Predicting seawater intrusion wedge length in coastal aquifers using hybrid gradient boosting techniques

Abstract Controlling seawater intrusion (SWI) into freshwater aquifers is crucial for preserving water quality in coastal groundwater management. This research evaluates the performance of three machine learning (ML) models: eXtreme Gradient Boosting (BO-XGB), Light Gradient Boosting Machine (BO-LGB), and Categorical Gradient Boosting (BO-CGB) in predicting the SWI wedge length. A database of 345 numerical simulations was compiled from previous research, and Bayesian Optimization (BO) with fivefold cross-validation was used to fine-tune the models. The inputs included abstraction well distance ( X a ), abstraction well depth ( Y a ), recharge well distance ( X r ), recharge well depth ( Y r ), abstraction rate ( Q a ), artificial recharge rate ( Q r ), and SWI wedge length ( L ). Results show that BO-CGB consistently achieved the best performance, with high R 2 values (0.996 in training and 0.969 in testing) and low RMSE values (0.439 m in training and 1.327 m in testing). SHapley Additive exPlanations (SHAP) analysis highlighted that Q a and Q r had the most significant impact on SWI wedge length predictions, followed by X a and Y a . Partial Dependence Plot (PDP) analysis revealed a strong negative correlation between flow variables Q a and Q r and wedge length, while X r displayed a more complex, non-linear pattern. BO-CGB emerged as the most reliable model for predicting SWI wedge length. To facilitate practical application, an interactive Graphical User Interface (GUI) was developed, enabling users to input variables and receive instant predictions, enhancing the practical usability of the ML models in managing SWI in coastal aquifers.