Fast and interpretable prediction of seismic kinematics of flexible retaining walls in sand through explainable artificial intelligence
Year: 2024
Type: article
Abstract: Assessing the response of earth-retaining walls to seismic loading is key for safety. Nonlinear dynamic analyses using the finite element method (FEM) calculate the permanent displacements (PDs) the soil-wall system accumulates during an earthquake, but are computationally intensive. Simplified dynamic displacement-based methods that obtain PDs using a failure mechanism (FM) and critical acceleration are faster. Still, they require geotechnical expertise, e.g., in strength, failure criteria, and stability under pseudo-static conditions. This paper presents a system using explainable artificial intelligence to predict the FM and kc (critical acceleration as a fraction of gravity) of flexible retaining walls in dry, coarse-grained soil, based on geometry and soil/wall properties. We created a large dataset (~1,000 samples) via FEM simulations based on plasticity limit theorems, with 7 types of FMs affecting 3 types of walls: propped, cantilever, and anchored. Each sample contained geometrical parameters, soil/wall properties, and FEM-derived FM and kc. Trained on these data, the system achieved a weighted F1-score of 97.28% and an R2 above 0.987 for FM and kc predictions, respectively. The system provides Shapley explanations (SHAP) of the results and a coherence method to check explanation consistency. Its high accuracy, millisecond-level inference, and interpretability promote expert collaboration and enhance decision-making.
Source: Computers and Geotechnics
Institutions: University of Pisa, Università degli Studi eCampus
Language: English
Subfield: Civil and Structural Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,580
OpenAlex ID: W4405891262