Precise Analysis and Prediction of Active Earth Pressure for Retaining Walls Based on Explainable Machine Learning

The classical Rankine and Coulomb theories frequently encounter difficulties in accurately modeling the complex, nonlinear, and displacement-coupled behavior of earth pressure on retaining walls under non-limit states. The present study proposes a “key feature refinement strategy based on collinearity analysis” and employs the said strategy by applying it to model test data. The strategy identified an optimum set of five physical parameters, namely displacement mode (DM), relative displacement (Δ/H), relative depth (Z/H), unit weight (γ), and internal friction angle (φ). A machine learning (ML) model has been developed that integrates Categorical Boosting with SHapley Additive exPlanations (CatBoost-SHAP). This model has been found to exhibit a marked enhancement in accuracy (R² = 0.917) when compared to classical theories, while concurrently offering the distinct advantage of explicit interpretability. SHAP analysis has been demonstrated to elucidate the nonlinear influence of each parameter. It is confirmed that displacement mode is identified as the governing factor for spatial pressure distribution, and classical mechanisms such as top‑down stress relaxation in the rotation-about-the-base (RB) mode and soil arching in the rotation-about-the-base (RT) mode are visualized. Furthermore, a displacement‑dependent mechanical threshold (Δ/H ≈ 0.006) has been identified, which marks the transition from a mode‑dominated to displacement‑driven pressure evolution. In addition, the proposed approach is integrated into a graphical user interface (GUI) that is designed to be user‑friendly, thereby furnishing practitioners with a precise tool for designing retaining walls. The validation of the model's performance against independent experimental results has demonstrated its superior agreement and practical utility under displacement-controlled conditions in comparison to conventional methods.