Wetland ecosystems are essential to the preservation of biodiversity. Plateau wetland ecosystems are vital components of wetland ecosystems, characterized by diverse wetland types and fragmented land distribution. In the extraction of plateau wetlands, there are such issues as inaccuracy in classification, inadequately fine categories, and difficulty in extracting vegetated wetlands. The aim of this study was to establish a new classification framework for extracting detailed information about plateau wetlands, and the Dianchi Basin was used as the study area. Using Gaofen-2 (GF-2) imagery from 2019–2021, land cover information was extracted by applying nearest neighbor classification and random forest classification. Wetlands were then extracted from the land cover data using ecological rule classification, and a detailed wetland map of the Dianchi Basin was obtained in 2020 with a 1 m resolution. Results showed that the production accuracies of forest wetlands, shrub wetlands, meadow wetlands, rivers, ponds, reservoirs, and lakes in the Dianchi Basin were 89.4%, 87.9%, 91.4%, 90.7%, 89.9%, 92.9%, and 95.9%, respectively, and the user accuracies were 94.9%, 92.4%, 92.6%, 95.4%, 94.2%, 91.0%, and 99.4%, respectively. Compared to the CAS_Wetlands, this study categorized the five categories of plateau wetlands into seven types with greater specificity and increased the spatial resolution of wetland mapping from 30 m to 1 m. This study can provide a new reference framework for wetland extraction and support the conservation of plateau wetland ecosystems.

Landslide detection in mountainous regions remains highly challenging due to complex terrain conditions, heterogeneous surface textures, and the fragmented distribution of landslide features. To address these limitations, this study proposes an enhanced object detection framework named YOLOv11-SAFM, which integrates a Spatially Adaptive Feature Modulation (SAFM) module, an optimized MPDIoU-based bounding box regression loss, and a multi-scale training strategy. These improvements strengthen the model’s ability to detect small-scale landslides with blurred edges under complex geomorphic conditions. A high-resolution remote sensing dataset was constructed using imagery from Bijie and Zhaotong in southwest China including GF-2 optical imagery at 1 m resolution and Sentinel-2 data at 10 m resolution for model training and validation, while independent data from Zhenxiong County were used to assess generalization capability. Experimental results demonstrate that YOLOv11-SAFM achieves a precision of 95.05%, recall of 90.10%, F1-score of 92.51%, and mAP@0.5 of 95.30% on the independent test set of the Zhaotong–Bijie dataset for detecting small-scale landslides in rugged plateau environments. Compared with the widely used Mask R-CNN, the proposed model improves precision by 13.87% and mAP@0.5 by 15.7%; against the traditional YOLOv8, it increases recall by 27.0% and F1-score by 22.47%. YOLOv11-SAFM enables efficient and robust automatic landslide detection in complex mountainous terrains and shows strong potential for integration into operational geohazard monitoring and early warning systems.

Soil organic carbon density (SOCD) in swamp wetlands is a critical indicator for assessing global carbon stocks. In plateau wetlands, challenges such as dense vegetation cover and fragmented land distribution complicate SOCD research. The availability of high-resolution optical and radar satellite data introduces new possibilities for precise carbon stock predictions. This study proposes a framework that combines multi-source remote sensing data with the SSA-RF (Sparrow Search Random Forest Algorithm) algorithm to predict SOCD in plateau swamp wetlands. It also compares the effectiveness of laboratory spectroscopy and multi-source remote sensing in monitoring SOCD. We integrated 24 features from Sentinel-1 (S1), Sentinel-2 (S2), topographic, and climatic data, along with spectral data ranging from 550 to 1400 nm, to construct the SSA-RF model and map the SOCD distribution of swamp wetlands in Dianchi Basin. Additionally, we estimated the total soil organic carbon stock in these wetlands. The results indicate that the multi-source remote sensing SSA-RF model (S1+S2+topographic+climatic SSA-RF) achieved an R² of 0.76, an RMSE of 1.14, an MAE of 0.65, and an RPD of 1.98. Compared to the spectral model, this model improved the R² by 0.24 and the RPD by 0.5. Relative to the S1+S2 SSA-RF model, the R² increased by 0.15, and the RMSE decreased by 0.46. The total soil organic carbon stock of the swamp wetlands in the Dianchi Basin was estimated to be 1.32 × 10⁵ t. This study provides a new framework for predicting carbon stocks in plateau wetlands, offering a reference for global wetland carbon sink assessments.

Soil total nitrogen (STN) is a key indicator of soil fertility and plays a fundamental role in agricultural productivity and sustainable land management. However, achieving an accurate and spatially continuous estimate of STN at the field scale remains challenging due to inherent soil variability and the constraints of conventional sampling methods. In this study, we employed unmanned aerial vehicle (UAV)-based hyperspectral imagery to estimate STN by integrating spectral preprocessing, feature selection, and machine learning techniques. Multiple feature selection methods, including Pearson correlation analysis, variable importance in projection (VIP), and competitive adaptive reweighted sampling (CARS), were evaluated to identify the most informative spectral bands. Several regression models—support vector regression with radial basis function kernel (SVR-RBF), random forest (RF), Extra Trees, PCA-SVR-RBF, and XGBoost—were compared for STN prediction. Among these, the VIP-PCA-SVR-RBF model yielded the best performance, achieving a test R² of approximately 0.77 and an RMSE of 0.45 g kg⁻¹. The integration of VIP-based feature selection with PCA dimensionality reduction significantly enhanced predictive accuracy and generalization capability compared to the other models tested. Spatial prediction maps derived from the optimal model revealed considerable heterogeneity in STN distribution across the study area. These results underscore the potential of UAV hyperspectral remote sensing for high-resolution mapping of soil nitrogen and offer a promising framework for precision nutrient management in agriculture.

Background: Rainfall-induced landslides are a widespread and destructive geological hazard that resist precise prediction. They pose serious threats to human lives and property, ecological stability, and socioeconomic development. Methods: To address the challenges in mitigating rainfall-induced landslides in high-altitude mountainous regions, this study proposes a digital twin framework that couples multiple physical fields and is based on the spherical discrete element method. Results: Two-dimensional simulations identify a trapezoidal stress distribution with inward-increasing stress. The stress increases uniformly from 0 kPa at the surface to 210 kPa in the interior. The crest stress remains constant at 1.8 kPa under gravity, whereas the toe stress rises from 6.5 to 14.8 kPa with the slope gradient. While the stress pattern persists post-failure, specific magnitudes alter significantly. This study pioneers a three-dimensional close-packed spherical discrete element method, achieving enhanced computational efficiency and stability through streamlined contact mechanics. Conclusions: The proposed framework utilizes point-contact mechanics to simplify friction modeling, enhancing computational efficiency and numerical stability. By integrating stress, rainfall, and seepage fields, we establish a coupled hydro-mechanical model that enables real-time digital twin mapping of landslide evolution through dynamic parameter adjustments.

Landslide deformation monitoring plays a critical role in geohazard prevention and risk mitigation in mountainous regions, where timely and reliable deformation information is essential for early warning and disaster management. Monitoring landslide deformation in mountainous areas remains a persistent challenge, largely due to rugged topography, dense vegetation cover, and low interferometric coherence—factors that substantially limit the effectiveness of conventional InSAR methods. To address these issues, this study aims to develop a robust time-series InSAR framework for enhancing deformation detection and measurement density under low-coherence conditions in complex mountainous terrain, and accordingly introduces the Sequential Estimation and Total Power-Enhanced Expectation–Maximization Inversion (SETP-EMI) approach, which integrates dual-polarization Sentinel-1 SAR time series within a recursive estimation framework, augmented by polarimetric coherence optimization. This methodology allows for dynamic assimilation of SAR data, improves phase quality under low-coherence conditions, and enhances the extraction of distributed scatterers (DS). When applied to Zhenxiong County, Yunnan Province—a region prone to geohazards with complex terrain—the SETP-EMI method achieved a landslide detection rate of 94.1%. It also generated approximately 2.49 million measurement points, surpassing PS-InSAR and SBAS-InSAR results by factors of 22.5 and 3.2, respectively. Validation against ground-based leveling data confirmed the method’s high accuracy and robustness, yielding a standard deviation of 5.21 mm/year. This study demonstrates that the SETP-EMI method, integrated within a DS-InSAR framework, effectively overcomes coherence loss in densely vegetated plateau regions, improving landslide monitoring and early-warning capabilities in complex mountainous terrain.