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.

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.

Because of the degradation of classification accuracy that is caused by the uncertainty of pixel class and classification decisions of high-resolution remote-sensing images, we proposed a supervised classification method that is based on an interval type-2 fuzzy membership function for high-resolution remote-sensing images. We analyze the data features of a high-resolution remote-sensing image and construct a type-1 membership function model in a homogenous region by supervised sampling in order to characterize the uncertainty of the pixel class. On the basis of the fuzzy membership function model in the homogeneous region and in accordance with the 3σ criterion of normal distribution, we proposed a method for modeling three types of interval type-2 membership functions and analyze the different types of functions to improve the uncertainty of pixel class expressed by the type-1 fuzzy membership function and to enhance the accuracy of classification decision. According to the principle that importance will increase with a decrease in the distance between the original, upper, and lower fuzzy membership of the training data and the corresponding frequency value in the histogram, we use the weighted average sum of three types of fuzzy membership as the new fuzzy membership of the pixel to be classified and then integrated into the neighborhood pixel relations, constructing a classification decision model. We use the proposed method to classify real high-resolution remote-sensing images and synthetic images. Additionally, we qualitatively and quantitatively evaluate the test results. The results show that a higher classification accuracy can be achieved with the proposed algorithm.

As data science advances, automated machine learning (AutoML) gains attention for lowering barriers, saving time, and enhancing efficiency. However, with increasing data dimensionality, AutoML struggles with large-scale feature sets. Effective feature selection is crucial for efficient AutoML in multi-task applications. This study proposes an efficient modeling framework combining a multi-stage feature selection (MSFS) algorithm and AutoSklearn, a robust and efficient AutoML framework, to address high-dimensional data challenges. The MSFS algorithm includes three stages: mutual information gain (MIG), recursive feature elimination with cross-validation (RFECV), and a voting aggregation mechanism, ensuring comprehensive consideration of feature correlation, importance, and stability. Based on multi-source and time series remote sensing data, this study pioneers the application of AutoSklearn for forest fire risk prediction. Using this case study, we compare MSFS with five other feature selection (FS) algorithms, including three single FS algorithms and two hybrid FS algorithms. Results show that MSFS selects half of the original features (12/24), effectively handling collinearity (eliminating 11 out of 13 collinear feature groups) and increasing AutoSklearn’s success rate by 15%, outperforming two FS algorithms with the same number of features by 7% and 5%. Among the six FS algorithms and non-FS, MSFS demonstrates the highest prediction performance and stability with minimal variance (0.09%) across five evaluation metrics. MSFS efficiently filters redundant features, enhancing AutoSklearn’s operational efficiency and generalization ability in high-dimensional tasks. The MSFS–AutoSklearn framework significantly improves AutoML’s production efficiency and prediction accuracy, facilitating the efficient implementation of various real-world tasks and the wider application of AutoML.

The spatial fragmentation of high-resolution remote sensing images makes the segmentation algorithm put forward a strong demand for noise immunity. However, the stronger the noise immunity, the more serious the loss of detailed information, which easily leads to the neglect of effective characteristics. In view of the difficulty of balancing the noise immunity and effective characteristic retention, an adaptive distance-weighted Voronoi tessellation technology is proposed for remote sensing image segmentation. The distance between pixels and seed points in Voronoi tessellation is established by the adaptive weighting of spatial distance and spectral distance. The weight coefficient used to control the influence intensity of spatial distance is defined by a monotone decreasing function. Following the fuzzy clustering framework, a fuzzy segmentation model with Kullback–Leibler (KL) entropy regularization is established by using multivariate Gaussian distribution to describe the spectral characteristics and Markov Random Field (MRF) to consider the neighborhood effect of sub-regions. Finally, a series of parameter optimization schemes are designed according to parameter characteristics to obtain the optimal segmentation results. The proposed algorithm is validated on many multispectral remote sensing images with five comparing algorithms by qualitative and quantitative analysis. A large number of experiments show that the proposed algorithm can overcome the complex noise as well as better ensure effective characteristics.