Explainable AI models for predicting liquefaction-induced lateral spreading
This work addresses the need for explainable AI in geotechnical engineering to enhance reliability and adoption in hazard assessment, though it is incremental as it applies existing methods to a specific domain.
The study tackled the problem of predicting liquefaction-induced lateral spreading by using SHAP to interpret an XGB model trained on data from the 2011 Christchurch Earthquake, resulting in the model successfully identifying key soil characteristics from CPT data and aligning with engineering knowledge.
Earthquake-induced liquefaction can cause substantial lateral spreading, posing threats to infrastructure. Machine learning (ML) can improve lateral spreading prediction models by capturing complex soil characteristics and site conditions. However, the "black box" nature of ML models can hinder their adoption in critical decision-making. This study addresses this limitation by using SHapley Additive exPlanations (SHAP) to interpret an eXtreme Gradient Boosting (XGB) model for lateral spreading prediction, trained on data from the 2011 Christchurch Earthquake. SHAP analysis reveals the factors driving the model's predictions, enhancing transparency and allowing for comparison with established engineering knowledge. The results demonstrate that the XGB model successfully identifies the importance of soil characteristics derived from Cone Penetration Test (CPT) data in predicting lateral spreading, validating its alignment with domain understanding. This work highlights the value of explainable machine learning for reliable and informed decision-making in geotechnical engineering and hazard assessment.