In the context of achieving peak carbon dioxide emissions and carbon neutrality, conducting a remote sensing-based ecological assessment and monitoring analysis is greatly significant for ascertaining the ecological condition in time and formulating scientific and reasonable ecological protection policies. The early remote sensing-based ecological assessment indices, simple and involving complex processes, are difficult to find wide applications. In contrast, the remote sensing ecological index (RSEI), contributing to elevated assessment efficiency, has been extensively used. To gain a deeper understanding of RSEI, this study describes its background, calculation method, and research status and provides a summary of the current issues and regional adjustments. Furthermore, it analyzes the main application directions of RSEI, namely the in-depth analyses of regional ecological assessment and change monitoring. Finally, the study proposes that despite a broad space for RSEI development, it is necessary to conduct research into the spatiotemporal scales of images, storage and batch processing capabilities, model adaption, and intelligentization.

Timely and accurate detection and statistical analysis of the spatial distributions and time-series variations of water bodies like rivers and lakes holds critical significance and application value. It has become a significant interest in current remote sensing surface observation research. Conventional water body extraction methods rely on empirically designed index models for threshold-based segmentation or classification of water bodies. They are susceptible to shadows of surface features like vegetation and buildings, and physicochemical characteristics like sediment content and saline-alkali concentration in water bodies, thus failing to maintain robustness under different spatio-temporal scales. With the rapid acquisition of massive multi-source and multi-resolution remote sensing images, deep learning algorithms have gradually exhibited prominent advantages in water body extraction, garnering considerable attention both domestically and internationally. Thanks to the powerful learning abilities and flexible convolutional structure design schemes of deep neural network models, researchers have successively proposed various models and learning strategies to enhance the robustness and accuracy of water body extraction. However, there lacks a comprehensive review and problem analysis of research advances in this regard. Therefore, this study summarized the relevant research results published domestically and internationally in recent years, especially the advantages, limitations, and existing problems of different algorithms in the water body extraction from remote sensing images. Moreover, this study proposed suggestions and prospects for the advancement of deep learning-based methods for extracting water bodies from remote sensing images.

The vegetation optical depth (VOD) serves as a microwave-based method for estimating vegetation water content and biomass. Compared to optical remote sensing, the satellite-based VOD, exhibiting a lower sensitivity to atmospheric disturbances, can measure the characteristics and information of vegetation in various aspects, thus providing an independent and complementary data source for global vegetation monitoring. It has been extensively applied to investigate the effects of global climate and environmental changes on vegetation. Discerning the research advances of VOD application in the dynamic monitoring of global vegetation is critical for VOD’s further development and application. Hence, this study first presented the primary methods for obtaining the VOD through inversion of passive and active microwave data, comparatively analyzing the principal characteristics of various sensor VOD products. Then, this study generalized the current research advances of VOD in the dynamic monitoring of vegetation in terms of vegetation characteristic monitoring (like vegetation water content and biomass), carbon balance analysis, drought monitoring, and phenological analysis. Finally, this study expounded the advantages, limitations, and improvement approaches of VOD products, envisioning the application prospect of VOD in the dynamic monitoring of vegetation.

To obtain the fundamental data of mine environments objectively, this study monitored the damaged mining land and the ecological restoration land in abandoned open-pit mines in China by combining remote sensing data with multi-source data, computer automated information extraction with human-computer interactive interpretation, and comprehensive laboratory research with field investigation. The remote sensing monitoring in 2022 shows that the mining land of abandoned open-pit mines in China covered an area of 82.74×10⁴ hm², representing 0.86‰ of the national land area, primarily distributed in Inner Mongolia and Xinjiang Uygur autonomous regions as well as Hebei, Shandong, and Heilongjiang provinces. Among them, the damaged mining land and the ecological restoration land accounted for 50.74×10⁴ hm² and 32.00×10⁴ hm², respectively, with an ecological restoration rate of 38.68%. The mining land of abandoned open-pit mines occupied primary farmland of 2.63×10⁴ hm², representing 3.18% of the total mining area. The mining land of nationwide abandoned open-pit mines within the ecological red line accounted for 8.09×10⁴ hm², representing 9.77% of the total mining area. The mining land of nationwide abandoned open-pit mines, coinciding with the result of the third national land resource survey (mining land), totaled 30.13×10⁴ hm², representing 36.42% of the total mining area. This study preliminarily analyzed the present situation and existing problems of remote sensing work involving the mining land of nationwide abandoned open-pit mines, the occupation of primary farmland, the mining land of such mines within the ecological red line, and corresponding environmental restoration and governance. Finally, this study proposed countermeasures and suggestions in this regard.

Inland surface water bodies, including rivers, lakes, and reservoirs, are significant freshwater resources for human beings and ecology, and their monitoring and control are greatly significant. Optical remote sensing provides great convenience for the monitoring of surface water resources, proving to be an important means for the information extraction and dynamic monitoring of inland surface water bodies. This study reviews the basic principles, remote sensing data sources, methods, existing issues, and prospects of the information extraction of water bodies. Owing to the unique characteristics of the remote sensing images of inland surface water bodies, their information can be extracted in an accurate, scientific, and effective manner using remote sensing. Multiple remote sensing data resources can be applied to the information extraction, and the optical remote sensing-based extraction methods include the threshold value method, classifier method, object orientation method, and deep learning method. Given that different methods have unique advantages, disadvantages, and applicable conditions, selecting appropriate multi-source data and varying methods based on the conditions of study areas tend to improve the information extraction accuracy. Nevertheless, there still exist some issues in the optical remote sensing-based water body information extraction, such as the balance of spatiotemporal resolution of remote sensing data, the information mining of water body characteristics, the generalization ability of water body models, and the uniformity of criteria for accuracy evaluation.

Snow proves to be both an important factor in characterizing the surface cryosphere and a critical parameter for weather and hydrological phenomena. Employing remote sensing to conduct long-term and large-scale monitoring of snow morphologies and their changes plays a vital role in research into global climate change, investigations into hydrology and water resources, and geological disaster prevention. After decades of development, significant progress has been made in the field of remote sensing-based snow monitoring technology both in China and abroad. Accordingly, the products for remote sensing-based snow monitoring have become increasingly abundant, and the snow-orientated inversion algorithms have been continuously improved. This paper provides a summary of the existing, widely applied products after categorizing them into three types: snow-cover extent (SEC), snow coverage, and snow depth/snow water equivalent (SWE) products. Furthermore, this study organizes the commercialized remote sensing inversion algorithms used in existing, typical SEC and SWE products. The review of advances in the relevant scientific research reveals that, with the constant presence of sensors with high temporal and spatial resolutions in China and abroad and the support of both novel optical and microwave data sources and new technologies, researchers have gradually improved the accuracy of snow-orientated inversion algorithms by optimizing these algorithms based on regional characteristics. This will provide more support for continuously improving remote sensing-based snow monitoring products in the future.

Rapid identification and detection of landslides can both meet the requirement of timely responses to disasters and hold great significance for loss assessment and rescue post-disaster. This study proposed a deep learning-based automatic information extraction method for landslides to improve their detection accuracy. Specifically, the model input of this method includes the remote sensing images of the target areas, data from digital elevation models, and variation characteristics extracted using robust change vector analysis (RCVA). Furthermore, a U-Net model integrating dense upsampling and asymmetric convolution is designed to improve the identification accuracy. Taking Wenchuan, Sichuan Province as the study area, this study designed experiments to test the pixel-level image segmentation accuracy of landslides using different data combinations and methods. The results indicate that the improved U-Net model proposed in the study can produce the optimal image segmentation results of landslides.

Coalbed methane (CBM), a type of self-sourced unconventional clean energy, occurs in coal seams and their surrounding rocks. Conventional exploration methods for CBM enrichment areas are laborious, while remote sensing provides a new approach to the rapid exploration of such areas. The basic principle behind the remote sensing-based exploration of CBM enrichment areas is as follows: ① The extraction and comprehensive analysis of multi-source data are conducted based on the comparison between the spectral features of typical surface features and those of surface feature anomalies, including rock and mineral alterations, vegetation anomalies, and thermal anomalies, caused by hydrocarbon micro-seepage in CBM enrichment areas, along with data obtained using geophysical prospecting methods like geological, seismic, and magnetotelluric methods; ② The distribution range and gas-bearing properties of CBM enrichment areas are gradually delineated. This paper reviews the hydrocarbon seepage in the CBM enrichment areas and the response mechanisms of spectral anomalies of surface rocks, minerals, and vegetation. It covers the applications of various methods based on the inversion of spectral parameters of surface rocks, minerals, and vegetation, together with the inversion of the spectral anomalies of surface features, in the exploration of potential CBM enrichment areas. Additionally, this paper elucidates the different explanations for surface thermal anomalies caused by CBM-bearing strata, as well as major methods to improve the accuracy of surface temperature inversion and their applications. In the future, the main approach to achieving low-cost, rapid exploration of CBM enrichment areas will be the analysis and information extraction of three-dimensional, multi-source information based on the combination of remote sensing technology with the geological data, seismic exploration, and geomagnetic prospecting of coalfields.

Inland water bodies, as irreplaceable resources in ecosystems, play a vital role in climate change and regional water circulation. Scientifically and accurately monitoring the distribution and dynamic changes of water bodies is critical for ecosystem balance maintenance, sustainable human development, and early warning of floods and droughts. However, current research primarily focuses on the static monitoring of inland water bodies, lacking high-resolution monitoring of dynamic changes in water bodies. Hence, relying on the Google Earth Engine (GEE) cloud computing platform, this study monitored the dynamic changes of water bodies at a spatial resolution of 10 m, with the Sentinel-2 surface reflectance data in 2020 as the data source. First, the optimal water body monitoring features were selected by examining the features of typical land cover types in Sentinel-2 spectral bands and water indices. Then, an automatic extraction method for water body training datasets was proposed in conjunction with priori water body products, obtaining high-confidence water body training samples. Furthermore, the spectral angle (SA) and Euclidean distance (ED) methods were integrated based on the Dempster-Shafer (D-S) evidence theory model, and a SA-ED dynamic monitoring model for water bodies was developed combined with the extracted optimal water body monitoring features. Finally, the stability of the SA-ED model was tested with Henan Province as a study area, demonstrating that the SA-ED model can effectively monitor the dynamic changes in water bodies. The SA-ED model yielded an overall monitoring accuracy of 97.03% for water bodies in Henan Province, with user accuracy of 95.85% and producer accuracy of 95.17% for permanent water bodies, user and producer accuracies of 96.21% and 93.82% for seasonal water bodies, respectively. The results of this study provide a novel approach for the fine-resolution monitoring of dynamic changes in water bodies.

Multi-label classification of remote sensing images plays a fundamental role in remote sensing analysis. Parsing given remote sensing images to identify semantic labels can provide a significant technical basis for downstream computer vision tasks. With the continuously improved spatial resolution of remote sensing images, many remote sensing objects with different scales, colors, and shapes are distributed in various zones of images, posing high challenges to the multi-label classification task of remote sensing images. This study focuses on the multi-label classification of images in the field of remote sensing, summarizing and analyzing the frontier research advances in this regard. First of all, this study expounded the problem definition for the multi-label classification task of remote sensing images while generalizing the commonly used multi-label image datasets and model evaluation indicators. Furthermore, by systematically presenting the frontier progress in this field, this study delved into two key tasks in the multi-label classification of remote sensing images: feature extraction of remote sensing images and label feature extraction. Finally, based on the characteristics of remote sensing images, this study analyzed the current challenges of multi-label classification as well as subsequent research orientation.

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 monitoring and assessment of urban ecological quality holds critical significance for sustainable urban development. To assess the ecological quality of developed coastal cities in China in recent years, this study investigated Nanjing City based on the Sentinel-2A remote sensing images obtained in 2021. It constructed a novel remote sensing green index (RSGI) model involving green spaces, blue spaces, buildings, and impervious surfaces for assessing the ecological quality of Nanjing. First, neural network supervised classification was applied to the Sentinel-2A remote sensing images, constructing the RSGI to assess the ecological quality of various districts in Nanjing. Then, the correlations between the RSGI and urban ecological factors were analyzed using the Pearson correlation coefficient. Finally, the ecological similarity between the districts was analyzed using the agglomerative hierarchical clustering method. The results of this study are as follows: (1) The ecological quality of Nanjing presented a pattern of low RSGI values in the central portion and high RSGI values in the surrounding areas, with the highest and lowest RSGI values (0.86 and 0.38) observed in Luhe and Qinhuai districts, respectively, differing by 0.48; (2) The RSGI exhibited a positive correlation with the density of green spaces and negative correlations with the densities of population, buildings, and impervious surfaces, all at the 0.01 level; (3) With the ecological similarity of 70% as the threshold, 11 districts in Nanjing were categorized into four clusters: Qinhuai, Gulou, and Jianye districts in the first cluster, Yuhuatai and Qixia districts in the second cluster, Xuanwu and Gaochun districts in the third cluster, and the rest four districts in the fourth cluster. The results of this study can provide a scientific basis for subsequent urban planning and sustainable development of Nanjing.

High-resolution remote sensing images contain rich data and information, which reduce the difference between the target and the background, resulting in substandard detection accuracy and reduced target detection performance. Based on the deep learning algorithm You Only Look Once (YOLO), this study designed a lightweight network model GC-YOLOv5 by combining end-to-end coordinate attention (CA) and the lightweight network module GhostConv. The CA was employed to encode channels along the horizontal and vertical directions, enabling the attention mechanism module to simultaneously capture remote spatial interactions with precise location information and helping the network locate targets of interest more accurately. The original ordinary convolutional module convolutional-batchnormal-SiLu (CBS) was replaced by the GhostConv module, reducing the number of parameters in the feature channel fusion process and the size of the optimal model. Experiments were conducted on the GC-YOLOv5 using the publicly available NWPU-VHR-10 dataset, with the robustness of the model verified on the RSOD dataset. The results show that GC-YOLOv5 yielded a detection accuracy of 96.5% on the NWPU-VHR-10 dataset, with a recall rate of 96.4% and mAP of 97.7%. Moreover, GC-YOLOv5 achieved satisfactory results on the RSOD dataset.

Lakes constitute a crucial part of terrestrial ecosystems. Changes in the water areas of lakes significantly influence environments and human production activities. Poyang Lake, the largest freshwater lake in China, has experienced many floods and droughts in recent years, thus necessitating its dynamic monitoring. With 175-phase Landsat images of Poyang Lake from 2000 to 2021 as the data source, this study comparatively analyzed four water body extraction methods: the normalized difference water index (NDWI), the modified normalized difference water index (MNDWI), the automated water extraction index (AWEI), and the spectrum photometric method (SPM), determining the optimal water body extraction index for Poyang Lake. Moreover, based on the 175-phase area data, this study delved into the inter-annual area variation trend from 2000 to 2021 as well as the intra-annual seasonal variations. Furthermore, it established the area - water level model by combining 50 sets of water level data from 2009 to 2013 and 2017 to 2018. The results show that: ① The AWEI model, outperforming the other three models in the extraction accuracy, was employed for the water body extraction of Poyang Lake; ② The area of Poyang Lake exhibited significant seasonal variations, large inter-annual fluctuations in the wet season, and relatively gentle inter-annual fluctuations in the dry season; ③ The area - water level piecewise linear model of the Tangyin gauging station proved optimal, which can predict the water coverage area based on real-time water level observations in Poyang Lake, compensating for the limitation of visible spectral remote sensing methods in monitoring the lake water coverage during cloudy and rainy weather.

Land surface temperature (LST) proves to be an important parameter in surface processes on regional and global scales, and its spatiotemporal information can be obtained through thermal infrared remote sensing. However, the constraints of thermal infrared sensors (TIRSs) themselves and the inability of thermal infrared electromagnetic waves to penetrate clouds render it impossible to obtain LST with a high spatiotemporal resolution currently. This study presents a method for reconstructing hourly LST at 100-m resolution in all weathers. This method consists of three main steps: ① cloudy LST at four moments is reconstructed using a moderate resolution imaging spectroradiometer (MODIS) based on the conventional annual temperature cycle (ATC) model; ② the daily variation curve of LST is estimated based on the daily trend in the skin temperature (SKT); ③ with spectral indices as regressors, spatial downscaling is conducted for the hourly LST using Extreme Gradient Boosting (XGBoost). The results show that the proposed reconstruction method can obtain spatiotemporally continuous LST products, improve the spatial resolution of LST, and provide more details. The validation of the hourly 100-m-resolution LST using data from the surface radiation budget network (SURFRAD) developed by the U.S. indicates that the reconstructed hourly LST exhibits roughly the same trend as the measured values of the SURFRAD. The method for reconstructing all-weather hourly LST boasts high accuracy, with R² of 0.95, a root mean squared error (RMSE) of 3.75 K, and a bias of 0.75 K.

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.

Forest fires are one of the most significant disturbance factors affecting forest ecosystems. Exploring their spatio-temporal variations and forest restoration holds certain sociological and ecological significance. The Great Xing’an Range, possessing the largest primitive area in China, is a key area suffering frequent forest fires. Hence, this study extracted the distribution information of burned zones in the Great Xing’an Range from 2002 to 2021 from the MODIS time series products involving burned zones, land cover, and gross primary productivity (GPP). Moreover, it statistically analyzed the post-fire forest restoration. The results show that: ① Fires in the forest area of the Great Xing’an Range showed an overall downward trend from 2002 to 2021, but the burned areas showed fluctuating changes. Both the burned area and fire frequency were the highest in 2003, followed by 2008, with the lowest burned area seen in 2019; ② Forest fires occurred primarily in spring and autumn, with the highest burned area and fire frequency in March and the second highest fire frequency in September; ③ Forest fires manifested an uneven spatial distribution from northeast to southwest, predominantly in the Great Xing’an Range within Heilongjiang and Hulunbuir City of Inner Mongolia. Moreover, the forest fire area in Inner Mongolia far exceeded that in Heilongjiang. The analysis of forest types in burned zones reveals that the burned areas decreased in the order of broad-leaved, mixed, and needle-leaved forests. According to the time series analysis of GPP in burned zones, GPP values recovered the fastest in the first year post-fire, but it took nearly seven years to recover to the pre-fire growth level. Different forest types manifested significantly distinct post-fire restoration rates, which decreased in the order of broad-leaved, needle-leaved, and mixed forests. Overall, ascertaining the spatio-temporal distribution of forest fires can provide data support for the arrangement and adjustment of fire prevention and control efforts, while investigating the post-fire forest restoration can provide a scientific basis for the rehabilitation and sustainable development of forests.

Crown volumes serve as a crucial factor for surface ecological monitoring. Laser point clouds can characterize the fine-scale spatial morphologies of individual trees, providing a data basis for crown volume extraction. However, existing laser point cloud-based methods for extracting crown volumes of individual trees are sensitive to parameters and exhibit low degrees of automation. Based on the analysis of the three-dimensional morphological structures of individual trees, this study proposed a spherical coordinate integration method for extracting crown volumes of individual trees based on the terrestrial laser scanning (TLS) point clouds. First, the crown points were obtained through visual elevation threshold-based segmentation according to the elevation distributions of TLS point clouds. Then, the TLS point clouds were projected onto the spherical coordinate space for infinitesimal segmentation into triangular pyramids. Finally, the crown volumes were determined through the three-dimensional spherical coordinate integration. Six types of TLS point cloud data for individual trees were selected for tests. As indicated by the test results, the proposed method effectively considers factors like crown morphology and point cloud density, achieving a maximum absolute error of 2.33 m³ and a maximum relative error of 3.40% in the crown volume extraction of individual trees. It manifests higher extraction accuracy and stability compared to the existing methods. Therefore, this study holds significant reference value for extracting tree parameters based on TLS point clouds.

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.

Vegetation can indicate the changes in ecological environments. Analyzing the spatio-temporal variations and influencing factors of vegetation phenology holds critical significance for exploring the carbon, water, and energy balance of terrestrial ecosystems. In this study, the MOD13Q1 EVI dataset was employed to extract the start of season (SOS), the growing season length (GSL), and the end of season (EOS) for vegetation in Beijing from 2001 to 2020 using the double logistic (D-L) function fitting method and the dynamic threshold method. The spatio-temporal variations of vegetation phenology in urban and rural areas of Beijing were analyzed by constructing an urban-rural gradient zone. The response of vegetation phenological parameters to climate factors like temperature, precipitation, sunshine, and wind speed, as well as urban heat island intensity and urbanization, was investigated through regression and trend analyses. The results show that from 2001 to 2020, the vegetation phenology of Beijing manifested a trend of earlier SOS, extended GSL, and delayed EOS. Compared to grassland, woodland and shrubs manifested earlier SOS and later EOS, suggesting that the phenology of woody plants started earlier and ended later. As revealed by the relationship between climate factors and phenology, temperature, precipitation, sunshine, and wind speed all displayed certain effects on vegetation phenology in Beijing, with SOS and EOS being the most sensitive to sunshine and wind speed, respectively. The vegetation phenology was characterized by a significant gradient change along the urban-suburban-rural direction. Compared to the rural area, the urban area showed SOS 12.2 d earlier and EOS 18.9 d later on average. The urban nighttime heat island intensity was significantly correlated with the SOS of vegetation in the urban-rural gradient zone (p<0.01). Moreover, the SOS, GSL, and EOS were significantly linearly correlated with population density, urban built-up area, and GDP per square kilometer of land (p<0.01). Therefore, urbanization played a significant role in advancing SOS, extending GSL, and delaying EOS of vegetation phenology in Beijing.

Rapid and accurate estimation and spatial distribution mapping of soil organic carbon content in farmland facilitate the refined management of soil and the development of smart agriculture. This study investigated three typical farmland areas in the Huangshui River basin of Qinghai Province using 296 soil samples and corresponding field in situ spectra collected synchronously. The unmanned aerial vehicle (UAV) with a hyperspectral camera was employed for image acquisition, and the soil samples were tested for spectral acquisition and organic carbon content in the laboratory. The spectral reflectance was transformed into seven different forms, and the main characteristic bands were screened out through correlation analysis. Using multiple linear regression, partial least squares regression, and random forest, the experimental spectra, field in situ spectra, and UAV spectra were modeled, with the accuracy of the models compared. The UAV spectra were corrected using the direct spectral conversion method, and the optimal model of corrected UAV spectra was used for modeling. The model was substituted into the UAV hyperspectral images for the organic carbon content mapping. Finally, the farmland areas meeting the mapping accuracy requirements were analyzed and discussed. The results show that: ① The multiple linear regression after logarithmic transformation of UAV hyperspectra failed to estimate the organic carbon content, with a relative percent deviation (RPD) of 1.375. Except for it, the experimental spectra, field in situ spectra, and original spectra of UAV hyperspectra as well as all conversion methods could estimate the organic carbon content, with coefficients of determination (R²) ranging from 0.562 to 0.942, root mean square errors (RMSEs) ranging from 1.713 to 5.211. and RPDs between 1.445 and 4.182; ② Among all spectral transformation methods, multiple scatter correction and first-order differential transformation exhibited the highest correlation with the organic carbon content, presenting characteristic bands of 429~449 nm, 498~527 nm, 830~861 nm, and 869 nm; ③ As revealed by the modeling results, the random forest model manifested the highest accuracy, followed by the partial least squares model and the multiple linear regression model in turn. The corrected UAV spectra yielded improved modeling accuracy; ④ The inversion accuracy of the three farmland areas all met the mapping requirements, with R² values above 0.88. Farmland A exhibited the highest average organic carbon content of 28.88 g·kg^-1 and an overall uniform spatial distribution. Farmland B manifested average organic carbon content of 13.52 g·kg^-1 and a significantly varying spatial distribution. Farmland C displayed the lowest average organic carbon content of 8.54 g·kg^-1 and significant differentiation between high and low values. This study can be referenced for the application of UAV hyperspectral remote sensing technology to the field-scale estimation and digital mapping of soil organic carbon content.

Hyperspectral technology has become the major means of coastal wetland monitoring. However, traditional hyperspectral classification methods usually face challenges such as insufficient feature extraction, the same surface features corresponding to different spectra, and fragmented scenes. To solve these problems, this study proposed a new classification method by applying Transformer to hyperspectral classification. This vision Transformer (ViT)-based method expanded the receptive field by learning global spatial features using non-local technology, thus overcoming the insufficient extraction of discriminant features. Meanwhile, this method enhanced the cross-layer information interchange through cross-layer adaptive residual connection, thus eliminating information loss. This study, taking NC16 and NC13 wetland datasets of the Yellow River Delta as experimental data, compared the classification method proposed in this study to support vector machine (SVM), one-dimensional convolution neural network (1DCNN), contextual deep convolution neural network (CDCNN), spectral-spatial residual network (SSRN), hybrid spectral network (HybridSN), and ViT. The comparison results show that the new method yielded significantly elevated overall accuracy (OA) of up to 96.24% and 73.84%, average accuracy (AA) reaching 83.42% and 74.87%, and Kappa coefficients of up to 94.80% and 68.94%, respectively for the two datasets.

Yunnan Province has abundant species resources but fragile ecosystems, and the ecological vulnerability is closely related to vegetation cover. Hence, based on the normalized difference vegetation index (NDVI) from the MOD13Q1 dataset for 2000—2022, this study dynamically monitored the spatio-temporal variations of vegetation using the maximum value composite (MVC), Theil-Sen median trend analysis, and Mann-Kendall significance test. Moreover, this study delved into the response of vegetation to factors like topography, climate change, and land cover through correlation analysis. The results show that: ① From 2000 to 2022, the overall vegetation coverage of Yunnan Province was relatively high, with average annual NDVI values ranging from 0.74 to 0.90, showing a fluctuating upward trend. Of the whole area, 91.17% exhibited an increasing vegetation coverage trend, with the fastest growth rate seen in northeastern Yunnan; ② Regional differences were observed in vegetation cover, which was higher in southeastern and southwestern Yunnan compared to northwestern, central, and northeastern Yunnan; ③ The NDVI values of Yunnan Province were relatively stable below the altitude of 3 900 m, and decreased with increasing altitude in the case of over 3 900 m; ④ The NDVI values were the lowest with slopes below 3°, and with an increase in slope, they increased first and then decreased; ⑤ The planar slope aspect displayed the lowest NDVI values, and other slope aspects showed minimal impact on vegetation growth; ⑥ From 2000 to 2022, the vegetation cover in central, southeastern, and northeastern Yunnan was positively correlated with precipitation, suggesting that precipitation in these areas was favorable for vegetation growth. However, the vegetation cover in southwestern and northwestern Yunnan showed a negative correlation with precipitation. Additionally, the vegetation cover in the whole region and various areas was positively correlated with temperature, suggesting that temperature is beneficial to vegetation growth. The results of this study will provide a scientific basis for strengthening ecological environment construction and ecological management in Yunnan Province.

Exploring the remote sensing-based classification of coastal wetlands is significant for their conservation and planning. Hence, this study investigated the Yellow River Delta with the 8-view Landsat8 OIL images from March to October 2019 as the data source. It constructed seven classification schemes based on different features of the images on the Google Earth Engine (GEE) cloud platform. Then, it employed the random forest classifier to classify different feature sets, with the scheme exhibiting the best classification effects selected for mapping the wetland categories of the Yellow River Delta. Considering poor data quality in August and September due to cloud contamination, this study filled in the cloudy zones using the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM) algorithm. The results show that: ① The predicted images generated from the ESTARFM manifested a high correlation with the real image bands, with R values above 0.73, suggesting that the reconstructed images could be used in this study; ② The random forest algorithm was used to classify the surface feature types in the study area. Through optimal feature selection, the classification results of Scheme 7 demonstrated an overall accuracy of 92.28%, higher than those of conventional schemes, with a Kappa coefficient of 0.91, aligning with the actual wetland conditions. The results of this study can assist in deeply understanding the spatial distributions of different wetlands in the area, and provide a scientific basis for the conservation and planning of the regional ecological environment.

In the early morning of August 18, 2022, a flash flood occurred in Datong Hui and Tu Autonomous County, Xining City, Qinghai Province, resulting in 26 deaths and 5 missing. This flash flood is a typical event of multiple casualties caused by a creek disaster. The superimposed effect of rainfall directly led to this flash flood. The early continuous rainfall caused soil moisture content to reach or approach saturation. On the night of August 17, 2022, local short-time heavy rainfall smashing historical records, which could not infiltrate into the soil or be retained by vegetation, resulted in a flash flood. As revealed by the comprehensive analysis of remote sensing data, digital elevation model, field data, and media data, the flash flood area exhibited a large catchment area, a narrow river valley, a high relative height difference, a shallow river channel, and many obstacles. Consequently, the flash flood manifested high potential energy, a long movement distance, and locally severe backwater overflow, destroying some houses, farmland, and roads on both sides of the river channel. Against the backdrop of global changes, low-risk areas of flash floods, including the arid region of northwest China and the Qinghai-Tibet Plateau, display significantly increased precipitation and frequent local short-time heavy rainfall. Hence, creeks in these low-risk areas are exposed to increasing risks of flash floods and even catastrophic ones. Additionally, heavy rainfall might induce the recurrence of flash floods in disaster areas.

Landslides may cause the loss of lives and property, and an accurate and complete map showing the spatial distribution of landslides and the determination of landslide susceptibility areas assist in guiding the optimization of the production, living, and ecological spaces. However, landslide investigations are complicated by dense vegetation. LiDAR technology enables the presentation of actual terrain features, thereby achieving landslide identification in densely vegetated areas. This study obtained the LiDAR point cloud data of the study area through ground-imitating flight and then built a digital elevation model (DEM) through data processing. Then, based on mountain shadow analysis, color-enhanced presentation, and 3D scene simulation, the locations and scales of existing landslides in the study area were identified. The field verification revealed an interpretation accuracy of landslides of up to 86.4%. For the assessment of landslide susceptibility areas, this study, with existing landslides as samples, delineated landslide susceptibility areas through remote sensing classification for the first time. Specifically, images were synthesized using the landslide-related elevations, slopes, and surface undulations, and then landslide susceptibility areas were determined using the support vector machine (SVM) classification method. The analysis of the inspection samples reveals a landslide identification accuracy of 81.91%. The results show that the image identification based on high-accuracy LiDAR data and visually enhanced images allows for the delineation of small landslides and that the SVM classification method enables the accurate location of landslide susceptibility areas. This study provides a basis for the future planning and optimization of the production, living, and ecological spaces.

This study aims to solve the challenges faced in the prediction of sugarcane yield in Guangxi, such as varied crops, complex investigations in the sugarcane planting areas, and difficult acquisition of remote-sensing images caused by the changeable weather. To this end, an improved semantic segmentation algorithm based on Sentinel-2 images was proposed to automatically identify sugarcane planting areas, and an extraction method for representative spectral features was developed to build a sugarcane yield prediction model based on multi-temporal Sentinel-2 and Landsat8 images. First, an ECA-BiseNetV2 identification model for sugarcane planting areas was constructed by introducing an efficient channel attention (ECA) module into the BiseNetV2 lightweight unstructured network. As a result, the overall pixel classification accuracy reached up to 91.54%, and the precision for sugarcane pixel identification was up to 95.57%. Then, multiple vegetation indices of different growth periods of the identified sugarcane planting areas were extracted, and the Landsat8 image-derived vegetation indices were converted into Sentinel-2 image-based ones using a linear regression model to reduce the differences of the indices derived using images from the two satellites. Subsequently, after the fitting of time-series data of the extracted vegetation indices using a cubic curve, the maximum indices were obtained as the representative spectral features. Finally, a yield prediction model was built using multiple machine learning algorithms. The results indicate that the test set of the decision tree model built using the fitted maximum values of the vegetation indices yielded R? of up to 0.759, 4.3%, higher than that (0.792) of the model built using the available actual maximum values. Therefore, this method can effectively resolve the difficulty in developing an accurate sugarcane yield prediction model caused by changeable weather-induced lack of remote sensing images of sugarcane of the key growth periods.

The concentrations of negative oxygen ions and particulate matter 2.5 (PM_2.5) serve as important indicators in the assessment of the degrees of air freshness and cleanliness. Based on 2018-2022 data from 50 negative oxygen ion observation stations affiliated with the Fujian meteorological departments, along with the ecological parameters such as aerosol, vegetation index, and surface brightness temperature obtained by satellite-based remote sensing inversion, this study built estimation models for the concentrations of negative oxygen ions and PM_2.5 using the Cubist machine learning method. Accordingly, it developed an air freshness index (AFI), and the fine-scale mesh-based monitoring of regional air freshness was achieved. The results show that the estimation model for the negative oxygen ion concentration yielded goodness of fit of 0.838 and 0.526 for the training and test sets, respectively. In comparison, the estimation model for the PM_2.5 concentration exhibited goodness of fit of 0.968 and 0.867 for the training and test sets, respectively. Then, this study developed the AFI by comprehensively considering negative oxygen ions and PM_2.5. Then, this study graded the AFI using the frequency quartiles of the statistical data series combined with the spatiotemporal changes in negative oxygen ions. The results indicate that the AFI monitoring results based on meteorology, remote sensing, and machine learning algorithms are consistent with the actual conditions.

In recent years, target detection, as an important branch of computer vision technology, has been widely applied in fields such as medicine, military affairs, and urban rail transit. As satellite and remote sensing technologies advance, images obtained using these technologies contain abundant information. This makes it crucial to conduct automatic target detection and understanding of these images. However, due to the random directions and dense distribution of targets in remote sensing images, conventional methods are prone to lead to missing or incorrect detection. In response, this study proposes a multi-convolution kernel feature combination-based adaptive region proposal network (MFCARPN) algorithm for multi-directional detection. This algorithm introduces multiple convolution kernel features for target extraction. The weight parameters of these convolution kernel features can be determined through adaptive learning according to the differences between the targets, yielding the characteristic patterns that match better with targets. Meanwhile, in combination with the original features of the targets, the parameters of the classification and regression model vary dynamically according to the difference between targets. Thus, the RPN’s adaptive ability can be improved. The experimental results indicate that the mAP of the standard dataset DOTA reached up to 75.52%, which is 0.5 percentages higher than that of the baseline algorithm GV. Therefore, the MFCARPN algorithm proposed in this study proves effective.

Based on thermal infrared and multispectral remote sensing data, this study analyzed the thermal spring-related structures interpreted from remote sensing images. Thermal springs crop out at the intersections of asterisk- and lambda-shaped structures, with asterisk-shaped structures exhibiting more favorable conditions. By delving into remote sensing characteristics related to thermal springs, this study presented remote sensing factors like surface temperature, hydroxyl anomaly, soil moisture, hydrographic net, and elevation. Using mathematical geostatistics and prediction methods based on geographical information system (GIS), including the weight of evidence, prospecting information content method, and feature factor method, this study analyzed the geological, remote sensing, and geophysical factors related to thermal springs for mathematical geostatistics and prediction. The comprehensive analysis reveals 57 favorable geothermal areas, including 8 in category A, 18 in category B, and 31 in category C. All the category-A favorable geothermal areas include known geothermal sites, and one category-B favorable area reveals a 51.6 ℃ thermal spring, suggesting reliable prediction results. The methodology of this study provides a new approach for geothermal resource prediction.

Building heights are necessary for urban informatics, providing a significant basis for the planning and early warning of risks for urban construction. The shadow method, which can measure the heights of urban buildings on a large scale at a low cost, faces challenges such as low efficiency, accuracy, and robustness in building height inversion in complex shadow scenes. This study proposed a measurement method for these scenes. First, the shadows were measured and delineated using the fishing net method combined with multiple constraints. Second, the shadow lengths of all the zones divided were obtained, and the optimal values were determined using the quartile method and the bidirectional approximation strategy. Third, the shadow lengths were determined through a comprehensive assessment of the optimal values of all zones. The results show that 90.6% of building heights calculated using the new method exhibited absolute errors ranging from 0 to 5 m. Therefore, this method features elevated accuracy of building height inversion for various complex shadow scenes, laying a basis for research into the inversion and expansion of urban building heights.

Assessing regional habitat quality holds great significance for maintaining regional biodiversity, enhancing human well-being, and achieving regional sustainable development. Based on the land use data of 2000, 2010, and 2020, this study analyzed the spatiotemporal characteristics of the habitat quality in the ecological green integrated demonstration area in the Yangtze River Delta using the InVEST model and the habitat quality index method. Furthermore, this study explored the relationship between regional habitat quality and land use. Key findings are as follows: ① From 2000 to 2020, the study area exhibited moderate habitat quality, with the habitat quality index trending downward and the habitat degradation gradually mitigating. Regarding the districts and counties in this area, Qingpu District of Shanghai, Wujiang District of Suzhou, Jiangsu, and Jiashan County of Jiaxing, Zhejiang (the two districts and one county) showed a downward trend in the habitat quality from 2000 to 2010. In contrast, from 2010 to 2020, Qingpu District and Jiashan County exhibited improved habitat quality, while Wujiang District still maintained a downward trend in the habitat quality; ② From 2000 to 2020, the study area primarily featured moderate habitat, with major land types including cultivated land and grassland. During this period, the water and wetland areas in the north and center, respectively exhibited the highest habitat quality, while the construction land in the study area displayed poor and inferior habitat; ③ There is a strong correlation between the habitat quality and land use structure in the study area. Specifically, areas with more intense changes in land use feature more significant variations in habitat quality. The results of this study will provide a reference for biodiversity conservation and land use management in the study area.

Due to the intricate geographical and geological environment, the mountainous-hilly area of Changli in northern Hunan Province is challenged by numerous, widespread, scattered, and frequent landslide hazards, which constitute the most significant geologic hazard that causes casualties and economic losses. The multi-source remote sensing technology integrating InSAR, optical remote sensing, LiDAR, and GIS is currently a high-feasibility and high-precision landslide hazard identification and monitoring technology, meeting the requirements for macroscale and timeliness. This study identified and extracted landslide hazards in the Changli area based on InSAR deformation rate data, multispectral images, and DEM data. First, two decision tree classification methods were employed to classify the land use types based on multispectral images, facilitating the observation of land use types and their distributions in the Changli area. Then, five topographic factors, including elevation, slope, aspect, undulation, and curvature, were extracted from DEM data to evaluate the landslide risk in the Changli area. Then, five topographic factors, such as elevation, slope, aspect, undulation and curvature, are extracted from DEM data to evaluate the landslide risk in the study area. Furthermore, the time-series surface microdeformation of the Changli area was measured based on SBAS-InSAR technology. Finally, landslide hazards were extracted and delineated in the GIS by combining risk assessment results and deformation rates. Additionally, based on the classification and regression tree (CART) results and the river system distribution in the Changli area, risk inference was conducted on zones with deformation rates exceeding -0.01 m/a except the delineated landslide hazard sites. This study identified several small-scale landslide hazards with high concealment in vegetation-covered and bare zones, delineating their spatial distribution ranges, which covered an area of 0.126 km². The multi-source remote sensing technology proved effective, demonstrating certain practical application value.

In the change detection for high-resolution remote sensing images, non-subsampled contourlet transform (NSCT) and change vector analysis (CVA) cannot ensure high detection accuracies under single thresholds due to significantly different changes in surface features. Hence, under the framework of change vector analysis in posterior probability space (CVAPS), this study proposed a NSCT-based change detection method combining fuzzy C-means (FCM) clustering and a simple Bayesian network (SBN): the FCM-SBN-CVAPS-NSCT method. First, the proposed method coupled FCM with an SBN to generate a change intensity map in posterior probability space. Then, the change intensity map was decomposed into submaps of different scales and directions through NSCT. The reconstructed change intensity map was optimized by preserving the details and eliminating noise in the high-frequency submaps. Finally, the multi-scale and multi-directional change detection in posterior probability space was achieved, enhancing the change detection accuracy. As indicated by the experimental results, the Kappa values obtained by the proposed method for three study areas were 0.100 9, 0.056 6, and 0.067 4 higher than those derived from the FCM-SBN-CVAPS method, demonstrating certain superiority.

High-resolution remote sensing technology can greatly enhance the efficiency of investigations into active faults due to its high ability to identify the fine structures of microlandforms. This study presents a systematic summary of the symbols of remote sensing images for active faults. By comprehensively utilizing data from the Landsat8 and GF-2 satellites, as well as previous results and field geological surveys, this study analyzed and examined the active faults in the Maoyaba area of western Sichuan Province through the interpretation of remote sensing images of both macro- and microlandforms. The results show that, besides the Yidun-Litang fault zone, several nearly-W-E-trending normal active faults occur in the study area. Based on this finding, as well as the analysis of the regional geological setting, it can be concluded that crustal materials along the southeastern margin of the Qinghai-Tibet Plateau were continuously squeezed out laterally under the background of the intense collision and compression between the Indian and Eurasian plates, leading to the formation of two conjugate faults: the dextral Batang strike-slip fault and the sinistral Litang strike-slip fault. The joint control of both faults resulted in the local extension of the study area and the formation of nearly-W-E-trending fault structures, which govern the development and evolution of the Damaoyaba Basin, the Xiaomaoyaba Basin, and the Cuopu Basin in the north.

Identifying granitic pegmatite-type lithium deposits based on remote sensing technology is a significant method for lithium ore prospecting. To enhance the information extraction accuracy of the deep learning-based semantic segmentation method for granitic pegmatites, this study improved the classic U-Net network. A batch normalization module was added to the convolutional layer of the encoder part, with the ReLU activation function replaced by the ReLU6 activation function. Simultaneously, a composite loss function was constructed to improve operational efficiency and reduce the precision loss in the training process. The domestic GF-2 images of a granitic pegmatite-type lithium deposit were employed to create a dataset for experiments. The results show that the improved U-Net model effectively identified the information on granitic pegmatites in the study area covered by GF-2 images. Compared to the original U-Net network, U-Net model based on VGG backbone network, U-Net model based on MobileNetV3 backbone network, and conventional random forest model, the improved U-Net model has its average intersection over union increased by 14.69, 0.95, 5.08, and 35.34 percentage points, respectively. Moreover, its F1-score increased by 18.38, 1.02, 5.7, and 54.59 percentage points, respectively. Hence, the improved U-Net model achieves the high-precision automatic extraction of ore-bearing granitic pegmatite information from remote sensing images in areas with low vegetation coverage.

This study constructed an assessment index system for ecological vulnerability based on the vulnerability scoping diagram (VSD) model. It dynamically assessed the three-phase ecological vulnerability of Kangding City from 2011 to 2019 using the analytic hierarchy process - principal component analysis - entropy weight method (AHP-PCA-EWM). Through the analysis of spatio-temporal variations, spatial correlations, and driving factors, it revealed the spatio-temporal differentiation characteristics and driving mechanism of Kangding’s ecological vulnerability, aiming to provide suggestions for the ecological restoration, conservation, and sustainable development of Kangding. The results of this study are as follows: ① Throughout the study period, Kangding exhibited an overall moderate ecological vulnerability, with increased potentially- and slightly-vulnerable areas and a decreased severely vulnerable area, suggesting a promising ecological evolutionary trend. Moreover, the ecological vulnerability of Kangding manifested spatial distributions characterized by high-high clusters in the western and southeastern portions and low-low clusters in the northeastern and middle portion; ② The spatial distributions of ecological vulnerability in Kangding were subjected to various internal and external factors, with natural driving factors like vegetation cover, biological abundance, soil and water conservation, and meteorology being the dominant ones.

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.

The pansharpening of remote sensing images is a process that extracts the spectral information of multispectral images and the structural information of panchromatic images and then fuse the information to form high-resolution multispectral remote sensing images, which, however, suffer a lack of spectral or structural information. To mitigate this problem, this study proposed a pansharpening algorithm for remote sensing images based on a multi-depth neural network. This algorithm includes a structural protection module and a spectral protection module. The structural protection module extracts the high-frequency information of panchromatic and multispectral images through filtering and then extracts the multi-scale information of the images using a multi-depth neural network. The purpose is to improve the spatial information extraction ability of the model and to reduce the risk of overfitting. The spectral protection module connects the upsampled multispectral images with the structural protection module through a skip connection. To validate the effectiveness of the new algorithm, this study, under consistent experimental conditions, compared the new algorithm with multiple pansharpening algorithms for remote sensing images and assessed these algorithms from the angles of subjective visual effects and objective evaluation. The results indicate that the algorithm proposed in this study can effectively protect the spectral information of multispectral images and the structural information of panchromatic images in solving the lack of structural information in current algorithms for image fusion.

Drought is identified as one type of the most serious natural disasters affecting agricultural production, and developing a comprehensive drought index holds practical significance for the assessment of drought in various districts and counties in Chongqing. By coupling the soil moisture and precipitation Z-index data downscaled using the XGBoost algorithm and using the Copula function, this study developed a gridded comprehensive drought index CSDIM-A on a kilometer scale with the boundaries of various districts and counties of Chongqing as the spatial division criteria and decades of a month as time units. Using this index, this study assessed the spatiotemporal characteristics of drought and performed an experimental demonstration of the index using Chongqing as the study area. The results indicate that the downscaling enhanced the spatial continuity of remote sensing-based products, thus providing support for the subsequent construction of a comprehensive drought index on a kilometer scale. The generalized extreme value distribution and the t location-scale distribution applied to the fitting of the data distributions of soil moisture and precipitation in most districts and counties of Chongqing, respectively, while the Frank-copula function suited for the fitting of the joint distribution of binary variables on a scale of a month decade. As validated based on soil moisture content, CSDI_M-A can more effectively reflect drought than the precipitation Z-index, with its spatial distribution in various districts and counties consistent with the actual drought data. This indicates that the CSDI_M-A can be used as a reference for drought assessment.

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.

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.

Constructing ecological security patterns in territorial space can constrain and guide urban spatial development for coordinated and sustainable development of cities and regional environments. Based on the remote sensing ecological index and the minimum cumulative resistance model, this study identified the ecological security pattern factors for Dongguan City, Guangdong Province, including ecological source area, ecological corridor, ecological pinch point, and ecological barrier. Moreover, this study proposed related optimization recommendations. The results of this study indicate that: ① Dongguan City exhibits a favorable ecological base, contiguous ecological spaces, and evenly distributed ecological corridors that can effectively connect ecological source areas; ② Enhanced waterfront space protection and road greening construction provide effective paths for the flow of ecological elements; ③ Agricultural production and transportation manifest the most significant effects on ecological networks, followed by industrial production and domestic life; ④ Ecological sources, 12-m-wide ecological corridors, and ecological pinch points can be classified as key ecological protection areas, while 200-m-wide ecological corridors and ecological barriers can be categorized into key ecological restoration areas. This study will provide a scientific basis for constructing the ecological security pattern in territorial space for Dongguan.

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.

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.

To explore the feasibility and accuracy of the method of utilizing hyperspectral data to estimate the contents of elements Cd and As for soil quality elevation of cultivated land, this study delves into the extraction of characteristic bands of the spectra of both elements and the modeling of quantitative hyperspectral inversion. The characteristic bands of spectra were extracted using multiple methods derived from the combination of four spectral transformations and two feature selection methods, with the former comprising first-order /second-order differential (FD/SD), reciprocal logarithm (LR), and continuum removal (CR) and the latter consisting of the competitive adaptive reweighted sampling (CARS) method and the Pearson correlation coefficient (PCC) analysis. Based on this, the element content inversion was conducted using the partial least squares regression (PLSR) and the particle swarm optimization optimized random forest regression (PSO-RFR), followed by the verification of inversion accuracy. The results indicate that the FD-CARS-PLSR inversion model exhibited the best prediction effect for both elements, with maximum determination coefficients R² of 0.863 and 0.959 and relative percent differences (RPDs) of 2.799 and 5.119 for Cd and As, respectively. The FD and SD spectral transformations combined with the CARS method can improve the accuracy of the PLSR inversion model. The results of this study can provide a reference for the rapid estimation of the contents of Cd and As in soil.

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.

The continuous advancement of urbanization in China leads to frequently changing urban buildings. Hence, grasping the change information of urban buildings duly and accurately holds critical significance for urban management, investigation of unauthorized construction, and disaster assessment. This study proposed a multi-level building change detection method combined with the digital surface model (DSM) and digital orthophoto map (DOM) generated from unmanned aerial vehicle (UAV) images. The proposed method consists of four steps: ① The dense point cloud and DOM generated from UAV images were pre-processed to generate differential normalized DSM (dnDSM) and extract vegetation zones; ② Candidate change zones were extracted using multi-level height difference thresholds, with vegetation and smaller zones eliminated; ③ The connected component analysis was conducted for lower-level candidate change zones. For connected objects, their higher-level change detection results were used to eliminate false detection results in the lower level; ④ The quantitative relationship between positive and negative height difference values of change objects was statistically analyzed to determine the change types. As demonstrated by experimental results, the proposed method can retain the change information of low-rise buildings detected through the lower height difference thresholds while ensuring correct and complete change information of high-rise buildings.

Surface temperature, a significant parameter of surface energy balance and land surface processes, is closely associated with the changes in surface parameters. With the Yanhe River basin in the Loess Plateau as a study area, this study derived the surface temperatures through inversion using the atmospheric correction method based on the Landsat OLI/TIRS images of 2015, 2018, and 2020. Moreover, by extracting the normalized difference build-up index (NDBI), normalized differential vegetation index (NDVI), and normalized difference moisture index (NDMI), this study analyzed the relationships of surface temperatures with surface parameters and land use types, as well as the spatio-temporal variations of surface temperatures. The results demonstrate that the correlation coefficients between the inverted and verified values of surface temperatures in 2015, 2018, and 2020 were 0.569, 0.675, and 0.632, respectively, all exceeding 0.5, suggesting certain accuracy and feasibility. Concerning the spatio-temporal variations of surface temperatures, the low-, sub-medium-, and sub-high-temperature zones exhibited decreased areas, whereas medium- and high-temperature zones manifested significantly and slightly increased areas, respectively, suggesting that the surface temperatures tended to increase towards medium and high temperatures. In terms of the relationship with land use types, the surface temperatures of underlying surface cover types increased in the order of water area, forest land, grassland, cultivated land, and construction land. The quantitative relationship reveals significant correlations between changes in surface temperatures and surface parameters of the Yanhe River basin. Specifically, the changes in surface temperatures were positively correlated with the NDBI but negatively correlated with the NDVI and the NDMI. From the perspective of geographical environment factors, surface temperatures decreased with increasing altitude. Different slopes exhibited distinct surface temperatures, which were the highest on flat slopes and lower on steeper slopes. Additionally, different slope aspects manifested significantly different surface temperatures, which were significantly higher on sunny slopes compared to shady slopes. The findings of this study will serve as a reference for exploring surface water thermal environments in complex areas.

Pine wilt disease (PWD) is identified as a major disease endangering the forest resources in China. Investigating the deep semantic segmentation network (DSSN)-based unmanned aerial vehicle (UAV) remote sensing identification can improve the identification accuracy of discolored trees infected with PWD and provide technical support for the enhancement and protection of the forest resource quality. Focusing on the pine forest in Laoshan Mountain in Qingdao, this study obtained images of suspected discolored trees through aerial photography using a fixed-wing UAV. To examine four deep semantic segmentation models, namely fully convolutional network (FCN), U-Net, DeepLabV3+, and object context network (OCNet), this study assessed the segmentation accuracies of the four models using recall, precision, IoU, and F1 score. Based on the 2 688 images acquired, 28 800 training samples were obtained through manual labeling and sample amplification. The results indicate that the four models can effectively identify the discolored trees infected with PWD, with no significant false alarms. Furthermore, these deep learning models efficiently distinguished between surface features with similar colors, such as rocks and yellow bare soils. Generally, DeeplabV3+ outperformed the remaining three models, with an IoU of 0.711 and an F1 score of 0.711. In contrast, the FCN model exhibited the lowest segmentation accuracy, with an IoU of 0.699 and an F1 score of 0.812. DeeplabV3+ proved the least time-consuming time for training, requiring merely 27.2 ms per image. Meanwhile, FCN was the least time-consuming in prediction, with only 7.2 ms needed per image. However, this model exhibited the lowest edge segmentation accuracy of discolored trees. Three DeepLabV3+ models constructed using Resnet50, Resnet101, and Resnet152 as front-end feature extraction networks exhibited IoU of 0.711, 0.702, and 0.702 and F1 scores of 0.829, 0.822, and 0.820, respectively. DeepLabV3+ surpassed DeepLabV3 in the identification accuracy of discolored trees, with the letter showing an IoU of 0.701 and an F1 score of 0.812. The train data revealed that DeepLabV3+ exhibited the highest identification accuracy of the discolored trees, while the ResNet feature extraction network produced minor impacts on the identification accuracy. The encoding and decoding structures introduced by DeepLabV3+ can significantly improve the segmentation accuracy of DeepLabV3, yielding more detailed edges. Therefore, DeepLabV3+ is more favorable for the identification of discolored trees infected with PWD.