Global climate change has led to a marked increase in the frequency of record-breaking extreme rainfall events, which often surpass historical benchmarks and pose significant challenges to conventional geological hazard risk assessment methods. This study used a record-breaking extreme rainfall event in Zhenba County, Shaanxi Province, in July 2023 as a case study to develop a tailored risk assessment framework for geological hazards under extreme rainfall conditions. By integrating high-resolution Planet satellite imagery, millimeter-scale surface deformation data derived from SBAS-InSAR, and detailed field investigation results, a comprehensive disaster inventory containing 1012 landslides was compiled. The proposed framework integrates cumulative extreme rainfall metrics with subtle ground deformation indicators and applies four advanced machine learning algorithms—DNN, XGBoost, RF, and LightGBM—for multidimensional hazard assessment. Among these, the DNN model exhibited the highest performance, achieving an AUC of 0.82 and Kappa coefficients of 0.833 (training) and 0.812 (prediction). Further analysis using SHAP values identified distance to rivers, cumulative rainfall, and the Topographic Wetness Index (TWI) as the most influential factors governing landslide occurrence under extreme rainfall conditions. Validation using representative case studies confirmed that the framework effectively identifies high-hazard zones, particularly in areas severely impacted by debris flows and landslide deformation zones. These findings provide a robust scientific foundation and technical basis for early warning, disaster prevention, and mitigation strategies in geologically complex regions increasingly affected by extreme rainfall events.

Based on a review of the fundamental principles of the Newmark sliding displacement method, this paper proposes an improved approach based on the upper bound solution of plastic mechanics, drawing on the theory of Academician Zuyu Chen, which states that “during a given time period t, whenever velocity V > 0 occurs, the integration domain must be determined based on the varying distributions of acceleration a.” The improved Newmark program integrates four main categories and eight subcategories of conditions into its framework through C + + programming. By employing the inclined strip method to construct velocity fields, the program enables more precise calculations of permanent slope displacements. To validate the effectiveness and accuracy of the improved method, calculations were conducted on both ideal slope models and real-world slope models. For the ideal soil and rock slope models, the results from the improved Newmark program were consistent with those obtained using the pseudo-static method and commercial software, demonstrating its strong applicability and accuracy. Furthermore, normalized artificial seismic waves, the Loma Prieta earthquake wave, and the Wenchuan earthquake wave, each with varying amplification factors, were input into the actual slope model of a colluvial deposit at the C₁ hydropower station in Tibet. A comparison of these results with existing data revealed that the improved Newmark program produced calculations that closely matched real-world observations. This further validates the method’s reliability and accuracy in practical applications. In conclusion, the improved Newmark program can more accurately calculate permanent displacements under seismic loads, which has far-reaching significance for the design and safety assessment of slope engineering.