In optical remote sensing images, the presence of clouds affects the completeness of the ground observation and further affects the accuracy and efficiency of remote sensing applications. Especially in quantitative analysis, the impact of cloud cover on the reliability of analysis results cannot be ignored. Therefore, high-precision cloud detection is an important step in the preprocessing of optical remote sensing images. In the past decade, with the continuous progress of artificial intelligence, algorithms based on deep learning have become one of the main methods for cloud detection. The rapid development of deep learning technology, especially the introduction of self-attention Transformer models, has greatly improved the accuracy of cloud detection tasks while achieving efficient processing of large-scale remote sensing images. This review provides a comprehensive overview of cloud detection algorithms based on deep learning from the perspective of semantic segmentation, and elaborates on the research progress, advantages, and limitations of different categories in this field. In addition, this paper introduces the publicly available datasets and accuracy evaluation indicators for cloud detection, compares the accuracy of mainstream deep learning models in cloud detection, and briefly summarizes the subsequent processing steps of cloud shadow detection and removal. Finally, this paper analyzes the current challenges faced by existing deep learning-based cloud detection algorithms and the future development direction of the field.

Over the past few decades, the coastal city of Shenzhen has been transformed from a small fishing village to a mega city as China’s first Special Economic Zone. The rapid economic development was matched by a sharp increase in the demand for usable land and coastal reclamation has been undertaken to create new land from the sea. However, it has been reported that subsidence occurred in land reclamation area and around subway tunnel area. Subsidence and the additional threat of coastal inundation from sea-level rise highlight the necessity of displacement monitoring in Shenzhen. The time Series InSAR technique is capable of detecting sub-centimeter displacement of the Earth’s surface over large areas. This study uses Envisat, COSMO-SkyMed, and Sentinel-1 datasets to determine the surface movements in Shenzhen from 2004 to 2010 and from 2013 to 2017. Subsidence observed can be attributable to both land reclamation and subway construction. Seasonal displacements are likely to be associated with precipitation. The influence of ocean tidal level changes on seasonal displacement is not strongly evident from the results and requires further investigations. In general, InSAR has proven its ability to provide accurate measurements of ground stability for the city of Shenzhen.

Soil erosion often leads to land degradation, agricultural production reduction, and environmental deterioration, which seriously restricts the sustainable development of regions. Clarifying the driving factors of soil erosion is the premise of preventing soil erosion. Given the lack of current research on the driving factors/force changes of soil erosion in different regions or under different erosion intensity grades, this paper pioneered to use machine learning methods to address this problem. Firstly, the widely used (Revised) Universal Soil Loss Equation ((R)USLE) framework was applied to simulate the spatial distribution of soil erosion. Then, the K-fold algorithm was used to evaluate the accuracy and stability of five machine learning algorithms for fitting soil erosion. The random forest (RF) method performed best, with average accuracy reaching 86.35%. Then, the Permutation Importance (PI) and the Partial Dependence Plot (PDP) methods based on RF were introduced to quantitatively analyze the main driving factors under different geological conditions and the driving force changes of each factor under different erosion intensity grades, respectively. Results showed that the main drivers of soil erosion in Chongqing and Guizhou were cover management factors (PI: 0.4672, 0.4788), while that in Sichuan was slope length and slope factor (PI: 0.6165). Under different erosion intensity grades, the driving force of each factor shows nonlinear and complex inhibitory or promoting effects with factor value changing. These findings can provide scientific guidance for the refined management of soil erosion, which is significant for halting or reversing land degradation and achieving sustainable use of land resources.

Mapping rubber plantations in a large area is still challenging in high-cloud-cover and complex-vegetation landscapes. Existing studies were often confined to the discrimination of rubber trees from natural forests and rarely concerned other tropical tree species. The Sentinel-2 constellation, with improved spatial, spectral, and temporal resolution, offers new opportunities to improve previous efforts. In this paper, four Hainan Sentinel-2 composites were generated based on the detailed phenological stages delineation of rubber trees. The random forest classifier with different phenological stage combinations was utilized to discuss the capability of Sentinel-2 composites to map rubber plantations. The optimal resultant rubber plantation map had a producer’s accuracy, user’s accuracy, and F1 score of 81%, 84.4%, and 0.83, respectively. According to the rubber plantation map in 2020, there was a total of 5473 km² rubber plantations in Hainan, which was 2.93% higher than the statistical data from the Hainan Statistical Yearbook. According to the Hainan Statistical Yearbook, the area-weighted accuracy at the county level was 82.47%. The mean decrease in accuracy (MDA) was used to assess the feature importance of the four phenological stages. Results showed that the recovery growth stage played the most important role, and the resting stage was the least important. Moreover, in terms of the combinations of phenological stages, any dataset group with two phenological stages was sufficient for rubber tree discrimination. These findings were instrumental in facilitating the rubber plantation mapping annually. This study has demonstrated the potential of Sentinel-2 data, with the phenology-based image-compositing technique, for mapping rubber plantations in large areas with complex vegetation landscapes.