigation-based on the demands for navigation services in complex and unstructured environments. First, the development of on-road navigation and the demand scenarios of off-road navigation were introduced. Based on four specific aspects of vehicle trafficability, scientific issues in the transition from on-road to off-road navigation were presented, including refining remote sensing detection of geographical and geological trafficability elements, remote sensing-based retrieval of soft soil parameters in off-road areas, and quantitative mechanisms behind the impacts of climatic change on ground characteristics. Accordingly, the research direction of off-road navigation was clarified. Then, key technologies like vehicle trafficability calculation and characterization, digital road network construction in off-road areas, and intelligent path planning for off-road navigation were summarized. The technical approach of roadization for off-road areas and the concept of a digital road network for off-road areas were introduced, followed by the establishment of a comprehensive technology system for off-road navigation. Finally, in combination with practical applications, the potential of off-road navigation was confirmed. Research on off-road navigation will further enrich the connotation of navigation and expand its application boundaries.

On April 1, 2023, China’s first satellite constellation-L-band differential interferometric Synthetic Aperture Radar (L-SAR)-began to test the distribution of interferometric SAR data for natural resource applications. To evaluate the coherence and effectiveness of deformation monitoring using the L-SAR satellite for areas with high vegetation coverage, complex terrain, and long-term baseline, this study conducted potential landslide hazard identification in the Ankang area in the eastern Qinba Mountain. The deformation information of the study area was extracted using L-SAR data. Using such information, combined with high-resolution optical images for comprehensive remote sensing identification, this study identified seven potential landslide hazards in the study area through interpretation. Field investigation confirmed that the observed deformation signs in potential landslide hazard areas were consistent with the InSAR monitoring results. The study indicates that the L-SAR satellite enjoys a high interference imaging ability, high imaging quality, and effective deformation monitoring, meeting the demand for deformation monitoring in areas with high vegetation coverage. For mountainous areas with high vegetation coverage, the use of L-band SAR data through DInSAR technology, combined with comprehensive remote sensing identification using high-resolution optical imagery, allows for the effective identification of potential landslide hazards.

The rapid assessment of building damage following destructive earthquakes serves as a critical foundation for decision-making and technical guarantee in post-earthquake scientific evaluations, holding great significance in humanitarian aid and emergency response. This study aims to overcome the challenge in rapidly quantifying the number of buildings affected. Considering that most existing post-earthquake building damage assessments based on remote sensing images rely on pre- and post-disaster image segmentation, this study, by using the U-Net deep convolutional neural network as the main model, introduced a three-stage convolutional neural network for building damage assessment (BDANet) framework that integrates assessment and prediction for post-earthquake building damage information. First, the encoder-decoder network structure of U-Net was used to extract building location information. Second, building damage was assessed using pre- and post-disaster images to localize and grade damage in the image segmentation results. Finally, the number of buildings damaged at various levels was predicted to support post-disaster rescue and reconstruction efforts. The study evaluated and quantified the levels of post-earthquake building damage in the M7.1 earthquake in Morelos State, central Mexico in 2017 and the M7.8 earthquake in Türkiye in 2023, confirming the accuracy and reliability of the proposed method. The experimental findings provide timely and precise data and technical support for post-disaster risk assessment.

Accurately extracting building information from high-resolution remote sensing images faces challenges due to complex background transformations and the diversity of building shapes. This study developed a high-resolution building semantic segmentation network-building mining net (BMNet), which integrated a hybrid attention mechanism with multi-scale feature enhancement. First, the encoder utilized VGG-16 as the backbone network to extract features, obtaining four layers of feature representations. Then, a decoder was designed to address the issue of detail loss in high-layer features within multi-scale information. Specifically, a series attention module (SAM), which combined channel attention and spatial attention, was introduced to enhance the representation capabilities of high-layer features. Additionally, the building mining module(BMM) with progressive feature enhancement was designed to further improve the accuracy of building segmentation. With the upsampled feature mapping, the feature mapping post-processed using SAM, and initial prediction results as input, the BMM output background noise information and then filtered out background information using the context information exploration module designed in this study. Optimal prediction results were achieved after multiple processing using the BMM. Comparative experiment results indicate that the BMNet outperformed U-Net, with accuracy and intersection over union (IoU) increasing by 4.6% and 4.8%, respectively on the WHU Building dataset, by 7.9% and 8.9%, respectively on the Massachusetts buildings dataset, and by 6.7% and 11.0%, respectively on the Inria Aerial Image Labeling Dataset. These results validate the effectiveness and practicality of the proposed model.

This study aims to evaluate and analyze the geology of mines in Ili Valley and investigate the countermeasures for ecological restoration therein. Utilizing the mining development status derived from remote sensing data and the remote sensing survey results of geological environment, as well as multi-source geological, socio-economic, and meteorological data, this study built a hierarchy structural model using analytic hierarchy process (AHP) and assessed the geological environment of mines in the Ili Valley, The results indicate that the severely affected areas are relatively concentrated, accounting for 4.61% of the total area of Ili Valley. The moderately severely affected areas present a continuous distribution. These areas overlap with each other, exhibiting indistinct boundaries. The generally affected areas are primarily distributed in extremely high mountain areas, medium to high mountain areas, and low mountain and hilly areas. The unaffected areas are primarily distributed in the alluvial plain area in the central part Ili River Valley and the plain area of the Zhaosu Basin. The areas with high ecological carrying capacity are mainly concentrated in the central region except for the south of Zhaosu County and Tekes County, the eastern edge of Nilka County, and the northern area of Khorgos. This study proposed corresponding ecological restoration and management measures and countermeasures against major geological issues. The findings of this study can provide basic data and technical support for the sustainable development of the ecology and the rational exploitation of mine resources in the Ili Valley. Additionally, these findings can serve as a case study for monitoring and assessing the geology of mines in arid and semi-arid areas.

Remote sensing data with a high spatial resolution can be used to quickly ascertain the current status of the geological environment of mines in China, yielding objective and accurate results. By comparing 2020—2021 remote sensing images of 169 districts, counties, and cities in Hebei Province, 728 patches signaling suspected lands destroyed in mines were identified through interpretation. In 2021, the newly rehabilitated areas of the mining environment in Hebei Province reached 1 305.51 hm², while the newly increased lands destroyed by mining were 932.13 hm², resulting in a net increase of 373.38 hm² in lands attributed to the geological environment rehabilitation. These results indicate the general achievement of mining while rehabilitating. Based on a preliminary analysis of the current status of the geological environment of mines in Hebei Province and existing primary issues, this study proposed countermeasures and recommendations for future rehabilitation efforts. The results of this study will provide foundational data and technical support for managing the geological environment of mines in Hebei Province and evaluating the effectiveness of mine greening initiatives.

To capture information about the 3D geometric structures of trees more effectively and address the challenge of high-precision, high-fidelity tree reconstruction, this study proposed a method for 3D modeling of trees based on terrestrial LiDAR point cloud. To overcome the occlusion caused by leaf gaps in TLS, this method fully considered the aggregation of leaves, as well as the morphological characteristics of both leaves and branches. By conducting the model fitting and reconstruction of tree leaves and branches using Delaunay triangulation and Alpha-shape algorithm, respectively, the proposed method effectively addressed previous issues such as unrealistic tree structures and imprecise organ modeling, thus achieving the 3D reconstruction of individual tree leaves and small branches efficiently. This study holds great significance for determining forest structural parameters and managing resources, while also offering a valuable reference for component-level real scene 3D modeling of typical trees.

The Xuyong-Gulin (Xugu) Expressway, located along the southern margin of the Sichuan Basin, faces complex geological conditions, with its safe operation threatened by geologic hazards. Therefore, the identification and analysis of geologic hazards along the expressway holds great significance. Interferometric synthetic aperture Radar (InSAR) technique enjoys the advantages of all-weather, all-time observation capabilities, wide coverage, and mm-scale surface deformation monitoring, playing an important role in wide-field landslide detection and monitoring. Based on this, this study processed the Sentinel-1 ascending and descending datasets from February 2017 to September 2020 using the small baselines subset (SBAS) InSAR technique. As a result, the surface deformation rates along the expressway were determined, and 18 landslides were identified. The analysis indicates that the deformations of landslides are related to anthropogenic activities. The analytical results also reveal that the combination of ascending and descending datasets allows for more accurate identification of landslide distribution. With the continuous data accumulation and technological development, InSAR is expected to play an increasingly important role in the prevention and control of geologic disasters.

To address the accuracy reduction in the semantic segmentation of remote sensing images due to insufficient extraction of contextual dependencies and loss of spatial details, this study proposed a semantic segmentation method based on context- and class-aware feature fusion. With ResNet-50 as the backbone network for feature extraction, the proposed method incorporates the attention module during downsampling to enhance feature representation and contextual dependency extraction. It constructs a large receptive field block on skip connections to extract rich multiscale contextual information, thereby mitigating the impacts of scale variations between targets. Furthermore, it connects a scene feature association and fusion module in parallel behind the block to guide local feature fusion based on global features. Finally, it constructs a class prediction module and a class-aware feature fusion module in the decoder part to accurately fuse the low-level advanced semantic information with high-level detailed information. The proposed method was validated on the Potsdam and Vaihingen datasets and compared with six commonly used methods, including DeepLabv3+ and BuildFormer, to verify its effectiveness. Experimental results demonstrate that the proposed method outperformed other methods in terms of recall, F1-score, and accuracy. Particularly, it yielded intersection over union (IoU) values of 90.44% and 86.74% for building segmentation, achieving improvements of 1.55% and 2.41%, respectively, compared to suboptimal networks DeepLabv3+ and A2FPN.

Extracting information about buildings from a large and complex set of remote sensing images has always been a hot research topic in the intelligent applications of remote sensing. To address issues such as inaccurate information extraction of buildings and the tendency to ignore small buildings within a complex environment in remote sensing images, this study proposed the SC-deep network-a semantic segmentation algorithm for remote sensing images based on a hybrid attention mechanism and Deeplabv3+. Utilizing an encoder-decoder structure, this network employs a backbone residual attention network to extract deep- and shallow-layer features. Meanwhile, this network aggregates the spatial and channel information weights in remote sensing images using a dilated space pyramid pool module and a channel-space attention module. These allow for effectively utilizing the multi-scale information of building structures in remote sensing images, thereby reducing the loss of image details during training. The experimental results indicate that the proposed method outperforms other mainstream segmentation networks on the Aerial imagery dataset. Overall, this method can effectively identify and extract the edges of complex buildings and small structures, exhibiting superior building extraction performance.

Based on 1985-2020 Landsat data, this study estimated eight phases of annual vegetation fractional cover (VFC) of the Beijing-Tianjin-Hebei region. Using the Theil-Sen Median and Mann-Kendall trend analyses, this study comprehensively analyzed the spatiotemporal variation characteristics of VFC in four major functional areas for the coordinated development of the Beijing-Tianjin-Hebei region. Furthermore, employing geodetectors, this study explored the degrees and mechanisms of the impacts of climatic, natural, and anthropogenic factors, along with their interactions, on the regional VFC from both static and dynamic perspectives. The results indicate that from 1985 to 2020, the Beijing-Tianjin-Hebei region exhibited sound vegetation coverage overall, which decreased in the order of the southern functional expansion area (SFEA), the northwestern ecological conservation area (NECA), the central core functional area (CCFA), the eastern coastal development area (ECDA). The VFC of the Beijing-Tianjin-Hebei region trended upward while fluctuating, with an increasing rate of 0.097%/10a. The VFC exhibited a spatial distribution pattern of high values in the west and low values in the east. Specifically, areas with elevated VFC were primarily distributed in the Yanshan, Damaqun, and Taihang mountains within the NECA, while those with reduced VFC were principally found in the built-up areas and their surrounding areas of cities and counties in the CCFA, ECDA, and SFEA. At the single-factor level, the primary and secondary factors controlling VFC across the four functional areas differed greatly, with land-use and soil types exhibiting higher interpretability. Regarding the influencing elements, the main factors driving spatial differentiation of VFC in the CCFA and SFEA included anthropogenic factors, those in ECDA comprised anthropogenic and natural factors, and those in NECA were dominated by climatic and natural factors. For the VFC of the four functional areas in all these years, the land use type manifested high interpretability, which trended upward overall. The q values of soil types were higher in ECDA and NECA, trending downward in the NECA. Secondary factors controlling the VFC exhibited different interannual interpretability in various functional areas. All influencing factors exhibited enhanced influence to varying extents, with no mutual independence or weakened influence observed. Additionally, the meteorological factor emerged as the primary interacting variable.

To resolve the limitations of traditional economic data such as the lack of spatial information and the difficulty in capturing the spatial disparities and dynamic patterns of regional economic development, this study integrated nighttime light data with land use and socio-economic data to develop a spatialized gross domestic product (GDP) model for the Chengdu-Chongqing region. Using trend analysis and a modified gravity model, this work analyzes the economic development characteristics of the region at the pixel level and in terms of inter-city economic relationships. The results indicate that the spatialized GDP model, constructed from multiple data sources, demonstrated high accuracy, with errors not exceeding 1.1%. The areas with the fastest GDP density growth in the Chengdu-Chongqing region are mainly concentrated around the core urban areas of Chengdu and Chongqing, accounting for approximately 73.9% of the total. These areas also show pronounced economic agglomeration characteristics. The inter-city economic relationships in the Chengdu-Chongqing region are continually strengthening, and the overall quality of urban development is steadily improving. Chengdu, in particular, has the closest economic ties with its neighboring cities. Overall, the Chengdu-Chongqing regional economy exhibits a spatial pattern of “dual-core driven development”, with the intensity of inter-city economic relationships continuing to strengthen. This study will provide valuable data support and methodological insights for promoting the high-quality economic development of the Chengdu-Chongqing urban agglomeration.

Synthetic aperture radar (SAR), allowing for all-weather and all-day imaging, can provide essential data for large-scale flood inundation monitoring. However, limitations such as the revisit period of SAR images make it challenging for single-source SAR data to meet the high temporal requirements for dynamic flood inundation monitoring, which is crucial for disaster relief and decision-making support. Combining multi-temporal SAR data for dynamic flood inundation monitoring is of significant practical value. Nevertheless, SAR images from different sensors exhibit significant spatiotemporal heterogeneity, rendering direct comparisons difficult. Additionally, previous studies frequently extracted flood inundation extents using single-pixel or local spatial neighborhood features while neglecting the application of spatiotemporal non-local features pre- and post-flooding. Therefore, this study first proposed a feature space alignment method for multi-source SAR data based on backscatter characteristics. Then, differential information pre- and post-flooding was extracted using the progressive non-local theory, and flood inundation maps were prepared. Finally, dynamic flood inundation monitoring results were obtained through logical operations of the time-series flood inundation maps. This method was validated using the flood disaster in August 2023 in Zhuozhou, during which five multi-source SAR datasets were acquired from Sentinel-1, Gaofen-3 (GF-3), and Fucheng-1. The results indicate that compared to six commonly used flood monitoring methods, the proposed method exhibited the optimal performance, yielding a Kappa coefficient and F1 score of 0.85 and 0.88, respectively. The dynamic monitoring results of the flood inundation in Zhuozhou reveal that the floodwater in the main urban area largely receded by August 3, and the water levels then gradually decreased, with the inundated areas shifting to the Baigou River in the lower reaches.

Shanxi Province is recognized as a significant coal base in China. The extensive and intensive coal mining activities have adversely affected the local ecology, rendering the research on ecological evolution in Shanxi Province highly significant. Utilizing the Google Earth Engine (GEE) platform, this study calculated the 2000-2022 remote sensing ecological index (RSEI) of Shanxi Province using images from Moderate Resolution Imaging Spectroradiometer (MODIS). The Mann-Kendall trend analysis method was employed to analyze the evolutionary trends of RSEI, while Pettitt mutation tests were conducted to identify RSEI mutations. Furthermore, the Pearson correlation coefficient was used to analyze the correlation between RSEI and climatic factors. The results indicate that Shanxi Province exhibited relatively high ecological quality on average during the period. However, the coal mining areas in the province displayed moderate ecological quality overall. The spatial distribution of precipitation and temperature can effectively account for the spatial distribution of RSEI. Most regions in Shanxi Province showed an upward trend in RSEI, with areas with reduced RSEI predominantly located in coal mining areas and basin areas with high population density and a developed economy. During the 23 years, the ecological quality in Shanxi Province has evolved from poor to moderate and then to relatively good, increased while fluctuating from 2000 to 2006, kept stable from 2006 to 2012, regressed after increase from 2012 to 2019, and continuously increased from 2019 to 2022. Similarly, the ecological quality in coal mining areas has shifted from relatively poor to relatively good, increased while fluctuating from 2000 to 2006, kept stable from 2006 to 2012, decreased while fluctuating from 2012 to 2019, and continuously increased from 2019 to 2022. The year 2010 is identified as a pivotal point for the ecological quality of Shanxi Province, with the ecological quality trending upward from 2000 to 2010 and comprehensively improving after 2010 across the province and its coal mining areas. The interannual variations in precipitation generally produce positive impacts on the ecological quality, while the variations in interannual temperature exert insignificant impacts.

Ecological quality is an important indicator of a regional development level. Objective, quantitative dynamic monitoring and analysis of long-term ecological quality can provide a scientific basis for urban sustainable development and ecological construction. Based on Landsat remote sensing images, this study constructed the remote sensing ecological index (RSEI) as an evaluation index using principal component analysis. Accordingly, this study explored the spatiotemporal change characteristics of ecological quality in Zhengzhou from 2001 to 2020, as well as the extent of influence of various driving factors, using the Sen+Mann-Kendall trend analysis, the Hurst index, and geographical detectors. The results indicate that from 2001 to 2020, Zhengzhou maintained moderate ecological quality overall. The RSEI showed downward, upward, and then downward trends sequentially. Spatially, the eastern plains showed lower ecological quality, whereas the southwestern mountainous and hilly areas exhibited higher ecological quality. The regional ecological quality remained unchanged predominantly or saw slight improvements over these years except for 2010, when the area of zones with ecological quality deteriorating significantly increased due to high temperature. From 2001 to 2020, the ecological quality in Zhengzhou exhibited significant trends, with 56.34% of areas showing an upward trend and 42.26% exhibiting a downward trend. These results, along with the Hurst index, reveal that the downward trend in ecological quality in the eastern part is primarily characterized by sustainable changes in the future, while the upward trend in ecological quality in the southwestern partition is primarily characterized by anti-sustainable changes in the future. Driving force analysis indicates that over the 20 years, primary factors influencing changes in ecological quality in Zhengzhou included land use type and population density, whose explanatory power is significantly stronger than other factors. The impact of natural factors, such as elevation and average annual precipitation, has gradually diminished, while the influence of the night light index, which reflects the urbanization level, has progressively increased. The results of this study will provide a scientific basis for the evaluation and preservation of ecosystems in Zhengzhou.

The rapid development of hyperspectral remote sensing technology in China fully ensures the effective application of large-scale surface feature classification. However, achieving high-precision classification under few-spot conditions while fully leveraging hyperspectral spatial-spectral information remains challenging. This study developed a 3D convolutional autoencoder (3D-CAE) network guided by physical constraints from mixed pixel decomposition. This approach enables accurate estimation of endmember abundance while effectively expressing regularized spatial-spectral features of hyperspectral data. In combination with a support vector machine (SVM) classifier, the method achieves hyperspectral classification under few-spot conditions. The classification performance of various models was evaluated at different sampling rates. To validate the proposed method, this study conducted experiments including comparisons with traditional hyperspectral feature extraction and classification methods, such as supervised classification approaches. The classification performance of various models was also evaluated at different sampling rates. The experimental results demonstrate that the proposed hyperspectral classification method has a significant advantage of accuracy, achieving a mean intersection over union (mIoU) of 0.829, which was close to 0.8 even at a low sampling rate of 1/200, surpassing its counterparts. These results confirm that the proposed method exhibits robustness under few-spot conditions. This study provides a valuable technical reference for addressing hyperspectral classification challenges under few-spot conditions.

Deep learning-based methods for information extraction of roads from high-resolution remote sensing images face challenges in extracting information about both global context and edge details. This study proposed a cascaded neural network for road segmentation in remote sensing images, allowing both types of information to be simultaneously learned. First, the input feature images were sent to encoders CNN and Transformer. Then, the characteristics learned by both branch encoders were effectively combined using the shuffle attention dual branch fusion (SA-DBF) module, thus achieving the fusion of global and local information. Using the SA-DBF module, the model of the features learned from both branches was established through fine-grained interaction, during which channel and spatial information in the feature images were efficiently extracted and invalid noise was suppressed using multiple attention mechanisms. The proposed network was evaluated using the Massachusetts Road dataset, yielding an overall accuracy rate (OA) of 98.04%, an intersection over union (IoU) of 88.03%, and an F1 score of 65.13%. Compared to that of mainstream methodsU-Net and TransRoadNet, the IoU of the proposed network increased by 2.01 and 1.42 percentage points, respectively. Experimental results indicate that the proposed method outperforms all the methods compared and can effectively improve the accuracy of road segmentation.

The key to the high performance of semantic segmentation models for high-resolution remote sensing images lies in the high domain consistency between the training and testing datasets. The domain discrepancies between different datasets, including differences in geographic locations, sensors’ imaging patterns, and weather conditions, lead to significantly decreased accuracy when a model trained on one dataset is applied to another. Domain adaptation is an effective strategy to address the aforementioned issue. From the perspective of a domain adaptation model, this study developed an adversarial learning-based unsupervised domain adaptation framework for the semantic segmentation of high-resolution remote sensing images. This framework fused the entropy-weighted attention and class-wise domain feature aggregation mechanism into the global and local domain alignment modules, respectively, alleviating the domain discrepancies between the source and target. Additionally, the object context representation (OCR) and Atrous spatial pyramid pooling (ASPP) modules were incorporated to fully leverage spatial- and object-level contextual information in the images. Furthermore, the OCR and ASPP combination strategy was employed to improve segmentation accuracy and precision. The experimental results indicate that the proposed method allows for superior cross-domain segmentation on two publicly available datasets, outperforming other methods of the same type.

In the management of modern agriculture production, the spatial distribution of different crop types is identified as important information about agricultural conditions. Identifying crop types from satellite remote sensing imagery serves as a fundamental method for acquiring such information. Although there exist various algorithms for identifying surface features from remote sensing imagery, reliable farmland classification remains challenging. This study selected three representative semantic segmentation-orientated deep convolutional models, i.e., UNet, ResUNet, and SegNext, and compared their performance in crop classification using remote sensing images of the Hetao irrigation district from the Gaofen-2 satellite. Using the three algorithms, nine network models with varying complexities were developed to analyze the differences in the performance of various network structures in classifying crops in farmland based on remote sensing imagery, thus providing optimization insights and an experimental basis for future research on relevant models. Experimental results indicate that the six-layer UNet achieved the highest identification accuracy (88.74%), while the six-layer SegNext yielded the lowest accuracy (84.33%). The ResUNet displayed the highest complexity but serious over-fitting with the dataset used in this study. Regarding computational efficiency, ResUNet was significantly less efficient than the other two model types.

Extracting accurate water body information holds great significance for water resources protection and urban planning. However, due to numerous surface features and complex environments, along with different morphologies, scales, and spectral characteristics of different water bodies, remote sensing images inevitably exhibit heterogeneity, spectral similarities, and inter-class similarities between water bodies and other surface features. Existing methods fail to fully exploit boundary cues, the semantic correlation between different layers, and multi-scale representations, rendering the accurate information extraction of water bodies from remote sensing images still challenging. This study proposed a boundary guidance and cross-scale information interaction network (BGCIINet) for information extraction of water bodies from remote sensing images. First, this study proposed a boundary guidance (BG) module for the first time by combing the Sobel operator. This module can be used to effectively capture boundary cues in low-level features and efficiently embed these cues into a decoder to produce rich boundary information. Second, a cross-scale information interaction (CII) module was introduced to enhance the multi-scale representation capability of the network and facilitate information exchange between layers. Extensive experiments on two datasets demonstrate that the proposed method outperforms four state-of-the-art methods, offering rich boundary details and completeness under challenging scenarios. Therefore, the proposed method is more effective in extracting water body information from remote sensing images. This study will provide a valuable reference of methods for future research.

Soil moisture products based on remote sensing are crucial for investigating climatic change and hydrological effects on a regional scale. However, there is a lack of verification and application of long-term soil moisture datasets in China due to factors such as inconsistent observation standards and instrument upgrades. Using the agro-meteorological dataset from the China Meteorological Administration and soil moisture data from the International Soil Moisture Network (ISMN), this study constructed a monthly dataset of soil moisture in eastern China covering the period from 1981 to 2013. Accordingly, this study analyzed and compared the performance of four microwave remote sensing-based soil moisture products developed by the European Space Agency’s Climate Change Initiative (ESA CCI): active, passive, combined, and combined adjusted products. The results indicate that active and passive products underestimated and overestimated soil moisture in eastern China, respectively. The maximum deviations from active products were found in the northern and northwestern regions, with relative deviations of -30.9% and -29.6%, respectively. In contrast, the passive products showed relative deviations of 39.1% and 26.5%, respectively for soil moisture in northeastern and northwestern regions. The combined products mitigated the underestimation of the active products and the overestimation of the passive product in these regions, reducing the relative deviations to 24.3% and 3.7%, respectively. Regarding the variation characteristics of regional monthly average soil moisture, both the active and combined products performed best for soil moisture in the Yangtze-Huaihe (YH) region, with the highest correlation coefficient of 0.66. The passive and combined products yielded correlation coefficients of 0.44 and 0.47, respectively for soil moisture in the northeastern region and performed poorly for soil moisture in the northern and northwestern regions. The analysis of the variance sources of the remote sensing-based products indicates that the active products enjoyed more advantages in describing the evolutionary characteristics of soil moisture, the passive products demonstrated greater accuracy, and the combined products yielded the highest accuracy overall. Additionally, this study investigated the impacts of changes in the integrated satellite equipment of CCI on product performance. The results indicate that the active products exhibited consistent performance for soil moisture in the northeastern and northwestern regions in different periods. However, passive sensors still exhibited gaps in reproducing the variations in soil moisture. The combined products exhibited better overall variance than both active and passive products. However, these products yielded comparable correlation coefficients with the active products for soil moisture in the northeastern and northwestern regions. The combined products presented no notable improvement after correction, proving that it is feasible to conduct long-term research using the combined products of CCI. The results of this study contribute to a deeper understanding of the error structures and characteristics of various satellite product datasets, providing evidence for researchers to select appropriate data products and conduct research on long time series.

Net ecosystem productivity (NEP) is recognized as an important characteristic quantity of ecosystems and a physical quantity of carbon exchange between terrestrial ecosystems and the atmosphere. Utilizing MODIS NPP and meteorological data, this study estimated the vegetation NEP in Hunan Province from 2000 to 2020 using a soil microbial respiration model. Furthermore, this study analyzed the dynamic characteristics of vegetation carbon sink through trend analysis, variation coefficient, and standard deviation ellipse methods, followed by a quantitative assessment of the impacts of natural factors on vegetation carbon sink using geographical detectors and correlation analysis. The results indicate that the annual multiyear average of vegetation carbon sink in Hunan Province was 603.01 gC·m^-2·a^-1. The vegetation carbon sink presented a spatial distribution pattern of higher values in the south and west and lower values in the north and east, decreasing gradually from southwest to northeast. From 2000 to 2020, the average trend coefficient of vegetation carbon sink was 2.97 gC·m^-2·a^-1, trending upward overall. The coefficient of variation was primarily characterized by small fluctuations and fairly small fluctuations, while areas of great fluctuations are mainly scattered around certain cities, which are more susceptible to natural or anthropogenic disturbances. The variations in vegetation carbon sink in Hunan Province result from multiple factors, with the explanatory power of various factors decreased in the order of altitude, slope, temperature, precipitation, and slope. Both altitude and slope exhibited strong explanatory power regarding the spatiotemporal distribution of vegetation carbon sink in Hunan Province, while temperature and precipitation demonstrated weaker explanatory power. Areas where vegetation carbon sink was positively correlated with temperature and precipitation accounted for 75.13% and 73.11% of the total vegetation area, respectively.

In recent years, geological hazard identification based on integrated remote sensing has been widely carried out, featuring wide surveyed areas, high time pressure, and heavy tasks. To meet the demand for the effective utilization of multi-source remote sensing data, multi-person collaboration, and quick result integration, along with the requirements of geological hazard identification tools, this study established a 3D geological hazard identification information platform. This platform, adopting a C/S architecture, allows for the effective organization and management of multi-source optical and radar remote sensing data, vector data, and 3D models and possesses functions such as the loading of multi-source data, multi-person collaboration, quick interpretations and identification, and result expression and output. This platform has successively supported fine-scale identification of hidden hazards and multiple emergency security efforts in national key areas with high geologic hazard susceptibility, such as Gansu, Yunnan, and Sichuan provinces. The application results indicate that this platform allows for rapid data supply and assists in improving work efficiency.

The rapid survey and accurate mapping of the spatial distribution of crops using remote sensing are fundamental to modern precision agriculture. However, limitations in the acquisition, processing, and analysis of remote sensing images impact the mapping accuracy of traditional crop planting structures. Therefore, there is an urgent need to conduct spatial modeling and feature analysis for the uncertainty in crop classification. Using the Ningxia Yellow River irrigation area as a trial area and farmland parcels as the basic spatial units, this study classified crops on a parcel scale utilizing multi-source remote sensing data and machine learning algorithms. Then, an uncertainty calculation model was constructed based on mixed entropy, yielding the spatial distribution of the uncertainty of crop types in farmland parcels. Afterward, multi-source auxiliary data were employed to build a regression model for the uncertainty, and the potential impacts of related geographical variables on the uncertainty were explored. The experiment results indicate that 1.49 million vector units were constructed for the farmland parcels during the farmland extraction and classification session, yielding an overall crop classification accuracy of 0.80. The mapping results aligned well with the actual agricultural management units, and the classification results proved more better than the traditional pixel-based methods. The uncertainty in the parcel-scale crop classification was generally lower, with significant differences among crop types. The uncertainty was low for rice, vegetable plots, and alfalfa, relatively higher for wheat of single- and double-cropping patterns, and moderate for maize. The uncertainty in parcel-scale crop classification is influenced by various environmental factors such as planting structure and resource conditions, exhibiting the most significant correlations with crop type and water accessibility.

Shaanxi Province, serving as both one of China’s initial pilot areas for the returning farmland to forestland/grassland project and an important energy supply base in the Yellow River basin, has made substantial investments in mineral resource development and ecological environment protection and restoration in recent years. Based on trend analysis and correlation analysis conducted using MATLAB, this study examined the spatiotemporal differentiation pattern of vegetation ecology and its responses to the dual disturbances of climate conditions and mining activities. The results indicate that from 2001 to 2022, the normalized difference vegetation index (NDVI) of Shaanxi Province exhibited an upward trend while fluctuating, with an average annual increase of 0.006. The lowest NDVI value occurred in 2015. Precipitation acted as the major factor affecting the NDVI of Shaanxi Province. In most areas, NDVI exhibited a significant positive correlation with both precipitation and humidity. The correlation between NDVI and mining activities was increasingly significant with an increase in the mining area. In some energy-based cities, NDVI decreased initially and then increased, exhibiting a V-shaped trend. Overall, mining activity made more positive than negative contributions to changes in NDVI of Shaanxi Province. The results of this study will provide foundational data and a scientific reference for ecological protection and mine restoration and management in Shaanxi Province.

A timely and accurate understanding of the spatial extents and distributions of industrial solid waste and open pits in mining areas is significant for the precise control of solid waste contamination and the ecosystem conservation. Remote sensing technology is an effective monitoring method. However, single-scale sample sets fail to fully represent the features of industrial solid waste yards and open pits with different shapes and sizes. Constructing multiscale sample sets may be effective in solving the problem of incomplete feature representation for different industrial solid waste yards and open pits, thereby enhancing the identification accuracy and generalization capability of models. By fully considering the differences in the shape and size of different industrial solid waste yards and open pits, this study proposed a remote sensing identification method for industrial solid waste and open pits based on the multiscale sample set optimization strategy. In the proposed method, a multiscale sample set was prepared based on the preprocessed data of the GF-1B, GF-1C, and GF6 satellite remote sensing images. Subsequently, a U-Net deep learning network model was constructed to identify industrial solid waste and open pits. Finally, the identification accuracy was compared with that of the single-scale sample set model. The results show that the U-Net deep learning network model based on the multiscale sample set achieved identification accuracy of 81.23 %, recall of 66.88 %, F1-score of 73.36 %, and average intersection over union of 73.55 %, suggesting improvements by 6.02, 1.02, 3.12, and 9.86 percentage points, respectively, compared to the single-scale sample set model. Overall, this study provides a reliable approach for precisely monitoring industrial solid waste and open pits.

As marine geological surveys continue to deepen, there is an urgent need to develop new-generation information technologies to accelerate the transformation of marine geological survey pattern. In recent years, the digital marine geological project has developed a comprehensive framework of trinity that integrates geological cloud, big data, and intellectualization based on the practical needs of marine geological surveys. Furthermore, the planning of three major systems, i.e., the support, core, and key systems, has been proposed for marine geological informatization. These suggest significant progress in the construction of marine geological cloud platform, marine geological big data infrastructure, and intelligent applications in marine geology. The progress also includes the building of professional marine geological nodes and network systems, the formation of a national marine geological data resource system, and the advancement in the intelligent application of marine geological operations. Information-based construction have played a full role in promoting the transformation and upgrading of geological surveys, while also serving natural resources management.

High-resolution remote sensing images have been widely applied to classification of ore deposits. However, there is a lack of studies on the information extraction and dynamic monitoring of open-pit lateritic nickel deposits. Using high-resolution remote sensing images from the Pleiades and GF-2 satellites, this study investigated the famous open-pit Tagaung Taung nickel deposit in Myanmar. First, information about surface features was extracted using object-oriented classification based on hierarchical multi-scale segmentation. Then, the dynamic changes in the nickel deposit were analyzed. Finally, qualitative and quantitative assessments of the classification accuracy were carried out. The results indicate that the hierarchical multi-scale segmentation technology exhibited encouraging classification and identification effects, with overall classification accuracy of 94.24% and 89.02% and the Kappa coefficients of 0.889 and 0.816, respectively for images from the Pleiades and GF-2 satellites. Therefore, the proposed method is suitable for the information extraction of open-pit lateritic nickel deposits. The dynamic change analysis reveals that the Tagaung Taung nickel deposit experienced continuous expansion of mining at high mining speeds from 2015 to 2017. It can be inferred that this deposit has great potential and broad prospects for resource development. The results of this study can provide technical support for the dynamic monitoring of the Tagaung Taung nickel deposit in Myanmar.

The Taiwan Strait holds a significant strategic position and great value for research. Investigating the spatiotemporal variations in sea surface temperature (SST) in the Taiwan Strait and its surrounding sea areas helps enhance the understanding of the marine-continental environmental interactions and changes in ocean currents in this region. Such investigation is particularly significant for comprehensively understanding the complex marine frontal systems within the Taiwan Strait. This study investigated the Taiwan Strait and its surrounding sea areas. Using 2016—2020 Himawari-8 satellite data, this study determined the annual, seasonal, and ten-day averages of SST remote sensing data. Based on these data, this study examined spatiotemporal variations in the SST and, accordingly, explored correlations between SST and inland precipitation and coastal fog in Fujian. The results indicate that the annual mean SST in the Taiwan Strait and surrounding sea areas exhibited a zonal distribution, increasing gradually from northwest to southeast. Seasonally, the SST exhibited two distribution patterns: a winter pattern, with isotherms approximately parallel to the coast, and a summer pattern, with isotherms more uniformly distributed. The ten-day SST data allowed for more fine-scale characterization of the spatiotemporal variations in the SST of the Taiwan Strait. The inland monthly precipitation generally exhibited a weak negative correlation with monthly mean SST, with this correlation strengthening with an increase in the distance from open sea areas. Additionally, a strong negative correlation was observed between the SST and coastal fog, with the coastal fog occurrence number trending downward with increasing SST.

This study aims to develop a machine learning algorithm based on the characteristics of AGRI data to generate an aerosol dataset with a high spatiotemporal resolution. Using aerosol data from 67 aerosol robotic network (AERONET) sites in China and its surrounding areas in 2021, this study selected data of factors such as apparent reflectance, observation angles, elevation, and MODIS surface reflectance acquired from FY-4A advanced geostationary radiation imager (AGRI)-a new generation geostationary meteorological satellite of China. Then, this study performed the inversion of aerosol optical depth (AOD) using four machine learning methods-random forest (RF), gradient boosting regression tree (GBRT), extreme gradient boosting (XGBoost), and back propagation neural network (BPNN). Using the optimal model determined based on evaluation metrics, this study achieved the AOD inversion with a spatial resolution of 4 km × 4 km based on FY-4A data. Then, this study compared the inversion results with MODIS aerosol products of roughly the same periods. The results indicate that the AOD inversion models based on the four machine learning algorithms yielded correlation coefficients (R) exceeding 0.90, mean absolute errors (MAEs) of less than 0.09, and root mean square errors (RMSE) below 0.14. This indicates that it is feasible to conduct AOD inversion using machine learning-based models. The GBRT-based model exhibited the highest inversion accuracy among the four methods, with a correlation coefficient of 0.82, MAE of 0.16, and RMSE of 0.25, as indicated by the verification results. Additionally, 47% of the inversion results fell within the expected error ranges, indicating that the results of AOD inversion from FY-4A data using the GBRT-based model were generally consistent with observed values. The comparison between the GBRT model-derived AOD inversion results and the results of MODIS aerosol products shows that the former exhibited high consistency with the latter in terms of spatial distribution, with 83.57% of grid deviations falling within the range from -1.0 to 0 and the former slightly higher than the latter.

Sandstone-type uranium deposits emerge as important uranium resources, while remote sensing is identified as a vital method for mineral resource exploration. Since sandstone-type uranium deposits typically occur underground and tend to be covered by sediments, whether remote sensing can be effectively applied to the exploration of such deposits merits investigation. This study investigated the Yingen area in the Bayingobi basin. Utilizing multi-source remote sensing data from Sentinel2, Landsat7 ETM+, ASTER, ALOS DEM, and airborne radioactivity measurements, this study performed terrain visualization, structural interpretations, K-T transformation, NDVI index calculation, alteration mineral extraction, and Th/U ratio calculation. The results were then comprehensively analyzed from the perspective of the metallogenic model, metallogenic conditions, and ore-controlling factors of secondary reduced sandstone-type uranium deposits. The analytical results indicate that the Yingen area consists of an uplift zone in the center, a depression zone in the southeast, and a slope zone between them. The granitic rocks in the uplift zone are identified as significant sources of uranium. Multiple EW-trending faults in the slope zone facilitate the migration of uranium-bearing oxidized water underground. Additionally, the water-rich areas in the depression zone, combined with strong surface evaporation, create favorable conditions for the drainage and evaporation of uranium-bearing oxidized water, further promoting groundwater circulation. Therefore, the uplift zone, slope zone, and depression zone in the Yingen area form a complete circulation system for uranium-bearing oxidized water. In combination with previous data, this study holds that the slope zone might serve as a favorable area for the formation of secondary reduced sandstone-type uranium deposits. This study also demonstrates that even in seriously overburden areas, remote sensing can provide valuable guidance for uranium exploration by identifying metallogenic conditions and ore-controlling factors.

Field verification of natural resources is a vital part of natural resource surveys. To address issues such as low efficiency and security risks encountered in traditional field verification methods, this study developed an application scheme for field verification utilizing UAV-based geographic information video technology. First, this study examined the characteristics of UAV-based geographic information video technology. Based on these characteristics, as well as the requirements of field verification, the features for the field verification were categorized into two types: land use classification and measurement assessment. Subsequently, the UAV-based geographic information video acquisition was designed for each type. The collected videos were then combined with a geographic information system (GIS) platform for feature evaluation and measurement. The application scheme was tested based on production practices. The test results indicate that the proposed scheme can improve the efficiency of the field inspection, with the measurement accuracy meeting the demand for actual production needs. Furthermore, the scheme can overcome the limitations of ground-based photography and reduce safety risks.

Analyzing the carbon stock in a terrestrial ecosystem is a key link for research on the global and regional carbon cycle. Assessing the long-time-series carbon stock in the West Dongting Lake National Nature Reserve will provide scientific data for regional ecological monitoring and management. Based on the land use data from 2000 to 2020, this study explored the spatiotemporal changes in the carbon stock of the nature reserve based on the carbon stock estimated using the InVEST model and identified key areas of carbon stock changes. The results indicate that in the past two decades, the carbon stock in the nature reserve exhibited a fluctuating upward trend, ranging from 113.5×10⁴ to 125.7×10⁴ tons. The carbon stock presented relative changing rates of less than 2% during this period, except for 2003, when the changing rate was 3.2%. Over the past two decades, the core zone of the nature reserve ranked first in carbon stock among subregions every year, followed by the pilot zones. The carbon stock in most areas of the nature reserve remained unchanged or changed slightly. Nevertheless, there still existed some areas with significant changes in the carbon stock. The key areas of carbon stock changes featured diverse spatial distribution patterns of carbon stock, such as concentrated, linear, and scattered patterns, with land use types in these areas exhibiting corresponding change intensities of carbon stock. The changes in the carbon stock in the pilot zones were greatly affected by human interference, while those in the core area were primarily related to precipitation. The results of this study will assist in scientifically promoting carbon neutrality and peak carbon dioxide emissions in the West Dongting Lake National Nature Reserve.

The increasing dependence on groundwater in the Hexi region has led to a significant drop in the groundwater table, which has induced land subsidence in some areas. Studying the relationship between groundwater changes and land subsidence hysteresis in the Hexi region holds great significance for local water resource management, land use planning, and agricultural development. This study determined the changing rate of groundwater in the study area from 2010 to 2017 using the GRACE and GLDAS data and verified the reliability of the inverted groundwater changes by combining measured data from monitoring wells. Then, this study derived the surface deformation rate of the local subsidence areas from October 2014 to June 2017 using the small baseline subset interferometric synthetic aperture radar (SBAS-InSAR) technique, as well as comparing and validating the results using the persistent scatterer interferometric synthetic aperture radar (PS-InSAR) technique. Finally, this study analyzed the relationship between groundwater changes and surface subsidence data using fast Fourier transform and time-delay correlation analysis. The results indicate that the time lags between land subsidence and groundwater changes were 74~86 d, 61~80 d, 80~99 d, and 74~99 d, respectively in the Linze, Ganzhou, Liangzhou, and Jinchuan subsidence areas, with respective correlation coefficients ranging from 0.541 to 0.593, from 0.589 to 0.689, from 0.600 to 0.750, and 0.543 to 0.630, respectively. The results of this study will provide a scientific basis for water resource management, land use planning, and agricultural development in the Hexi region.

This study investigated the temperature distribution in the sea area around the Qinshan Nuclear Power Plant using Landsat thermal infrared remote sensing data. The results indicate a strong correlation between the inversion results of temperature and the measured data, suggesting reliable inversion results. Before the operation of the nuclear power plant, the surrounding sea area exhibited relatively uniform temperature, with no significant temperature difference except for natural warming. Furthermore, the temperature along the coast remained almost unchanged in the north-south direction and displayed slight temperature gradients in the east-west direction, with temperature variation not exceeding 0.6 ℃ within 10 km from the coast. After the operation of the nuclear power, the surrounding sea area showed temperature differentiation. The distribution characteristic of thermal discharge was closely related to tides and seasons. In the same season, the increased amplitude of the temperature during ebb tides generally exceeded that during flood tide. Under the same tidal condition, the increased amplitude of the temperature in summer typically exceeded that in winter. At a certain water intake of the first plant, the surface seawater manifested a temperature rise of over 1.0 ℃ during flood tide. Landsat data generally meet the demand for research on temperature distribution in the surrounding sea area of the Qinshan Nuclear Power Plant, and the distribution of thermal discharge under specific tidal conditions can be investigated using aerial remote sensing monitoring.

The changes in land cover types will affect the amount of solar radiant energy absorbed by the land surface and then influence the radiative equilibrium of the surface ecosystem. Under the background of dramatic changes in land cover, the patterns and changes of the solar radiation absorptivity of land exert significant influence on the thermal equilibrium of the land surface. Based on the MODIS MCD12Q1 land cover data, the MCD43A3 surface albedo data, and the MCD43A2 solar zenith angle data from 2001 to 2020, along with two adjacent phases of spatiotemporal changes in the surface cover types and the solar radiant energy absorbed by land surface across northwestern China, this study analyzed and explored the impacts of the changes in land cover types on solar radiation absorption. The results indicate that the changes in land cover types in the study area are primarily characterized by reduced bare land area and the expansion of other land cover types, with the largest areal change occurring in the shift from bare land to grassland. Different types of land cover display varying solar radiation absorptivities. Water bodies exhibit the greatest solar radiation absorptivity, followed by woodland, cultivated land, grassland, and construction land, with bare land and permanent ice and snow presenting the poorest solar radiation absorptivities. The conversion of land cover types will lead to different radiation absorptivities. Specifically, the transfer from grassland, cultivated land, bare land, and permanent ice and snow primarily exhibits an increasing trend in solar radiation absorptivity, while that of water bodies and forest land largely displays a decreasing trend. The same land cover type differs in the time series of solar radiation absorption, which primarily increases for construction land, grassland, cultivated land, bare land, and water bodies but decreases for woodland and permanent ice and snow. The results of this study will provide a scientific basis and reference for research on climatic change, ecological construction, and sustainable development in northwestern China.

Mangrove forests are recognized as one of the most biodiverse and productive marine ecosystems globally. This study investigated Beibu Gulf, Guangxi Province. Using Landsat, Sentinel, and PALSAR SAR images from 1985 to 2019 as data sources, as well as the Google Earth Engine (GEE) cloud platform, this study established a multisource dataset by integrating spectral bands, spectral indices, texture features, digital elevation models (DEMs), and backscatter coefficients. Furthermore, 14 classification schemes were developed, and a mangrove remote sensing recognition model was built using an object-based random forest (RF) algorithm. Accordingly, the long-time-series spatiotemporal dynamics of mangrove forests in Beibu Gulf were monitored. The monitoring results show that the object-based RF algorithm demonstrates a high ability to identify mangrove forests. Specifically, Scheme 3 combined with data from 2019 yielded the highest overall accuracy (96.3%) and a kappa coefficient of 0.956, which are 16.3% and 0.195 higher than those of Scheme 1 combined data from 1995, respectively. The classification schemes differed in the producer’s and user’s accuracy of different surface features in the Beibu Gulf. Specifically, these schemes yielded the highest user’s and producer’s accuracy of mangrove forests exceeding 94.6% and 92.0%, respectively. From 1985 to 2019, the area of mangrove forests in Beibu Gulf showed an increasing trend, with an annual changing rate of 6.63%, and the area expanded from inland to coastal areas. The results of this study provide a reference for the protection and sustainable management of mangrove forests while also verifying the feasibility of monitoring long-term spatiotemporal dynamics of mangrove forests based on the GEE platform.

This study aims to overcome the challenges of precise mapping of open beach areas using stereo satellite imagery. Based on the complementary characteristics of stereo optical satellite imagery and light detection and ranging (LiDAR) point cloud data in geometric positioning, this study developed a high-precision mapping method that employed high-precision LiDAR point cloud data for generalized control. First, the LiDAR depth map was matched with the optical satellite images to extract corresponding point pairs for generalized control. Then, the images and control points were used as inputs for adjustment to achieve an accurate geometric positioning of the images. Finally, guided by LiDAR point cloud data and in combination with multi-baseline and multi-primitive matching algorithms and the geomorphologic refined matching (GRM) algorithm, a high-precision digital surface model (DSM) for open beach areas was automatically extracted. The results of this study indicate that the combined use of laser point clouds and stereo satellite imagery, along with photogrammetric technology, allows for the quick and accurate preparation of high-precision topographic maps of open beach areas. This study provides valuable guidance for the precise mapping of open beach areas.

To address the issues of missing small-scale surface features and incomplete continuous features in segmentation results, this study proposed a densely connected multiscale semantic segmentation network (DMS-Net) model for land cover segmentation. The model integrates a multiscale densely connected atrous spatial convolution pyramid pooling module and strip pooling to extract multiscale and spatially continuous features. A position paralleling Channel attention module (PPCA) is employed to assess feature weights for high-efficiency expression. A cascade low-level feature fusion (CLFF) module is applied to capture neglected low-level features, further complementing details. Experimental results demonstrate that the DMS-Net model achieved an overall accuracy (OA) of 89.97 % and a mean intersection over union (mIoU) of 75.59 % on an iteratively extended dataset, outperforming traditional machine learning methods and deep learning models like U-Net, PSPNet, and Deeplabv3+. The segmentation results of the DMS-Net model reveal structurally complete surface features with clear boundaries, underscoring its practical value in multiscale extraction and analysis of remote sensing information for land cover.

The Liaohe estuary of China boasts the largest red beach landscape in the world. Monitoring the spatiotemporal dynamics of Suaeda salsa in this region is of great significance for revealing the performance of conservation measures such as returning aquaculture to wetlands. Currently, satellite remote sensing technology has been widely applied to the mapping and identification of coastal vegetation including Suaeda salsa. However, existing classification methods rely on black-box models, which are difficult to interpret, while overlooking exploring identification mechanisms. This has hindered the improvement and development of related methods. Fortunately, the advancement in explainable artificial intelligence (XAI) has provided new directions for analyzing the black-box models. Considering that the decision rules in random forests are interpretable, this study developed a new method to extract the optimal decision rules from trained random forest models. Using this method, this study ultimately reconstructed the optimal decision rules used to identify Suaeda salsa, i.e., B3/B4<0.90 & B5/B3≥1.46, with an overall data accuracy exceeding 90%. Using annual Sentinel-2 images from 2017 to 2022 as a data source, the study successfully extracted the annual dynamics of Suaeda salsa in the Liaohe Estuary. Accordingly, by combining the centroid migration method, this study analyzed the spatiotemporal changes in the Suaeda salsa following the implementation of returning aquaculture to wetlands, revealing the current status that the Suaeda salsa in this region is undergoing rapid restoration.

In recent years, the rapid expansion of the aquaculture pond industry has given rise to a series of ecological and environmental issues. The Jianghan Plain is recognized as one of the most important freshwater aquaculture bases in China, and investigating changes in its aquaculture ponds is crucial for China’s ecological conservation. Focusing on the Jianghan Plain, this study proposed a method for extracting and monitoring changes in aquaculture ponds using Google Earth Engine (GEE) and Sentinel-2 dense time-series images. Using this method, which combined K-means clustering and a hierarchical decision tree classification algorithm, this study achieved accurate information extraction and spatiotemporal pattern analyses of aquaculture ponds in the plain in each year from 2016 to 2022. The results indicate that the combination of K-means and the hierarchical decision tree algorithm that integrated time-varying features allowed for accurate classification of aquaculture ponds, with an overall classification accuracy of 91.90% and a Kappa coefficient exceeding 0.84. In 2022, the aquaculture pond area of Jianghan Plain is 2 126.43 km². Among these area of aquaculture ponds, 43.24% were concentrated in Jingzhou City, while Yichang City had the fewest area of aquaculture ponds, accounting for only 0.76%. From 2016 to 2022, aquaculture ponds in the Jianghan Plain exhibited an upward trend overall and dynamics with pronounced spatial heterogeneity. Specifically, the total area increased to 2 126.43 km² from 1 947.43 km², increasing by 9.19%. The proposed methodology provides an important reference for the precise monitoring of aquaculture ponds, and the resulting dataset serves as a valuable reference and holds great practical significance for the ecological conservation and the assessment of sustainable development goals in the Jianghan Plain.

The accurate and timely detection of landslides is of great significance for reducing the threats to human life and properties, along with relevant losses, caused by landslides. This study proposed a landslide detection method using feature fusion based on convolutional neural networks (CNNs) and Segmentation Transformer (SETR). The CNN-based models utilized a fully convolutional network (FCN), U-Net, and Deeplabv3+, while the Transformer-based models used SETR. First, the landslide detection effects of the CNN-based models were evaluated. Then, SETR was introduced into the encoders of the CNN-based models, and the output of SETR was fused into the CNN decoder structure as the final output of the models. The experiments using the LandSlide4Sense dataset indicate that the fusion of typical CNNs with SETR can effectively improve the landslide detection effects. After SETR fusion, the FCN, U-Net, and Deeplabv3+ models exhibited higher F1-scores, which increased from 0.672 6, 0.727 3, and 0.687 3 to 0.686 9, 0.743 0, and 0.705 5, respectively. Given the close relationship between landslides and terrain, a digital elevation model (DEM) was incorporated into the U-Net model, which outperformed other models. As a result, the F1-score of the model increased from 0.732 5 to 0.750 3.

The change in carbon stocks is recognized as an important indicator of the carbon pool function. The effective, accurate assessment of carbon stocks is of great significance for research on regional carbon cycle and carbon source/sink dynamics, climate change mitigation, and regional sustainable development. Based on multi-time series remote sensing images (Sentinel-1 and Sentinel-2) and the Google Earth Engine (GEE) cloud computing platform, this study matched the photon point data of ICESat-2-derived vegetation canopy for the inversion of mangrove forest heights. Then, the inversion of the biomass of mangrove forests was conducted using a large-scale tree height-biomass model. Consequently, the heights, above-ground biomass, and carbon stocks of mangrove forests in Hainan Island were obtained, and their distribution and variations were further analyzed. The results indicate that in 2016, 2019, and 2022, mangrove forests in Hainan Island exhibited average heights of 6.99 m, 7.26 m, and 7.71 m, respectively, with an increasing trend observed in the highlights across all regions in the three years. Their total above-ground biomass was 400 939.48 t, 411 928.64 t, and 458 759.02 t, respectively, with average densities of 110.23 t/hm², 114.61 t/hm², and 120.02 t/hm², respectively. The above-ground biomass of Dongzhai Port and the Bamenwan area, both located in the northeastern part of Hainan, accounted for about 80% of the total. The carbon stocks of mangrove forests exhibited rates of increase ranging from 1% to 4.45% over the three years, with the top two growth rates occurring in Dongzhai Port and the Bamenwan area, respectively (4.45% and 3.17%). The results of this study can provide foundational data and a methodological reference for assessing carbon stocks of large-scale mangrove forests and serve as important parameters for mangrove forest management and protection in Hainan Island, holding THE value of widespread applications.

Traditional water-body index models exhibit high susceptibility to sediments in the shallow water areas at the boundaries of water bodies. This susceptibility leads to challenges such as water misclassification and omissions during water information extraction. Focusing on the Tanghe Reservoir, Tonghu Lake, and shallow offshore areas, this study developed a new multi-band water index (NMBWI) based on the spectral information of typical surface features derived from Landsat images. The comparison with traditional water-index models, including NDWI, MNDWI, EWI, and RNDWI, reveals that NMBWI can significantly enhance the detection effects of shallow water areas at water body boundaries, resulting in more comprehensive extraction results of water areas. NMBWI outperforms traditional water index models in terms of overall accuracy and Kappa coefficient. Furthermore, NMBWI demonstrates high universality and stability in the information extraction of shallow water areas across various water body boundaries.

Coal gangue mountains are key areas for the ecological restoration of coal mines. Understanding their geographical distribution holds great significance for regional environmental management. This study focused on part of Xinluo District, Longyan City, Fujian Province. Using GF-2 remote sensing images and data from the ASTER GDEM digital elevation model, this study extracted spectral, texture, and topographic features and then optimized these features using the sequential forward selection method. Subsequently, this study developed a model for surface feature classification using a random forest algorithm. Using this model, this study categorized surface features by integrating multi-source data and comprehensive feature combinations and then achieved the identification and information extraction of coal gangue mountains. The results indicate that the classification accuracy did not necessarily increase with the number of features. After feature selection, the number of features was reduced from 17 to 9, and the overall extraction accuracy of coal gangue mountains reached 94.07%, with a Kappa coefficient of 0.819. Factors playing an important role in the identification and information extraction of coal gangue deposit areas included elevation, slope, aspect, multi-spectral bands B1, B2, and B4 in the spectral characteristics, normalized vegetation index, and grayscale value of images. In contrast, texture features merely improved the accuracy of surface feature types with distinct textural variations, while producing limited effects on the information extraction of coal gangue mountains. For the study area, only the mean texture feature produced significant effects on the information extraction accuracy of coal gangue mountains. The combination of random forest and feature optimization algorithm can effectively enhance the information extraction accuracy of coal gangue mountain, efficiently integrate multi-source feature data, and accelerate model calculation, serving as a practically feasible method for the information extraction of coal gangue mountains.