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.

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.

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.

Nearshore monitoring covers natural environments and human activities. High-accuracy identification of nearshore monitoring targets significantly influences the healthy development of the marine economy, the ecological protection of marine environments, and the prevention and mitigation of marine disasters. The nearshore monitoring targets feature multiple types, diverse sizes, and uncertainty. The existing identification models suffer low accuracy, low efficiency, and severe omission of small targets. This study proposed an identification model (Re-YOLOX) for nearshore monitoring targets by improving YOLOX using a learnable image resizer model (the Resizer model). First, the model training was intensified using the Resizer model to improve the feature learning and expression abilities and the recall rate of the Re-YOLOX model. Then, the feature pyramid fusion structure of the YOLOX algorithm was improved to reduce the omission of small targets in the identification. With the nearshore video data from UAV monitoring as the data set and cars, ships, and piles as monitoring targets, this study compared the Re-YOLOX model with other models, including CenterNet, Faster R-CNN, YOLOv3, and YOLOX. The results show that the Re-YOLOX model yielded a mean average precision of 94.23%, a mean recall of 91.99%, and a mean F1 score of 89.67%, all of which were higher than those of the other models. In summary, the Re-YOLOX model can improve the target identification accuracy while ensuring target identification efficiency, thus providing technical support for managing nearshore seas.

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 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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

Landscape indices are quantitative indices used to reflect the composition and spatial configuration of a landscape ecological structure. Current landscape index systems are generally constructed based on the characterization of 2D spatial characteristics, thus their evaluation results fail to accurately reflect the pattern and composition of a real 3D landscape system. Accordingly, there is an urgent need to develop an index system used to describe the 3D landscape characteristics of islands and a whole-process evaluation method. With Tianheng Island in Shandong Province as a case study and based on the point clouds of unmanned aerial vehicle (UAV) tilt photogrammetry, as well as the classification and processing of point clouds using the deep learning method, this study constructed six basic 3D landscape indices covering type and landscape scales to quantitatively describe the 3D landscape features of the island. Moreover, this study established the building landscape indices to evaluate the impacts of the construction activities of human beings on the island ecosystem. The results are as follows: ① As revealed by the analysis of basic 3D landscape indices, the buildings on Tianheng Island are characterized by small 3D volumes and dense spatial distribution. Furthermore, tall vegetation exhibits high isolation, regularity, and spatial aggregation, while low vegetation exhibits high diversity, compactness, and connectivity; ② Due to the difference in dimension, 3D landscape indices contain more spatial information than 2D landscape indices and are greatly affected by terrain undulation; ③ In the case of the same landscape type, the landscape shape index (TLSI) is more sensitive to the change in height (sensitivity index: 7.480). In the case of the same landscape index, the building type changes more greatly than vegetation with irregular spatial characteristics (sensitivity index: 5.861) and is influenced by the design characteristics of buildings; ④ Tianheng Island has a 3D building index (TBI) of 0.523, which increases with an increase in the density and complexity of buildings. Compared with building density and spatial congestion indices, TBI can better reflect the influence of artificial structures on the 3D landscape pattern of the island. This study aims to provide methodological support and a case study for the construction of 3D landscape indices based on modern surveying and mapping technology, as well as the planning of 3D spatial landscapes and the development of their management and evaluation system.

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.

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.

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.

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.

Evaluating the remediation effect of heavy metal pollution in mines properly and rapidly holds considerable significance for ecological restoration and rehabilitation of mines. Based on the field-measured vegetation spectra, this study analyzed the typical spectral features of the main vegetation in the Dexing copper mining area. According to the heavy metal content in the leaves of vegetation tested in the laboratory, this study analyzed the relationship between heavy metal content and red edge position-a spectral characteristic parameter. This study calculated the red edge position of the vegetation in 2003 and 2009 using 2-scene Hyperion hyperspectral data, inferring the heavy metal enrichment in the vegetation of the mining area. Furthermore, this study evaluated the remediation effect of heavy metal pollution in the mining area. The results show that satisfactory results have been achieved from the remediation of heavy metal pollution around mine tailings nos. 1 and 2 in typical reclamation areas. Compared with 2003, 2009 witnessed generally satisfactory remediation effects of heavy metal pollution, with most areas being remedied and some newly polluted areas requiring remediation. The method proposed in this study can achieve a quick and reasonable evaluation of the remediation effect of large-scale heavy metal pollution in mining areas.

The Five-hundred-meter Aperture Spherical radio Telescope (FAST), also known as Tianyan (meaning the Eye of the Sky), has attracted worldwide attention and is the largest single-dish radio telescope in the world. The joint observations of FAST and several more FAST-type radio telescopes allow detection sensitivity and resolution to be further improved and the research fields to be expanded. Therefore, Chinese radio astronomy scientists have the expectation of building more FAST-type radio telescopes in China, which should be achieved based on the preceding research on depressions as the sites of FAST-type radio telescopes. Presently, the shared digital elevation model (DEM) data enjoy intercontinental coverage and different ground resolutions. The development of computer processing technology has greatly enhanced the processing and analysis capacities of DEM data and continuously innovated the processing technologies. Moreover, relevant analyses and expressions can be simulated. Therefore, based on a comparative analysis of the structural scales of the projects of the Arecibo radio telescope and the FAST, as well as the morphological characteristics of karst depressions, this study proposed the conditions of ideal depressions as the sites of FAST-type radio telescopes. Moreover, by analyzing the resolution and data quality of shared DEM data on the Internet, it is concluded that areas with ASTER_GDEMV3 data with a resolution of 30 m are suitable as sites of large radio telescopes in provincial-level regions. In search of large-scale depressions in Guizhou Province, this study developed special modules for quantitative analyses, such as extracting the characteristic parameters of depressions and the fitting of filling, excavation, and superimposed sections, based on the ArcGIS platform and summarized the key steps to organize and apply the major tools of ArcGIS in the special modules. The results of this study determined key technology in search of large Karst depressions in provincial-level regions. Furthermore, this study proposed several issues that are noteworthy in the application.

The western Sichuan Plateau, with a fragile and sensitive ecological environment, acts as a critical ecological barrier between the Qinghai-Tibet Plateau and the Sichuan Basin. Research on the dynamic changes in the normalized difference vegetation index (NDVI) and their driving factors holds practical significance for monitoring the ecological environment quality of the western Sichuan Plateau. Based on 2001—2021 MODIS NDVI data, as well as meteorological data, surface factor data, and human activity data, this study analyzed the NDVI distribution of vegetation in the western Sichuan Plateau on a spatio-temporal scale using trend analysis, Hurst index, and geographical detector. Furthermore, this study determined the principal driving factors in NDVI changes. The results are as follows: During 2001—2021, the NDVI of 67.19% of regional vegetation in the western Sichuan Plateau showed a fluctuating upward trend. Elevation is the most critical factor influencing NDVIs, with an explanatory power of 0.529. The elevation is followed by accumulated temperature ≥0 ℃ and air temperature. The driving factors in interactions among NDVI exhibited nonlinear or double-factor enhancement, with q values between relative humidity and elevation being highest (0.623). 84% of factor combinations showed significantly different effects on the spatial NDVI distribution in the western Sichuan Plateau. The results of this study facilitate the research on the driving mechanism of vegetation growth, providing a reference for vegetation protection in the western Sichuan Plateau.

There are only a few low-accuracy methods available for the feature extraction of sparse woods from remote sensing images. Moreover, there is a lack of datasets for intelligent identification. This study proposed a method for intelligent information identification of sparse woods from remote sensing images. First, a dataset was created using QGIS and Python separately to provide data support for model training. Then, feature maps were generated through feature extraction, and then regions of interest (ROIs) were extracted from the feature maps. Subsequently, these ROIs were filtered through pooling operations (ROI align) to reduce the memory consumption caused by too many ROIs in the images. Experiments show that the method proposed in this study can create datasets quickly and facilitate the identification of sparse woods from remote sensing images. Moreover, the Mask R-CNN-based intelligent identification has a target detection mean average precision (MAP) of up to 0.92.

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.

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.

Spatio-temporal fusion can generate image sequences with sufficiently high temporal and spatial resolution. However, current studies tend to improve prediction accuracy using as much spatio-temporal data as possible and complex non-linear models, while few of them focus on analyzing images themselves by making full use of their intrinsic features, such as trends and textures. This study proposed a 2DSSA spatio-temporal fusion model (2DSSA-STFM) based on 2D singular spectrum analysis (2DSSA). In this model, the major spatial trends and details of the existing images at the target moment can be predicted by decomposing the images into trend and detail components. Firstly, the linear relationship between the trend of high-spatial-resolution data and low-spatial-resolution data was built to calculate the trend components of the images at the target moment. Then, the linear relationship between the low-resolution and the high-resolution detail components in two time phases was established to determine the detail components of the images at the target moment. Finally, the calculated trend and detail components were combined to form the target prediction images. The 2DSSA-STFM was applied to two sets of medium-resolution Landsat7 ETM+ and MODIS images, yielding smaller experimental errors than conventional spatio-temporal fusion models.

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.

Hyperspectral images are characterized by large data volumes, multiple bands, and strong interband correlation. Conventional classification methods using hyperspectral images usually consider only spectral or spatial information, while suffering insufficient feature extraction and ignoring the texture structures and important spectral information of images. Aiming at these problems, this study proposed a new classification method using hyperspectral images. First, multi-scale spatial-spectral data were processed based on the three-dimensional convolutional neural network (3D CNN), and a spectral attention mechanism was proposed by improving the dual attention mechanism. Then, the classification accuracy of surface features was further improved by adopting cross-layer feature fusion and multi-channel feature extraction strategies. In this study, 6 043 samples of two scenes of images captured by the GF-5 satellite were selected as experimental data. The proposed method was compared with five other methods, namely the support vector machine (SVM), the one-dimensional convolutional neural network (1D CNN), the two-dimensional convolutional neural network (2D CNN), the 3D CNN, and the residual network (ResNet). The results show that the method proposed in this study yielded significantly improved overall accuracy (OA) and Kappa coefficients with averages of 95.25% and 0.943, respectively. When applied to the dataset of Nantong, Jiangsu, this method yielded OA of up to 95.84%, which was 21.54, 21.71, 7.28, 3.94, and 2.56 percentage points higher than that of the five other methods, respectively.

The emergence of geographic big data provides a new data source for the study of urban spatial structures. Identifying the polycentric urban structure based on geographic big data is currently a hot research topic in academic communities. This study proposed a method for identifying the polycentric urban structure based on multi-source geographic big data. First, the spatial units in the study area were determined using a region segmentation algorithm based on drainage divides. Then, the urban centers and subcenters were identified using the two-stage algorithm for urban center identification. Finally, the identification results were compared and verified. The results of this study are as follows: ① The region segmentation algorithm based on drainage divides can effectively identify the spatial features of nighttime light data, and the basic spatial units acquired using this algorithm can be used to identify urban spatial structures; ② The urban centers identified based on the Weibo (MicroBlog) check-in data, which can effectively reflect urban human activities, and the two-stage algorithm for urban center identification are roughly consistent with those set in the urban planning. Therefore, the method proposed in this study is of great significance for expanding the application scope of geographic big data and enriching the existing research methods for urban spatial structures.

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.

Resources serve as the material guarantee of the existence and development of human society. However, as a basis for resource discovery, geological exploration tends to damage the ecological environment. With the official release of the Specification for Green Geological Survey and Mineral Exploration (DZ/T 0374—2021) in June 2021, green geological exploration has been officially promoted to the national level and was implemented nationwide in China. However, the supervision of green geological exploration faces many difficulties and challenges in practice. To meet the demands of responsible entities for the supervision, inspection, and management of green geological exploration projects, this study proposed a high-efficiency supervision method based on remote sensing. By applying this method to a polymetallic survey project in Qinghai Province, this study expounded the specific implementation process of the method, as well as its effectiveness in the supervision services for geological exploration projects. As indicated by the results, the method proposed in this study allows for ascertaining the basic external environment of the project area, following the project layout and implementation, and verifying the consistency with the project plan. In addition, through quantitative information investigation, this method allows for the full identification of the disturbance and damage to the ecological environment and its restoration during the project implementation. Therefore, this study can provide effective technical support and basic data for evaluating the performance of green geological exploration.

Many unplanned natural roads, which are also known as temporary roads or unpaved roads, exist in the vast arid and semi-arid regions of the Mongolian Plateau. These natural roads, which were formed due to the arbitrary running of vehicles, will influence the surface ecology and its stability and aggravate land degradation in arid and semi-arid regions. They have a large quantity, are distributed irregularly, and tend to change with regional development. Therefore, there is an urgent need for the efficient and accurate information acquisition of natural roads in large-scale grassland regions, which is a challenge. Based on domestic high-resolution satellite (GF-1) images, this study extracted information on the natural roads in Mongolia using the object-oriented method. First, the data of GF-1 images covering the study area were preprocessed, and the image objects were segmented using the multiresolution segmentation method. Then, the characteristics of the natural roads were analyzed for information extraction. By calculating the parameters of spectral and geometric features and randomly selecting road samples to statistically analyze the characteristic values of samples, the parameters that could characterize the natural roads were selected to construct a set of rules for information extraction of roads. Finally, information on roads was extracted and optimized by combining multiple methods for classification, among which the nearest neighbor classification method was used for preliminary extraction while other classification algorithms such as threshold classification were used for optimization. Consequently, natural roads with a length of 3 708.745 km were extracted in the study area, with a density of 0.129 km/km². This result shows that the natural roads in the study area are densely distributed in the southeast and sparsely distributed in the north and west overall. These distribution characteristics are consistent with the actual production of coal mine enterprises and the living of local residents in the study area. Therefore, the method proposed in this study can extract almost complete information about natural roads in the study area and thus can be used as a reference for the information extraction of natural roads in vast arid and semi-arid regions of the Mongolian Plateau.

Based on the long-time-series (1982—2015) GIMMS NDVI3g and CRU Ts datasets of precipitation, temperature, and potential evapotranspiration (PET) of Asia, this study identified the spatio-temporal variations in the vegetation coverage and climatic elements in Asia in the past 34 years using the maximum-value composite procedure, Mann-Kendall trend tests, and correlation analysis. Furthermore, this study analyzed the response of vegetation coverage to climate changes and explored the influence mechanisms of climate changes on the dynamic changes of vegetation. The results show that the vegetation in Asia during 1982—2015 is as follows: ① the vegetation coverage was high (NDVI > 0.5) in Southeast Asia, Japan, India, and the southern coasts of China but low in most parts of central Asia; ② the NDVI in Asia showed an upward trend at an increasing rate of 0.000 7/a. Moreover, the vegetation coverage exhibited a significant seasonal increase, with spring contributing the most to the interannual NDVI; ③ The PET in Asia was high in the west but low in the east. For example, the PET was high (> 40 mm) in arid and semi-arid Central Asia and Western Asia; ④ The temperature in Asia was high in the south and low in the north. For example, in China, the temperature was higher than 15 ℃ in the south and lower than 15 ℃ in the north. Rainfall exhibited a similar but more significant spatial distribution compared to the temperature; ⑤ The temperature, rainfall, and PET showed regional effects on NDVI. For example, rainfall and PET served as the main factors influencing NDVI in northern Asia, while the temperature was the main factor influencing NDVI in central and southern Asia; ⑥ The effects of climate changes on NDVI were significant in spring and especially summer but were nonsignificant in autumn and winter; ⑦ The effects of climate changes on NDVI showed a significant time lag of one month.

Featuring many mountains and few flatlands, Guizhou Province has scarce cultivated land resources. Consequently, dam areas become a main carrier for developing high-quality modern agriculture and increasing farmers’ income in Guizhou. The information extraction and characteristic research of dam areas can provide a scientific reference for the adjustment of the agricultural industrial structure and the sustainable utilization of land resources in Guizhou. With the domestic high-resolution satellite images of 2020 with a resolution of 2 m as the main data source, this study extracted, verified, and analyzed the remote sensing images of the dam areas with an area over 500 mu (33.33 hm²) using the global navigation satellite system (GNSS), the geographical information system (GIS), and remote sensing (RS). The remote sensing monitoring results are as follows: ① Guizhou has about 1 749 dam areas with an area of over 33.33 hm² each, covering a total area of about 337 080.14 hm², which account for 9.71% of the cultivated land; ② The dam areas with an area of 33.33~66.67 hm² and 66.67~100 hm² each account for the highest two proportions and account for 46.65% in total; ③ The dam areas mostly have small areas, with 32.05% on a scale of 10 000 mu (666.67 hm²). Moreover, there is not a proportional relationship between the number of dam areas and their area. The dam areas with an area of over 33.33 hm² each are mainly distributed in the central region along the northeastern-southwestern area in Guizhou, with Qiannan Buyi and Miao Autonomous Prefecture, Zunyi City, and Anshun City ranking the top three in terms of area. The dam areas are dominated by those at altitudes of 1 000~1 500 m, which account for 46.68%. In addition, the dam areas are largely distributed in hilly and mountainous areas, with a few of them spreading in basins and platforms.

Based on the technical research task of “one survey for multiple purposes” in the national pilot project of integrated survey and monitoring of natural resources, this study aims to connect multiple special surveys of natural resources and multisectoral purposes through one integrated survey. First, this study analyzed the existing land classification and the Guidelines for the Classification of Land and Sea Use for Land and Space Survey, Planning, and Use Control (trial). Then, it formulated the criteria for the classification of “one survey for multiple purposes” for the integrated survey and monitoring of natural resources by subdividing some land categories according to the Land Use Classification. Moreover, the verification results show that the criteria for the classification enable the mutual conversion of classifications, such as land and sea use classification and land survey classification, and can connect to special surveys by rapidly providing special resource survey layers.

Digging ponds to raise crabs is a non-grain behavior of cultivated land, endangering national food security. However, the intelligent interpretation of remote sensing images targeting this behavior faces challenges such as laborious manual interpretation and low verification efficiency. Based on a cooperative interpretation mechanism, this study proposed an intelligent method for detecting crab ponds using remote sensing images. This method, integrating the HRNet segmentation network and the Swin-Transformer classification network models and combining manual verification, improved the detection accuracy and work efficiency. The application results of this method to Gaochun District, Nanjing City, Jiangsu Province show that the method for intelligent detection can automatically determine 83.4% of the spots for detection, with final identification accuracy of 0.972. The method proposed in this study can significantly reduce the identification difficulty and manual verification workload while improving the detection accuracy. Therefore, this study will provide a reliable solution for the accurate and efficient detection of non-grain surface features such as crab ponds.

Hydro-fluctuation belts are frequently struck by geological disasters. Therefore, ascertaining the effects of hydrological factors such as reservoir water level and rainfall on the surface deformation of these belts is of great significance for the early warning, prevention, and control of geological disasters. Based on 63 scenes of Sentinel-1 ascending images of the Fengjie section of the Three Gorges Reservoir Area from July 2018 to July 2020, this study conducted the inversion of surface deformation using the small baseline subset interferometric synthetic aperture Radar (SBAS-InSAR) technique. The inversion results were compared with the data of ground monitoring points, and the hydrological elements were analyzed using the time series diagrams of deformation, reservoir water level, and monthly rainfall. The conclusions are as follows: ① The change in the reservoir water level and rainfall are important factors causing surface deformation. The effects of the change in the reservoir water level on the slope are primarily reflected in the buoyancy effect and the water level difference inside and outside the slope. In comparison, rainfall can decrease the shear strength and increase the dead weight of the slope, thus further increasing the deformations; ② Quicker change in the reservoir water level corresponds to larger surface deformation, and vice versa; ③ Rainfall is directly proportional to surface deformation and totally dominates the surface deformation in the case of extremely heavy precipitation; ④ The surface of the study area is stable overall. However, two deformation anomaly zones have been found near the hydro-fluctuation belt. They have annual deformation rates of over 30 mm/a, with a maximum of up to 89 mm/a within the anomaly zones. The above conclusions have high theoretical and practical values and can provide scientific support for the accurate prevention and control of geological disasters in hydro-fluctuation belts.

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.

Soil moisture is the core of water conversion and circulation that connects the atmosphere, surface, soil, and subsurface. As a basic climate variable of the global climate observing system, soil moisture plays a vital role in regional-scale water and energy exchange. The estimation of root zone soil moisture (RZSM) and the analysis of its spatio-temporal variations are of great significance for crop yield assessment, flood and drought prediction, and soil and water conservation. Based on the artificial neural network (ANN), this study estimated the daily RZSM in the Western Liaohe River basin during 2019—2020 with remote sensing image-based surface soil moisture, cumulative precipitation, cumulative daily maximum and minimum temperatures, relative humidity, sunshine duration, cloud coverage, wind speed, soil attributes, normalized difference vegetation index, and actual evapotranspiration as explanatory variables, the in-situ measured RZSM as the target variable, and the 2013—2018 data used for model training. The estimated results show that the average RMSE and average R between the RZSM estimated based on ANN and the in-situ measured RZSM were 0.056 7 m³/m³ and 0.611 7, respectively. Therefore, the ANN can effectively estimate the RZSM in the Western Liaohe River basin. In addition, this study shows that the variation in the soil moisture is closely related to precipitation.

This study constructed a monthly soil moisture content dataset of Henan Province during 1948—2021 by combining 1948—2014 GLDAS_2.0 data and 2000—2021 GLDAS_2.1 data. Through the Mann-Kendall (M-K) trend analysis, mutation test, wavelet analysis, and cross-correlation analysis, this study revealed the spatio-temporal distribution and critical influencing factors of soil moisture content in Henan Province. The results show that compared with the monthly soil moisture content data provided by GLDAS_2.1, the reconstructed monthly soil moisture content data during 2000—2014 showed an average deviation, average absolute error, and root mean square error of 2.09 mm, 13.01 mm, and 18.26 mm, respectively, indicating reliable data. According to the constructed soil moisture content data, the soil moisture content decreased at a rate of 0.301 0 mm/a during 1948—2021, with change rates of -0.236 8 mm/a in spring, -0.085 5 mm/a in summer, -0.380 5 mm/a in autumn, and -0.240 3 mm/a in winter in Henan Province. Spatially, the soil moisture content decreased from south to north, highly consistent with precipitation and evapotranspiration. The soil moisture content was 2.63 mm/cm in the vertical direction. The wavelet and cross-correlation analyses show that precipitation is a critical factor influencing soil moisture content. This study revealed the long-time-series spatio-temporal distribution of soil moisture content in Henan Province, providing a basis for the scientific management of surface water resources in Henan Province.

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.

By introducing cultural, educational, and scientific research indices and optimizing gas regulation indices, this study proposed an index system to assess the gross ecosystem product (GEP) of natural resources in Hunan Province based on the existing theories and methods for ecosystem service. This study then built a grid-based GEP model with a grid scale of 30 m × 30 m to analyze the spatio-temporal evolution of the GEP of Hunan in 2000, 2010, and 2020. The results are as follows: ① In the temporal dimension, the GEP of the province increased by 3.34×10⁴ billion yuan over the past 20 years, with increased amplitude of 40.28%. The contribution of all ecosystems to the GEP was in the order of forest > farmland > grassland > wetland > city. ② In the spatial dimension, the GEP exhibited high values in western and southeastern regions and low values in central and northern regions. The GEP growth rate was higher in the Wulingshan area of western Hunan and lower in the Dongtinghu area of northern Hunan. ③ Compared with the existing research results on a grid scale of 10 km×10 km, the GEP results with a high spatial resolution showed more details of the spatial distribution of the aquatic and urban ecosystems. ④ The contribution degrees of ecosystem function values to the GEP of Hunan changed regularly over time. The contribution of the soil conservation function value dominated the changes in the GEP of the Wulingshan and Dongtinghu areas. The results of this study provide a basis for scientific decision-making in supervising natural resources and protecting the ecological environment in Hunan Province.

Research on the spatio-temporal evolution of urbanization is significant for optimizing the spatial structure of a city. Through the saturation and consistency correction of DMSP/OLS and NPP/VIIRS data, this study constructed a remote sensing dataset of night light in the Loess Plateau from 2000 to 2019. Then, this study calculated the compound night light index (CNLI) on different spatial scales and extracted the area of build-up areas in the Loess Plateau using a dichotomy method. Furthermore, this study analyzed the spatial evolution patterns using methods such as standard deviational ellipse (SDE). The results are as follows: ① The CNLI calculated from night light data correlated strongly with the urbanization development index (UDI) and various sub-indicators. ② The CNLI values of the Loess Plateau and five urban agglomerations showed significant upward trends during 2000—2019 and spatial downward trends from southeast to northwest. ③ The area of build-up areas in the Loess Plateau extracted using the dichotomy method had mean absolute and relative errors of 2.45 km² and 3.72%, respectively. ④ The focus of the built-up areas in the Loess Plateau showed a southeastward shifting trend during 2000—2019, with the SDE-covered area decreasing significantly (slope = 0.0107 km²/a; p < 0.01) and the azimuth angle changing from northeastern 83.33° to 88.37°. The results of this study can provide data support and a methodological reference for investigating the spatio-temporal patterns of urbanization in the Loess Plateau and other ecologically vulnerable areas.

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.

Conventional pansharpening fusion methods suffer inaccurate extraction of details and low spectrum fusion accuracy. This study proposed a pansharpening algorithm of remote sensing images based on nonsubsampled Contourlet transform (NSCT) and pulse coupled neural networks (PCNN) by combining the multi-scale and -directional decomposition characteristics of NSCT and the pulse synchronous emission characteristics of PCNN. The process of this pansharpening algorithm is as follows: first, the details of panchromatic images were extracted through NSCT; then, the extracted detail features were injected into the irregular segmentation regions obtained using the PCNN model; finally, the sharpening fusion results of high-resolution multispectral remote-sensing images were obtained through statistical weighting. As corroborated by the experimental results of WorldView-2 and GF-2 data sets, the pansharpening algorithm outperforms other remote sensing image fusion algorithms in detail preservation and spectral consistency, verifying its effectiveness.

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 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.