Soil moisture is a key parameter in the exchange of energy and water between the land surface and the atmosphere. This parameter plays an important role in the dynamics of permafrost on the Qinghai-Xizang Plateau, China, as well as in the related ecological and hydrological processes. However, the region's complex terrain and extreme climatic conditions result in low-accuracy soil moisture estimations using traditional remote sensing techniques. Thus, this study considered parameters of the backscatter coefficient of Sentinel-1A ground range detected (GRD) data, the polarization decomposition parameters of Sentinel-1A single-look complex (SLC) data, the normalized difference vegetation index (NDVI) based on Sentinel-2B data, and the topographic factors based on digital elevation model (DEM) data. By combining these parameters with a machine learning model, we established a feature selection rule. A cumulative importance threshold was derived for feature variables, and those variables that failed to meet the threshold were eliminated based on variations in the coefficient of determination (R2) and the unbiased root mean square error (ubRMSE). The eight most influential variables were selected and combined with the CatBoost model for soil moisture inversion, and the SHapley Additive exPlanations (SHAP) method was used to analyze the importance of these variables. The results demonstrated that the optimized model significantly improved the accuracy of soil moisture inversion. Compared to the unfiltered model, the optimal feature combination led to a 0.09 increase in R2 and a 0.7% reduction in ubRMSE. Ultimately, the optimized model achieved a R2 of 0.87 and an ubRMSE of 5.6%. Analysis revealed that soil particle size had significant impact on soil water retention capacity. The impact of vegetation on the estimated soil moisture on the Qinghai-Xizang Plateau was considerable, demonstrating a significant positive correlation. Moreover, the microtopographical features of hummocks interfered with soil moisture estimation, indicating that such terrain effects warrant increased attention in future studies within the permafrost regions. The developed method not only enhances the accuracy of soil moisture retrieval in the complex terrain of the Qinghai-Xizang Plateau, but also exhibits high computational efficiency (with a relative time reduction of 18.5%), striking an excellent balance between accuracy and efficiency. This approach provides a robust framework for efficient soil moisture monitoring in remote areas with limited ground data, offering critical insights for ecological conservation, water resource management, and climate change adaptation on the Qinghai-Xizang Plateau.

This study investigates the application of machine learning (ML) algorithms for seismic damage classification of bridges supported by helical pile foundations in cohesive soils. While ML techniques have shown strong potential in seismic risk modeling, most prior research has focused on regression tasks or damage classification of overall bridge systems. The unique seismic behavior of foundation elements, particularly helical piles, remains unexplored. In this study, numerical data derived from finite element simulations are used to classify damage states for three key metrics: piers' drift, piles' ductility factor, and piles' settlement ratio. Several ML algorithms, including CatBoost, LightGBM, Random Forest, and traditional classifiers, are evaluated under original, oversampled, and undersampled datasets. Results show that CatBoost and LightGBM outperform other methods in accuracy and robustness, particularly under imbalanced data conditions. Oversampling improves classification for specific targets but introduces overfitting risks in others, while undersampling generally degrades model performance. This work addresses a significant gap in bridge risk assessment by combining advanced ML methods with a specialized foundation type, contributing to improved post-earthquake damage evaluation and infrastructure resilience.

This study provides a comprehensive analysis of the undrained failure envelope for spudcan foundations in anisotropic clays using the AUS failure criterion as the soil strength model. The influence of embedment depth (L/D) and anisotropic strength (re) on spudcan behaviour under combined loading conditions is investigated. Failure envelopes are derived through three-dimensional finite element limit analysis (3D FELA) in both (H/ suTCA, M/suTCAD) and (V/Vult, H/suTCA, M/suTCAD) spaces. The study also illustrates spudcan foundation failure mechanisms, providing valuable insights for designing footings in anisotropic clays under combined loads (V, H, M). Additionally, an innovative soft-computing approach is introduced: a machine learning model that integrates categorical boosting (CatBoost) with the flower pollination algorithm (FPA) for optimized predictions of the spudcan failure envelope. The proposed FPA-CatBoost model is validated against numerical FELA results, demonstrating a strong correlation and offering engineers a reliable tool for determining spudcan foundation failure envelopes under varied loading conditions.