The development of emerging technologies poses some risks while improving urban construction and human life, thus further causing urban safety problems. Tianjin is a coastal city in China, where the coastal sea level keeps increasing, water cycling is changed by the water supply of the South-to-North Water Diversion Project, and the underground space is subject to development and utilization. These factors, coupled with land subsidence, are all critical for the assessment of emerging risks in Tianjin. This study extracted information on the land subsidence of the southern plain in Tianjin and then predicted the retreat of the natural coastline in Tianjin by combining the sea level rise rate. Accordingly, this study predicted the high-risk factors brought by relative sea level rise in Tianjin using a machine learning method (XGBoost). In addition, this study analyzed the emerging risks caused by the South-to-North Water Diversion Project and the development and utilization of underground space and revealed the response patterns of the water supply and the construction and operation of subways to the urban safety of Tianjin. The study on the emerging risks brought about by the combination of land subsidence and modern human activities will provide a scientific basis for regional disaster prevention and mitigation and improve cities’ ability to resist disasters.

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.

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.

To scientifically evaluate the land suitability of urban functional areas and to accurately assess the intensive urban land use (IULU) in Hohhot City, this study built an indicator system by integrating the industry survey data and the features extracted from remote sensing images. Then, it assessed the urban function zoning and the IULU in Hohhot through quantification and integration based on land. The results show that 93.0% of the functional areas share common multivariate quantitative characteristics, indicating suitable functional orientation and land use. Moreover, this study built a high-precision multivariate regression model using remote sensing factors (i.e., the principal components of images and the proportions of the shadow and vegetation areas) and survey data (i.e., carbon stock, building density, and the land prices of residential and commercial functional areas). Then, the floor area ratio was calculated based on the model, thus achieving the quantitative assessment of the IULU. The results of this study show that the assessment of IULU based on remote sensing images and industry survey data is feasible and has value in popularization and applications.

Since the availability of global runoff data decrease year by year, the inversion algorithms, as substitutes for the river discharge measured at hydrological stations, have become increasingly important. With the continuous development of satellite remote sensing technology, the methods for estimating river discharge have increased in number. This study systematically summarized the remote sensing-based inversion methods for river discharge, as well as the inversion methods for hydraulic remote sensing elements that are closely related to the estimation of river discharge and the progress made in them. Moreover, this study reviewed the methods, principles, and application status of two types of algorithms based on hydrological models and empirical regression equations and summarized the applicable conditions and shortcomings of different methods. Finally, this study predicted the worldwide development trends of the river discharge inversion based on the satellite remote sensing technology, including ① actively developing the advanced data assimilation technology for satellite remote sensing data; ② integrating new sensor products; ③ optimizing and innovating algorithms.

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.

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.

With the trend towards the precise and digital planting management of orchards, apple cultivation relies more heavily on the planting management supporting technologies of orchards. In recent years, continuous breakthroughs made in spatial resolution and revisiting frequency have made remote sensing technology a major supporting technology for the precise planting management of apple orchards. However, there is an absence of reviews of the application status and prospect of this technology in the planting management of orchards. Based on the analysis of primary applications of remote sensing technology in the precise planting management of apple orchards, this study classified the applications into three major categories, namely the surveys of basic orchard information, inversions of orchard parameters, and the planting management support of orchards. Furthermore, this study reviewed the methods and performance of the applications of remote sensing technology in various fields and explored the application potential. Finally, it identified three types of problems with current research and application of remote sensing technology, namely insufficient studies on mechanisms and in some application fields, low-degree integration of multiple technologies, and the lack of large-scale application models. In addition, this study proposed four hot research and application topics in the future, namely models used to simulate the growth mechanisms of apple trees, the integrated support system for the planting management of apple trees, the single-tree monitoring based on satellite data, and the diversified services of remote sensing-based monitoring products.

The remote sensing-based feature extraction of opencast mining areas is a hot topic in research on the monitoring of mining activities. However, there is a lack of systematic reviews and summaries of relevant studies. Therefore, this study first defined the features of an opencast mining area, divided the feature extraction into single- and multi-feature extractions according to feature types, and briefly described the differences between the feature extraction of opencast mining areas and general surface feature extraction and land use classification. Then, this study briefly summarized the sources and data processing platforms of remote sensing images available in relevant studies. Subsequently, this study divided the remote sensing-based methods for the feature extraction of opencast mining areas into three categories, namely visual interpretation, traditional feature-based approach, and deep learning. Then, it summarized the research status of these methods and analyzed their advantages, disadvantages, and applicability. Finally, this study proposed the future research direction of the remote sensing-based feature extraction of opencast mining areas, holding that the future developmental trend is to further promote the intelligent, fine-scale, and robust feature extraction of mining areas by effectively utilizing multi-source and multi-temporal data, networks with a stronger feature extraction capacity, and methods for the optimization of complex scenes. The results of this study can be used as a reference for the study and application of remote sensing-based feature extraction of opencast mining areas.

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.

As an essential branch of surveying and mapping science, underwater topographic surveys are closely related to human operations in oceans and lakes. For underwater topography detection in shallow-water areas, conventional acoustic methods face the hull stranding risk, and passive optical methods have low survey accuracy. The airborne laser sounding is a novel means for bathymetric surveys in shallow-water areas, and its application in offshore areas can fill the gap of underwater topography data in shallow-water areas. This study presents a brief introduction to the composition and principle of the airborne laser sounding system, followed by a description of laser sounding data acquisition. Furthermore, this study highlights the critical processing technologies for airborne laser sounding data, including waveform data processing, error correction, and point cloud data processing. Finally, this study summarizes the technical difficulties and developmental trends of airborne laser sounding.

Acquiring the number of building floors can provide data support and decision-making services for urban safety and disaster hazards. The number is primarily acquired through manual investigation and statistics currently. Furthermore, the automatic inversion of building heights based on remote sensing images suffers from low algorithmic efficiency, incomplete extraction, and a low automation degree. To acquire the number of building floors quickly and extensively, this study designed an identification algorithm based on GF-7 satellite images. First, shadow lines were automatically extracted using the fishing net method based on preprocessing such as principal component analysis. Then, the building height was calculated based on the geometric relationship formed by the shadow, and the building height was then converted into the number of building floors. Finally, the error in the extraction results was corrected through support vector machine regression, aiming to eliminate the influence of the measurement error of the shadow length. With Chaoyang District in Beijing as the study area, this study conducted model training and testing of the identification algorithm. As shown by the experimental results with Zhengzhou City in Henan Province as the verification area, the overall identification accuracy was 90.21%, with an identification error of three floors at most for buildings with 6~50 floors. This study provides novel technical support and application service for automatically acquiring the number of building floors rapidly and extensively based on satellite data.

The continuous monitoring of the dynamic changes in coastlines is crucial to ascertaining the change patterns and evolution characteristics of coastlines. Long-time-series coastline datasets allow for the detailed description of the dynamic changes in coastlines from the spatio-temporal dimensions and further reflect the effects of human activities and natural factors on coastal areas. Therefore, they are conducive to the scientific management and sustainable development of the spatial resources in coastal wetlands. Based on the Google Earth Engine (GEE), this study analyzed the change in the coastline of Hangzhou Bay during 1990—2019 based on long-time-series Landsat TM/ETM+/OLI images. Using the pixel-level modified normalized difference water index (MNDWI) time series reconstruction technology, this study achieved the automatic information extraction of long-time-series coastlines and the analysis of spatio-temporal changes by combining the Otsu algorithm threshold segmentation and the Digital Shoreline Analysis System. The results show that the total coastline length of Hangzhou Bay increased by about 20.69 km during 1990—2019, corresponding to an increase in the land area by about 764.81 km², with an average annual increase rate of 0.35%. In addition, the average end point rate (EPR) and linear regression rate (LRR) of the coastline were 110.07 m/a and 119.06 m/a, respectively. The analysis of the spatio-temporal evolution of the coastline in Hangzhou Bay over 30 years will provide a basis for the sustainable development and comprehensive management of resources along the coastline in Hangzhou Bay.

Myrica rubra is a specialty crop in Zhejiang Province. Its cultivation area in Zhejiang ranks first in China. This study aims to comprehensively investigate and analyze the suitability of Myrica rubra planting in Zhejiang and better serve the Myrica rubra planting by scientifically using modern meteorological observation data. Based on the distributed simulation of climate factors, this study introduced the influencing factors related to soil and terrain and determined the weights of these factors through the analytic hierarchy process (AHP). Then, in combination with the suitability grade indices of various influencing factors, this study divided Zhejiang into regions suitable, fairly suitable, and unsuitable for Myrica rubra planting. The results are as follows: Regions with a suitable climate occupy most of Zhejiang, indicating superior climate resources; Zhejiang Province enjoys excellent soil conditions and roughly varies between regions fairly suitable and suitable for Myrica rubra planting regarding soil conditions; The terrain varies greatly and is a key factor in the suitability of precise Myrica rubra planting. The regions with suitable terrains have altitudes of 250~450 m and slopes of 5°~25°; Except for northern Zhejiang and the boundary between Shaoxing and Ningbo cities, Zhejiang is suitable or fairly suitable for Myrica rubra planting. This study achieved the spatial simulation of meteorological factors, thus providing data support for the development and improvement of the Myrica rubra planting layout in Zhejiang and being of great practical significance for improving the yield and quality of Myrica rubra.

Soil moisture is closely associated with global climate change, the carbon cycle, and the water cycle, as well as agricultural production and ecological conservation and restoration. The detection of soil moisture has shifted from ground survey to remote sensing detection, achieving global- and regional-scale survey and monitoring. Given differences in data spectrum segments, radiative transfer mechanisms, and inversion algorithms, it is necessary to comprehensively analyze the mechanisms, advantages, and limitations of algorithms, with the purpose of laying a foundation for accuracy and algorithm improvement. From the aspects of optical remote sensing, microwave remote sensing, and optic-microwave cooperation, this study systematically analyzed the features and challenges of the following inversion techniques: inversion based on the T_s-VI spatial and T_s-NSSR temporal characteristics of optical remote sensing data, inversion using passive and active microwave data, joint inversion using active and passive microwave data and remote sensing data, and optical-microwave cooperative inversion based on accuracy improvement and spatio-temporal transformation. At present, the joint inversion of soil moisture using multi-source remote sensing data faces the following challenges: ① The data suffer missing and spatio-temporal mismatching; ② Different data sources exhibit varying degrees of surface penetration; ③ The joint inversion model relies on empirical parameters and numerous auxiliary parameters. These challenges can be addressed with the improvement in the satellite monitoring network, the increase in the surface detection depths of data sources, the clarification of the physical mechanisms of joint inversion, and the establishment of spatio-temporal continuous datasets of auxiliary parameters.

This study aims to investigate the application of high-resolution remote sensing images in the supervision of river and lake sand mining in the Dongting Lake area. Based on the aerial and space high-resolution remote sensing images over the past 20 years, as well as human-computer interaction interpretation and field investigation verification, this study summarized the types and meanings of surface elements in river and lake sand mining, established the remote sensing interpretation symbols for river and lake sand mining, and analyzed representative typical cases. The results show that the interpretation symbols of remote sensing images for river and lake sand mining differ from those for onshore mining summarized previously. The river and lake sand mining was carried out using dredges as the mining equipment, sand carriers as the transport equipment, and sand yards and docks as transfer sites. The mining surfaces caused serrated bank lines during sandbar digging. Furthermore, surface cover changed near mining areas, including turbid water and shrinkage of sandbars and shoals. This study analyzed three typical cases, namely the evolution of the Hualong sand yard, the treatment of the Chenglingji wharf, and the illegal sand mining in Piaoweizhou of the eastern Dongting Lake. The analytical results indicate that high-resolution remote sensing can provide technical support for supervising river and lake sand mining.

Urbanization has decreased the area of ecological land and deteriorated ecological environment in Zhanjiang City. Therefore, it is significant to quickly, comprehensively, and accurately monitor the changes the ecological environment quality in this city. Based on the Landsat images in 2000, 2005, 2009, 2015, and 2020, this study constructed the improved remote sensing ecological index (IRSEI) using six indicators, namely greenness (NDVI), humidity (WET), dryness (NDBSI), heatiness (LST), land use (LUI), and population distribution (POP). Using IRSEI, this study quantitatively analyzed the changes in the ecological environment quality in Zhanjiang during 2000—2020. The results are as follows: ① The mean IRSEI values of 2000, 2005, 2009, 2015, and 2020 are 0.18, 0.18, 0.35, 0.42, and 0.38, respectively, showing a first increasing and then decreasing trend. ② According to the difference processing on IRSEIs during 2000—2020, the proportions of ecological environment areas with significant improvement (dominant), improvement, no change, deterioration, and significant deterioration in the study area are 78.95%, 8.70%, 8.01%, 1.35%, and 2.99%, respectively. ③ The IRSEI can effectively reflect the poor urban environment along the coastal zone during 2000—2020, specifically manifested as a low IRSEI value of building land along the coastal zone. The results of this study can provide a theoretical and scientific basis for Zhanjiang’s ecological environment protection.

Daily mean temperatures, as a primary indicator reflecting climatic characteristics, play a decisive role in monitoring urban heat island effects and agroecological environments. However, daily mean temperatures measured at meteorological stations lack spatial representativeness in regional-scale models. By contrast, the inversion results of daily mean temperatures using remote sensing data can better accommodate the large-scale monitoring needs, but with insufficient accuracy and quality. This study presented several common estimation methods for daily mean temperatures using remote sensing data, including multiple linear regression, machine learning, and feature space-based extrapolation. Then, based on the principle and process for estimation of daily mean temperatures using remote sensing data, this study systematically analyzed the effects of uncertainties such as clouds and aerosols and offered corresponding solutions. Finally, this study predicted the development trend of such estimation methods. Additionally, this study posited that image fusion and multi-source data fusion at different transit times can significantly improve the estimation accuracy under cloud interference.

With the rapid socio-economic development and the increasing demand for natural resources in China, the protection of natural reserves is facing increasing difficulties. The remote sensing-based research on monitoring the disturbance and the restoration of mangrove forests through time series analysis is still in its initial stage. Moreover, time series algorithms are highly complex. Based on the LandTrendr time segmentation algorithm of Google Earth Engine (GEE) and the Landsat image time-series data, this study investigated the disturbance to mangrove forests in the Dongzhaigang Mangrove Nature Reserve during 1990—2020. The results are as follows: ① A total of 42.39 hm² of mangrove forests were disturbed during 1990—2020, among which the largest disturbance area of 12.78 hm² occurred in 2014; ② During 1990—2020, minor, moderate, and severe disturbances accounted for 65.39%, 30.78%, and 3.83%, respectively; ③ The overall identification accuracy of the pixels of mangrove forests subject to changes was 89.50%, and the overall detection accuracy of years witnessing disturbance was 88%, with a Kappa coefficient of 0.79. This study analyzed the years and areas of the disturbance to mangrove forests in the Dongzhaigang Mangrove Nature Reserve over 30 years based on LandTrendr. Moreover, this study analyzed the disturbance factors according to the actual situation and concluded that human activities are the main disturbance factor, followed by natural factors, such as diseases, pests, and extreme weather events. This study will provide a scientific basis and a decision reference for the management of the mangrove forest reserve.

Zhejiang Province is both the birthplace of the theory that both the mountain of gold and silver and the lushmountain with lucid waters are required (also known as the Two Mountains theory) and the first ecological province in China. The study on the vegetation ecological quality of Zhejiang can be used as an important reference for the construction of ecological civilization. Based on multi-source remote sensing data and meteorological observation data, this study investigated the spatio-temporal variations of vegetation ecological quality in Zhejiang during 2000—2020, as well as their response to climate factors and human activities. The results show that: ① Both the fractional vegetation cover (FVC) and the net primary production (NPP) in Zhejiang showed an upward trend during 2000—2020, with significantly increased vegetation greenness; ② The vegetation eco-environmental quality in Zhejiang showed a fluctuating upward trend during 2000—2020, with the vegetation ecological quality indices (VEQIs) of mountainous areas significantly higher than those of basin and plain areas; ③ The dominant factor driving the VEQI variations in Zhejiang during 2000—2020 is human activities, while climate factors occupied a dominant position only in some areas of southwestern Zhejiang. This study deepens the understanding of the spatio-temporal variations of vegetation ecological quality in Zhejiang and their driving factors and, thus, is of great significance for the construction of ecological civilization in Zhejiang and even other regions in China.

In the Pearl River Delta (PRD) region, widespread surface water and vegetation are liable to cause interferometric synthetic aperture Radar (InSAR) interference decoherence, and the cloudy, foggy, rainy, and humid climates frequently cause severe atmospheric delay noise in InSAR data. Accordingly, targeting the Longgang District of Shenzhen City in the southeastern PRD, this study generated the connection graph of interference image pairs using the small baseline subset and InSAR (SBAS InSAR) technique based on interference coherence optimization. This study also obtained the surface deformation information of Longgang District from September 2019 to November 2020 based on 35 scenes of Sentinel-1A images. It then compared the surface deformation information with the inversion results obtained using the persistent scatterer InSAR (PS InSAR) technique. Finally, this study deduced the causes of surface deformation. The results are as follows: ① The inversion results of SBAS InSAR and PS InSAR yielded almost the same surface deformation fields. SBAS InSAR exhibited a much higher coherent point density than PS InSAR in the region with high-amplitude deformation. This indicates that the SBAS InSAR based on the optimal interference coherence can yield accurate and reliable inversion results, enjoying more advantages in the inversion for a complete deformation field. ② The primary causes of surface deformation in Longgang District and its surrounding areas include unstable Karst collapse or slope triggered by continuous heavy rainfall, the changes in the underground hydrogeological environment caused by industrial mining and drainage, the subsidence of mining gob induced by underground construction, and static foundation load imposed by new high-rise buildings. The technical route of this study can provide a reference for the automation and engineering application of InSAR in the early identification of geological hazards in the PRD region.

Accurate information about land use/land cover (LULC) can provide significant guidance for regional spatial planning and sustainable development. However, conventional methods for remote sensing image classification are challenging due to complex surface morphologies, diverse surface feature types, and nonlinear features of remote sensing images. Therefore, they fail to fully utilize the rich information in remote sensing images. This study developed a random forest-based classification method for remote sensing images to extract LULC information by integrating indices and principal components. First, the images covering the study area were selected to determine cloud cover and conduct median synthesis of images, obtaining interannual remote sensing images. Then, various calculated indices and the extracted principal components were integrated into the band stacks of remote sensing images. Furthermore, classifiers were constructed using different machine-learning algorithms. Finally, based on a confusion matrix, the classification results were evaluated using overall accuracy and the Kappa coefficient. The experimental results of the Hangzhouwan area show that the decision support based on vegetation, water, building indices, and principal components can improve the classification accuracy, yielding overall accuracy and Kappa coefficient of 91.42% and 0.894 2, respectively, which were higher than those of conventional methods such as random forest, classification and regression tree, and support vector machine. The method for remote sensing image classification proposed in this study, which integrates indices and principal components, can obtain high-accuracy land use classification results by accurately extracting land cover features in remote sensing images. This study will provide method support for fine-scale surface classification.

Monitoring the spatio-temporal dynamic changes in macroalgae aquaculture is crucial to its environmental management. However, few studies have been reported on the comparative monitoring of different macroalgae species. Based on images of the Sentinel-2 satellite and using the normalized difference vegetation index (NDVI) and the support vector machine (SVM), this study monitored the dynamic characteristics of both the Porphyra aquaculture area in the sea area of southern Wendeng District, Weihai City, Shandong Province and the kelp aquaculture area in the sea area of southern Rongcheng City, Weihai City. The results show that: ① The Porphyra aquaculture in Wendeng District was first captured in the satellite images of 2016, which is the same as the first year of Porphyra aquaculture in this city; the extraction method used in this study performed well in extracting the information about both the Porphyra and the kelp aquaculture areas overall, with the overall accuracy of 84% and above; ② During 2017—2021, the Porphyra aquaculture area monitored through remote sensing increased year by year and showed a trend far away from the shore; ③ The Porphyra and kelp aquaculture areas monitored both showed seasonal variations (high in winter and low in summer) of cold-water macroalgae aquaculture, but the minimum and maximum values of the Porphyra aquaculture area appeared 1~2 months earlier than those of the kelp aquaculture area. Compared with statistical yearbooks, satellite remote sensing can provide more accurate spatio-temporal information on macroalgae aquaculture. This study can be used as a reference in terms of monitoring technology and data for the management of macroalgae aquaculture in coastal areas of northern China.

Land subsidence is a common geological disaster in the Beijing-Tianjin-Hebei region. The uneven land subsidence poses a potential threat to the protection of the Great Wall of the Ming Dynasty (the Ming Great Wall), thus causing irreversible losses. This study acquired information about the surface deformation of the Qinhuangdao section of the Ming Great Wall from 53 scenes of the Sentinel-1 data during 2016—2018 using the persistent scatterer interferometric synthetic aperture Radar (PS-InSAR) and the small baseline subsets (SBAS). The accuracy of the monitoring results was determined by the cross-validation of the deformation results obtained using different processing methods based on synthetic aperture Radar (SAR) data, yielding linear correlation with a coefficient of determination R² of 0.81 between the two types of data. Then, this study analyzed the causes of the land subsidence along the Ming Great Wall based on auxiliary data, such as changes in the groundwater level, geological structures, stratigraphic lithology, land use, and the distribution of highways and railways. Finally, the land subsidence of the Ming Great Wall was predicted using the generalized regression neural network (GRNN). The results are as follows: ① The Qinhuangdao section of the Ming Great Wall exhibits varying degrees of deformation, with the severe deformation primarily distributed in the eastern and northeastern regions and a maximum subsidence rate of more than -12 mm/a; ② The land subsidence is slightly related to groundwater exploitation; ③ The land subsidence rate of the Ming Great Wall differ slightly before and after the great wall encounters the fault zone; ④ The areas with severe land subsidence are mainly distributed in the Quaternary Holocene clay layer; ⑤ Traffic road operation has not caused any great impact on the settlement along the Ming Great Wall. The GRNN-based prediction results show that the land subsidence along the Ming Great Wall will gradually increase in the future, and special attention should be paid to some areas. This study will provide technical support for the systematic monitoring and overall protection of the sections of the Ming Great Wall located in mountainous areas.

Consumer-grade unmanned aerial vehicles (UAVs) each have a single camera and high lens distortion. The accuracy of terrain modeling using UAVs is influenced by route design and control surveys. By designing different data collection schemes and Monte Carlo tests, this study investigated the influence of the camera’s tilt angle, flight height, and the number of ground control points (GCPs) on terrain modeling accuracy in three small river basins on the Loess Plateau. The results are as follows: ① Before the processing of UAV photogrammetry data, it is necessary to analyze the quality of GCPs through Monte Carlo tests to eliminate GCP errors. ② The effects of the tilt angles of cameras include: in the case of no available GCPs, tilt photogrammetry with tilt angles of cameras can both improve the overall accuracy of the sampling area and optimize the spatial distribution of errors, with these advantages related to the optimization of the camera distortion model; in the case of available GCPs, the camera tilt angle has minor influence on elevation accuracy but affects the saturation number of GCPs. Compared with vertical photogrammetry, tilt photogrammetry requires slightly more GCPs to achieve the optimal accuracy. ③ The effects of the flight height include: in the case of no available GCPs, tilt photogrammetry can reduce the sensitivity of elevation accuracy to flight height; in the case of available GCPs, flight heights of 60~160 m have no significant influence on elevation accuracy, and the change in flight height does not affect the saturation number of GCPs.

Hyperspectral data, exhibiting technical advantages in the spectral dimension, have been extensively used for accurately identifying surface features, particularly mineral information. Mineral identification relies on hyperspectral reflectance products, necessitating the application of proper atmospheric correction methods to obtain high-precision surface reflectance products that meet application requirements. Hence, three commonly used atmospheric correction models, ATCOR, FLAASH, and QUAC, were utilized to correct the hyperspectral data acquired by the ZY-1 02D satellite. Moreover, a comparative analysis was conducted on their visual effects, spectral analysis of typical surface features, and extraction of mineral information. The results are as follows: ① All three atmospheric correction models can effectively enhance image clarity in terms of visual effects. Specifically, the ATCOR model slightly outperformed the FLAASH and QUAC models; ② The correlation coefficients (R²) between the typical surface feature spectra of the three models and the ASD-measured spectra showed average values exceeding 0.7, suggesting high consistency and accuracy. Especially, the imaging spectra derived from the inversion results of the ATCOR model were more similar to the ASD-measured spectra; ③ The three models yielded relatively consistent results in chlorite identification but divergent results in sericite identification. Comparatively, the FLAASH and QUAC models exhibited high omission rates in surface regions with low sericite content. Overall, all three models can achieve satisfactory atmospheric correction effects, but the ATCOR model is superior to the other two models in mineral identification.

Focusing on Quanjiao County in Chuzhou City, this study determined 90 features, including spectral, traditional vegetation index, red-edge vegetation index, and texture features, from Sentinel-2 satellite data on the GEE platform. This study examined the effects of diverse feature optimization algorithms combined with a random forest classifier on identifying crop planting types in the study area. These algorithms included the random forest-recursive feature elimination (RF_RFE) algorithm, the Relief F algorithm based on Relief expansion, and the correlation-based feature selection (CFS) algorithm. On this basis, this study further analyzed the classification effects of the optimal feature optimization algorithm in various machine learning classification approaches. The study demonstrates that: ① Spectral features proved to be the most crucial for crop identification, followed by red-edge index features, and texture features manifested minimal effects; ② RF_RFE-based remote sensing identification results exhibited the highest accuracy, with overall accuracy of 92% and a Kappa coefficient of 0.89; ③ Under the RF_RFE feature optimization method, the RF’s Kappa coefficient was 0.01 and 0.41 higher than that of the support vector machine (SVM) and the minimum distance classification (MDC), respectively. This indicates that the RF_RFE feature optimization method based on multiple features, combined with the RF algorithm, can effectively enhance the accuracy and efficiency of remote sensing identification of crops.

Tailings ponds are considerable hazard sources with high potential energy. Ascertaining the number and distribution of tailings ponds in a timely manner through rapid identification and monitoring of their spatial extents is critical for the environmental supervision and governance of tailings ponds in China. Due to the lack of pertinence for potential targets, identifying tailings ponds based on solely remote sensing images is prone to produce confusion between tailings ponds and exposed surfaces, resulting in significant errors in practical applications. This study proposed an extraction method for tailings ponds, which integrated enterprise directory, multi-source geographic data (e.g., data from spatial distribution points, digital elevation model (DEM), and road networks), and high-resolution remote sensing images. The application of this method in Gejiu City, Yunnan Province indicates that integrating multi-source geographic data can effectively exclude the interferential areas without tailings ponds, with the precision and recall rates of the extraction results reaching 83.9% and 72.4%, respectively. The method proposed in this study boasts significant application prospects in high-frequency and automated monitoring of tailings ponds nationwide.

The accurate acquisition of land cover/use changes and their types is critical to territorial space planning, ecological environment monitoring, and disaster assessment. However, most current studies on the change detection focus on binary change detection. This study proposed a multi-class change detection method using a multi-task Siamese network of remote sensing images. First, an object-oriented unsupervised change detection method was employed to select areas that were most/least prone to change in the new and old temporal images. These areas were used as samples for the multi-task Siamese network. Subsequently, the multi-task Siamese network model was used to learn and predict the new and old temporal land-use maps and binary change maps. Finally, the final multi-class change detection results were derived from these maps. The multi-task Siamese network was tested based on the images from the Third National Land Survey and corresponding land-use maps. The results demonstrate that the method proposed in this study is applicable to the change detection cases where changed and unchanged samples lack but there are available historical thematic maps.

Coastal zones are the world’s most populated areas, with their ecosystems being strongly influenced by human activities. Tidal flats, shorelines, and aquacultural water bodies are critical elements in monitoring the health of coastal zone ecosystems. However, the dynamic changes in the waterlines between land and sea areas caused by tidal effects make it challenging to detect tidal flats and shorelines using the remote sensing technology. By integrating Landsat4/5/7/8 and Sentinel-2A/B satellite remote sensing images, this study conducted seven phases (1989—2021) of monitoring of tidal flats, shorelines, and aquacultural water bodies along coastal zones in China mainland. By taking advantage of the high frequency of multi-source satellite observations, this study identified tidal flats, shorelines, and aquacultural water bodies by detecting the waterlines at different tidal levels. The results are as follows: ① Seawater of different colors requires different combinations of water body indices. For clear or low-turbidity seawater, this study selected the modified normalized difference water index (mNDWI) and the normalized difference water index (NDWI) to detect the waterlines at high and low tidal levels, respectively. This improved the reliability of tidal flat detection, with the detected tidal flat area being 122% larger than that detected only using the mNDWI. For high-turbidity seawater (in Zhejiang, Jiangsu, and Shanghai), this study selected mNDWI to detect the waterlines at high and low tidal levels, avoiding misidentifying high-turbidity seawater as tidal flats using NDWI. Besides, this study selected NDWI to detect aquacultural water bodies. ② During 1989—2021, coastal zones in China mainland changed significantly, as evidenced by rapidly decreased tidal flats and increased aquacultural water bodies and shorelines. The decreased rate of tidal flats and the increased rates of shorelines and aquacultural water bodies along the coastal zones averaged 46.2%, 34.4%, and 149.3%, respectively. Correspondingly, the tidal flat area decreased by 7 173.2 km², while the the shoreline length and aquacultural water body area increased by 5 320.5 km and 9 046.5 km², respectively. Provinces or cities in northern China suffered more tidal flat losses than those in southern China. Based on the average decrease rate of tidal flats during 1989—2021, tidal flats in Liaoning, Hebei and Tianjin, and Shandong will disappear within 27 a, 10 a, and 22 a, respectively. ③ The area changes between tidal flats and aquacultural water bodies are highly negatively correlated, indicating that the expansion of aquacultural water bodies is a critical driving factor for the decrease in tidal flats.

This study aims to provide a guide for the optimal management of land use and ecological environment in the Bayin River basin or similar areas by revealing the comprehensive evolution characteristics of the ecological environment in the Bayin River basin. Based on the 12 scenes of remote sensing image data from 2005 to 2020, this study quantitatively explored the critical factors influencing the ecological environment in the study area using a geographical detector. By combining the model for integrated valuation of ecosystem services and trade-offs (InVEST), this study established an ecological environment quality assessment model through statistical analysis, overlay analysis, and analytic hierarchy process, revealing the comprehensive evolutionary characteristics of the ecological environment in the basin. The results show that: ① The critical factors influencing the ecological environment quality in the basin included population size, GDP, elevation, and rainfall. The comprehensive assessment value of the ecological environmental quality in the basin increased from 0.455 to 0.533, suggesting an overall upward trend; ② The ecological environmental quality in the basin exhibited significant regional differences. Specifically, 14.9% of the basin manifested degraded ecological environmental quality, primarily distributed in the vicinity of the Bayin River basin and the surrounding area of Delingha City. In contrast, 33.6% displayed improved ecological environmental quality, spreading in areas to the south of lakes in the middle and lower reaches of the Bayin River basin. This study indicates that the future ecological environment protection and planning in the Bayin River basin should focus on the balance between agricultural land and other ecological and construction land during urbanization, thereby achieving coordinated development of economy and ecology through scientific planning of spatial framework.

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.

The one-class classification (OCC) of land use in image interpretation is a hot research topic of remote sensing. Many novel algorithms of OCC were introduced and developed. The maximum entropy model (MaxEnt)-the most promising OCC algorithm as evaluated-is widely used in the OCC study of land use. However, it is unclear about the applicability of these algorithms (including MaxEnt) in multi-class classification (MCC) of land use. Thus, this study established a procedure for MaxEnt-based land-use MCC in remote sensing image interpretation and applied the procedure to the land-use MCC of the Yunyan River basin. The overall classification effect of MaxEnt and the performance of MaxEnt in the prediction of various land were evaluated using overall classification accuracy, Kappa coefficient, sensitivity, and specificity. Moreover, the Kappa coefficient was also used to evaluate the consistency between MaxEnt and random forest (RF), maximum likelihood classification (MLC), and support vector machine (SVM) in the prediction of land use maps. The results are as follows: ① MaxEnt showed the best classification effect, with overall classification accuracy of 84% and a Kappa coefficient of 0.8; ② MaxEnt showed no worst performance in any land type, and even performed the best in some land types; ③ MaxEnt showed high classification consistency with RF and SVM, and the consistency evaluation of the land use maps obtained using the three algorithms yielded Kappa coefficients of greater than 0.6; ④ Compared with the other the three algorithms, MLC yielded a significantly different land use map, with a Kappa coefficient of less than 0.4. This result indicates that MLC is not applicable to the interpretation of land use of the study area. The procedure established in this study only depends on the occurrence probability of land use rather than the threshold selected. As a result, the OCC algorithms represented by MaxEnt have great potential for application to the land-use MCC in remote sensing image interpretation. In addition, the introduction of parallel computing into large-scale land use interpretation will help improve the efficiency of solving MCC problems using MaxEnt.

Conventional processing methods for remote sensing data are inefficient and time-consuming. Using the object-oriented classification method this study extracted the distribution of mangrove forests of 2000, 2010, and 2020 in the Shankou Mangrove Nature Reserve in Guangxi based on the GEE cloud platform and Landsat TM/OLI remote sensing data. Then, this study monitored the spatio-temporal variations in mangrove forests in the study area in combination with the landscape analysis method and revealed their driving factors. The results are as follows: ① During 2000—2020, the mangrove forests in the study area increased by about 63 hm², including a significant increase of about 40 hm² during 2010—2020; ② Compared with other land use types, the mangrove forests showed the most intense conversion with spartina alterniflora areas and mudflats, with 152 hm² of spartina alterniflora areas and mudflats being converted to mangrove forests and 122 hm² of mangrove forests being converted to spartina alterniflora areas over the 20 years; ③ During 2000—2020, the mangrove landscape in the study area showed decreased fragmentation, increased patch aggregation, continuously expanded landscape dominance, and landward migration of the mangrove forest centroid; ④ Among the factors affecting the area of mangrove forests in the nature reserve, the control of invasive vegetation and moderate aquaculture can increase the area of mangrove forests, while climate changes and invasive vegetation had adverse effects on the growth of mangrove forests. The results of this study will provide a method reference and data basis for the conservation and management of mangrove wetlands in Shankou, Guangxi.

Southwestern China suffers frequent geological disasters. The exploitation of mineral resources in southwestern China is highly liable to induce geological disasters and related secondary disasters. This study investigated the remote sensing-based dynamic monitoring technology for coal mine collapse areas in the coal mining concentration areas in Liupanshui City, Guizhou Province. Based on the high-resolution remote sensing images, this study established remote sensing geological interpretation symbols of coal mine collapse areas in the mountainous plateau of southwestern Guizhou and then dynamically monitored the geological disasters in Liupanshui from 2009 to 2018. Moreover, this study analyzed the present geological disasters in the study area. The remote sensing interpretation revealed that geological disasters in the study area were significantly aggravated over the years. Compared with 2009, 2018 witnessed an increase of 167% in the geological disasters, including 40% of new geological disaster areas and 34% of areas with deteriorated geological disasters. According to the geological disaster degrees in the study area, this study identified four geological disaster concentration areas, which were highly consistent with the mining concentration areas in the study area. Based on the remote sensing data, this study analyzed the types of land damaged by geological disasters in mines and investigated possible resulting damage to the people and the ecological environment in the study area. The results show that disasters that severely damaged land caused the largest damage area for forest and cultivated lands, which had a total number of 193 and a total area of about 333.55 hm². There are 360 areas with potential hazards in the study area, covering an area of 506.36 hm². They are dominated by 126 threats to roads, which cover an area of 110.04 hm². The results of this study can provide a reliable data reference and a critical research approach for restoring the local ecological environment and controlling geological disasters in mines. Moreover, based on the characteristics of the study area, this study further analyzed the causes of the geological disasters in mines, explored the geological disaster control schemes, and proposed countermeasures and suggestions.

Conventional information extraction methods for aquacultural ponds frequently yield blurred boundaries and low accuracy due to the effect of different objects with the same spectrum in complex geographical environments of offshore and coastal areas. This study proposed a method for extracting information on coastal aquacultural ponds from remote sensing images based on the U²-Net deep learning model. First, an appropriate band combination method was selected to distinguish aquacultural ponds from other surface features through preprocessing of remote sensing images. Samples were then prepared through visual interpretation. Subsequently, the U²-Net model was trained, and information on coastal aquacultural ponds extracted. Finally, the scopes of aquacultural ponds were determined using the local optimum method. The experimental results show that the method proposed in this study yielded the average overall accuracy of 95.50%, with the average Kappa coefficient, recall, and F-value of 0.91, 91.45%, and 91.01%, respectively. Furthermore, 19 ponds were extracted, with a total area of 9.79 km². The average accuracies of the number and area of aquacultural ponds were 94.06% and 93.18%, respectively. The method proposed in this study allows for quick and accurate mapping of coastal aquacultural ponds, thus providing technical support for marine resource management and sustainable development.

Assessing the landslide susceptibility of highways in precarious mountainous areas can provide crucial information for the geologic route selection of highways. Conventional landslide susceptibility assessment methods ignore the application of surface deformation data and other dynamic data, leading to low-accuracy assessment results. Hence, this study proposed a landslide susceptibility assessment method for mountain highways based on optical and SAR remote sensing images. With the Longwuxia-Gongboxia section of the Yanhuang Highway in Qinghai Province as the study area, this study extracted various static factors of landslides from high-resolution QuickBird satellite images and calculated the initial risk level of landslide susceptibility within the route area using a random forest model. Afterward, this study obtained the surface deformation factors, which directly reflect the dynamic changes of landslides, based on the long-time-series Sentinel-1A images. Finally, this study corrected the initial landslide susceptibility risk level based on the surface deformation factors, generating a landslide susceptibility assessment zoning map. As demonstrated by engineering practice, the method proposed in this study yielded a high-accuracy landslide susceptibility assessment zoning map for the mountain highway by combining data on both static and dynamic factors of landslides, thus providing accurate information for subsequent geologic route selection of the highway.

As an integral component of the urban ecosystem, water bodies hold considerable ecological significance for mitigating the urban heat island effect and the thermal environment of human habitat. With multi-temporal Landsat and SPOT data as experimental data, this study proposed a method for determining surface emissivity for mixed pixels based on the principle behind the construction of the support vector machine (SVM) optimal endmember subset. Then, this study employed the surface emissivity determination method to analyze the coupling relationship of the water bodies and surrounding land of the Bahe River with the surface temperature using a mono-window algorithm. The results are as follows: ① The SVM optimal endmember subset construction method for mixed pixels yielded an error of surface emissivity less than 0.005 (R = 0.832) relative to the MODIS LSE product. This result indicates that the method has high accuracy and thus can be used to extract surface emissivity. ② Over the past 27 years, the land types and local surface temperature patterns on both sides of the Bahe River have changed significantly, with a sharp increase in construction land and a significant warming trend. The effects of land use types surrounding the Bahe River on surface temperature varied in different periods, with construction land, grassland, water bodies, and forest land being the principal land use types affecting the thermal environment on both sides of the Bahe River. The cooling effects of water bodies, forest land, grassland, and cultivated land are in the order of water bodies > forest land > grassland > cultivated land. ③ The effects of land use types on both sides of the Bahe River on local temperatures exhibited spatial differences during the same period. To the east of the Bahe River, the water bodies, forest land, grassland, and cultivated land show significant cooling effects. In contrast, to the west of the river, only water bodies, forest land, and grassland showed significant cooling effects. This study contributes to the proper understanding of the influence of urban rivers on the local thermal environment, providing a scientific reference for mitigating the local thermal environment of urban rivers and their surrounding areas.

The rapid growth of China’s photovoltaic (PV) industry is accompanied by unplanned construction of PV power plants. Ascertaining the regional PV development suitability, power generation potential, and emission reduction effects holds critical significance for the sound development of the PV industry. Based on remote sensing, meteorological, and fundamental geographic data, this study constructed an evaluation index system for PV development suitability. Using this system, it assessed the zones suitable for PV development in the Western Sichuan Plateau and estimated the PV power generation potential and emission reduction effects. The results are as follows: ① The zones suitable for PV development account for 57.43% of the entire plateau, with highly suitable zones covering an area of approximately 2.07×10⁴ km², which are distributed primarily in the southwestern and northwestern portions of the plateau; ② The plateau exhibits significant power generation potential, reaching 17 197.97×10⁸ KWh in highly suitable zones under a full development scenario, which is equivalent to 6.52-fold Sichuan Province’s total electricity consumption in 2019 before the COVID-19 outbreak; ③ Contrasting with conventional thermal power generation, PV power generation in highly suitable zones can achieve annual CO₂ emission reduction of 12.45×10⁸ t, which is about 12.71% of China’s total CO₂ emissions in 2019 and 3.95-fold Sichuan Province’s CO₂ emissions. Moreover, PV power generation can diminish the emissions of coal and conventional pollutants as well as heavy metals. The findings offer a scientific reference and guidance for selecting sites for PV power plants in the Western Sichuan Plateau and promoting the sustainable growth of the PV industry.

As a principal instrument for observing and researching earthquake precursors, a borehole strain meter allows for point-based observation, high-accuracy observation, and the direct observation of shallow crustal stress-strain information. However, it fails to obtain information on spatial continuous deformation and is susceptible to interference by site environments such as pumping. The persistent scatterer interferometric synthetic aperture Radar (PS-InSAR) method can derive spatial continuous deformation fields and time-series deformation, with the cumulative deformation consistent with groundwater level changes. Using the PS-InSAR method, this study analyzed the land subsidence near the Huailai seismic station based on Sentinel-1 images, aiming to counteract surface deformation in the monitoring of borehole strain and to accurately analyze the anomalous information in the observational data. This study also investigated the mechanism of extension anomalies in the 2020—2021 observational data of the borehole strain. The results are as follows: The deformation center in the area near the Huailai seismic station was situated at the pumping well east of Yihebu Village. The time of the regional subsidence and that of the observed borehole strain anomalies were consistent with the pumping time of the pumping wells for heating in Yihebu Village. The extension anomalies in the borehole strain observational data of the Huailai seismic station shared consistent mechanisms with the surface changes caused by the pumping of the nearby pumping wells for heating. Therefore, the extension anomalies of borehole strain at the Huailai seismic station resulted from pumping the pumping wells for heating in Yihebu Village. This study shows that, in areas significantly affected by groundwater pumping, PS-InSAR plays a role of application demonstration in research on the anomaly mechanism through observation using observation instruments for earthquake precursors.

Cloud detection, as a crucial step in preprocessing optical satellite images, plays a significant role in the subsequent application analysis. The increasingly enriched optical satellite remote sensing images pose a challenge in achieving quick cloud detection of numerous multi-source satellite remote sensing images. Given that conventional cloud detection exhibits low accuracy and limited universality, this study proposed a multi-scale feature fusion neural network model, i.e., the multi-source remote sensing cloud detection network (MCDNet). The MCDNet comprises a U-shaped architecture and a lightweight backbone network, and its decoder integrates multi-scale feature fusion and a channel attention mechanism to enhance model performance. The MCDNet model was trained using tens of thousands of globally distributed multi-source satellite images, covering commonly used satellite data like Google and Landsat data and domestic satellite data like GF-1, GF-2, and GF-5 data. Several classic semantic segmentation models were used for comparison with the MCDNet model in the experiment. The experimental results indicate that the MCDNet model exhibited superior performance in cloud detection, achieving detection accuracy of over 90% for all types of satellite data. Additionally, the MCDNet model was tested on the Sentinel data that were not used in training, yielding satisfactory cloud detection effects. This demonstrates the MCDNet model’s robustness and potential for use as a general model for cloud detection of medium- to high-resolution satellite images.

Rocky desertification is the primary eco-environmental problem in Karst mountainous areas in southwestern China. Scientific measures must be formulated to comprehensively promote the prevention and control of rocky desertification. Remote sensing technology, which enjoys the advantages of rapid positioning, wide coverage, and economic efficiency, has become an important technical method for investigating the spatial distribution of regional rocky desertification. Therefore, this study extracted three key indices used to characterize rocky desertification information (i.e., vegetation coverage, bedrock exposure rate, and soil coverage) of the study area using the pixel unmixing method based on GF-5 hyperspectral data and the spectral index method based on Landsat8 multispectral data. The results show that information on vegetation coverage can be accurately extracted from the two types of satellite remote sensing data. However, Landsat8 multispectral data are difficult to distinguish information about exposed bedrocks from that of bare soil due to their band setting and spectral resolution. By contrast, GF-5 hyperspectral data enable the direct and effective extraction of bedrock exposure rate and soil coverage, as well as the accurate identification of mineral components such as calcite and dolomite in exposed bedrocks. The results of this study can provide a scientific and effective technical and theoretical basis for the evaluation, classification, and comprehensive control of rocky desertification.

The Inner Mongolia reach of the Yellow River basin is suffering severe degradation as an ecological barrier at present. Analyzing its landscape pattern and ecological risk is of great significance for promoting the high-quality development of this reach. Based on the land use data of 1980, 2000, and 2020 of the study area, this study analyzed the spatial distribution and spatio-temporal evolution of the ecological risks by calculating the regional landscape pattern index and the ecological risk index. The results show that: ① During 1980—2020, the land in the study area was dominated by grassland, which accounted for more than 50%. In this period, the areas of cultivated land, grassland, water areas, and unused land decreased by 578 km², 1 911 km², 383 km², and 255 km², respectively. By contrast, the areas of forest land and construction land increased by 1 055 km² and 2 072 km², respectively. In terms of land use types, the land in the study area mainly shifted from grassland, cultivated land, and water areas to construction land and forest land. The comprehensive land use intensity during 2000—2020 was 0.85 percentage points higher than that during 1980—2000; ② During 1980—2020, the patch number of all types of land decreased except for water areas and unused land; the degree of landscape fragmentation of all types of land increased except for construction land; the degree of landscape disturbance of all types of land decreased except for forest land; the degree of landscape loss of all types of land did not change significantly except for construction land, for which the degree of landscape loss decreased significantly; ③ The ecological risk value of the Inner Mongolia reach of the Yellow River basin showed a downward trend during 1980—2020. Areas with fairly low and low ecological risks increased by 9 000 km² in total and were primarily concentrated in the northern and central areas in this period. In contrast, areas with high and fairly high ecological risks decreased by 1 350 km² in total and were scattered on the eastern and northern edges.

Surface subsidence caused by the exploitation of mineral resources must be considered during the development and utilization of land and space in mining areas. Furthermore, it serves as a significant indication of underground areas subjected to illicit mining. The exploitation of mineral resources is generally conducted in widespread, uneven, and dispersed areas, making it necessary to quickly and accurately identify and extract the spatial distribution of mining subsidence in large areas. This study determined the multitemporal differential interferometric phase diagram of mining areas using the differential interferometric synthetic aperture Radar (D-InSAR) technique. Furthermore, it trained networks for the intelligent identification of mining subsidence by employing deep-learning FCN-8s, PSPNet, Deeplabv3, and U-Net models. The results show that the U-Net model enjoys a high detection accuracy and a short detection time. To improve the semantic segmentation and extraction accuracy of information about mining subsidence, this study introduced the efficient channel attention (ECA) module into the conventional U-Net model during the training. Compared with the conventional model, the improved U-Net model increased the intersection over union (IOU) corresponding to mining subsidence by 2.54 percentage points.

Economic development is frequently accompanied by the decreased quality and dysfunctional service capacity of the ecological environment. Clarifying the relationship and spatial differences between ecology and economy is a prerequisite for sustainable regional development. Based on the remote sensing images and socio-economic data of the Dongting Lake area in 2000, 2010, and 2020, this study calculated the ecosystem service values using the value equivalent method. Furthermore, it determined the coordination and consistency indices of ecosystem services and economy in 24 districts and counties in the Dongting Lake area. Then, this study comprehensively explored the relationship between ecological services and the economy, as well as their spatial aggregation, proposing targeted optimization measures for coordinating and balancing regional ecological services and economic development. The results are as follows: ① The total ecosystem service value of the Dongting Lake area decreased from 261.541 billion yuan in 2000 to 255.646 billion yuan in 2020. The spatial distribution of ecosystem service values presented a circular layer pattern, with high values occurring in the center, followed by the peripheral mountains, while the lowest values present in adjacent hills and plains. ② As for individual ecological service values, hydrological regulation contributed the most significantly, while the nutrient cycle maintenance contributed slightly. Additionally, the values of ecological services, except for biodiversity and aesthetic landscape, decreased to varying degrees during the study period. Among them, the hydrological regulation presented the most significant reduction in the ecological service values, accounting for more than 70% of the total reduction. ③ Regarding the spatio-temporal variations in the ecological services and economic development, the Dongting Lake area showed relatively stable ecological differences and expanded economic gaps. Districts and counties in the Dongting Lake area showed high coordination degrees but low consistency levels between ecology and economy. The ecological and economic spatial aggregations exhibited significant differences, with dominant ecological aggregation zones mainly distributed within and along Dongting Lake. ④ The critical driving factors in the spatial differences in ecological service values include human disturbance, elevation, slope, temperature, and precipitation. Therefore, to promote the harmonious development of ecology and economy in the Dongting Lake area and weaken the gap between both, it is necessary to propose feasible measures for strictly protecting the natural basement, strengthening human-guided utilization, and promoting the transformation from ecological resources into economic products.

The video synthetic aperture radar (VideoSAR) technology is widely used in military reconnaissance, geological exploration, and disaster prediction, among other fields. Owing to multiple interference factors in SAR videos, such as speckle noise, specular reflection, and overlay effect, moving targets are easily mixed with background or other targets. Therefore, this study proposed an effective VideoSAR target detection and tracking algorithm. Firstly, several features of VideoSAR were extracted to construct multichannel feature maps. Then, deeper features were extracted using the improved lightweight EfficientDet network, thus improving the accuracy of SAR target detection while considering algorithm efficiency. Finally, the trajectory association strategy based on bounding boxes was employed to associate the same target in VideoSAR. The experimental results show that the method proposed in this study is effective for SAR shadow target detection and tracking.

Interferometric synthetic aperture Radar (InSAR) can extract three-dimensional information about a ground target from the phase information in an interferogram. Phase unwrapping is an important step in the InSAR process, and its accuracy dictates the accuracy of the digital elevation model (DEM) or the ground deformation information. To overcome the serious phase decorrelation and phase noise in complex mountainous areas, this study divided the study area according to the quality of interference phases and proposed a quality-guided least squares phase unwrapping algorithm. Then, the algorithm was employed for the phase unwrapping of simulated low-noise interferometric phase data and Sentinel-1A InSAR interferometric images of the Qinling area of China. The results show that the proposed algorithm can effectively improve the phase consistency among high- and low-quality zones and the overall accuracy of phase unwrapping.

In recent years, the research on residents’ carbon emissions has mostly focused on the economic level and direct energy consumption, and less involved in the area of residential areas, and most of the research has relied on traditional surface measured data. In order to improve data accuracy and make more targeted policies, this paper selected China as the research object by taking advantage of the features of strong timeliness, wide coverage and small constraints of remote sensing images, and analyzed the correlation between residential area and residential carbon emissions in China in 2019. After determining the significance of the two, combined with the influencing factor of GDP, a multiple linear regression model was established between residents’ carbon emissions and residential area and GDP. The results show that there is a linear correlation between residents’ carbon emissions and the area of residential areas and GDP. With the development of economic level, the expansion of residential area is the main driving force for the increase of residential carbon emissions, and the driving effect of GDP on the increase of residential carbon emissions has decreased. Therefore, it is necessary to reasonably control the expansion of residential areas while considering economic development, so as to make more refined emission reduction policies and achieve the country's future green and low-carbon goals.

The survey and change monitoring of natural resources can provide an important guarantee for the implementation of systematic policies, protection, and rational utilization of resources and are of great significance for the building of the national land space planning system, the reform of the resource management system, the modernization of space governance capacity, and the construction of national ecological civilization. Western China is characterized by a vast area, insufficient basic land data, and unreliable land change monitoring. Therefore, there is an urgent need to provide efficient and accurate survey results at a low cost for such a large area. Based on the domestic high-resolution satellite (GF-6) images and the results of the third national land survey, this study carried out a demonstration of the application of the intelligent rural land survey to the areas subject to rapid development in western China in Xuyong County. To this end, remote sensing images with high spatial resolution and hyperspectral resolution were obtained through panchromatic and multispectral image fusion. Then, the fused data were used for the basic survey of land resources in Xuyong County. Subsequently, based on the object-oriented image classification and the results of the third national land survey, supervised classification of the remote sensing images was conducted, and areas with changes in land were automatically extracted, thus forming a new efficient land survey model for the areas subject to rapid development in western China. The survey results can provide strong support in terms of basic land information for the rapid development of specialty industries in western China and have a certain value in popularization and applications.

In view of the drastic changes in the ocean-atmosphere environment, the accurate and efficient identification of coral reef substrate information is essential for the dynamic monitoring of coral reefs. Based on the Landsat8 satellite data of the Yongle Atoll in the Xisha Islands of four periods during 2013—2021, this study proposed a decision tree classification model using spectral and texture indices according to the spectral and texture differences between different substrates. Then, the coral information was extracted using object-oriented and pixel-based classification methods. In addition, the changes in the substrate of the Yongle Atoll were quantitatively analyzed. The results are as follows: ① The results of the object-oriented classification are superior to those of pixel-based classification overall. Moreover, the decision tree classification results yielded Kappa coefficients of 0.63~0.68, with classification accuracy about 7~10 percentage points higher than that of conventional supervised classification; ② Coral thickets are mostly distributed in the central, weakly-hydrodynamic parts of islands and reefs. The corals in the Yinyu Reef and the Jinyin Island exhibit a planar distribution pattern, while those in other islands and reefs mostly show a zonal distribution pattern; ③ The areas of coral thickets and sandbanks in the Yongle Atoll changed significantly overall. Although the total area of coral thickets increased by 1.689 km², the coral thickets in the Shiyu, Jinqing, Quanfu, and Shanhu islands and the Lingyang reef were severely degraded, with areas decreasing by 0.107~0.892 km². This study verified that the substrate index established using medium spatial resolution images is reliable and can be applied to remote sensing information extraction of corals. Therefore, this study will provide technical support for the investigation and scientific management of coral reef resources.