Hybrid explainable machine learning models for predicting rapid chloride penetration test and sorptivity of self-compacting concrete with fly ash and silica fume under thermal exposure

In this study, a comprehensive dataset comprising 360 Rapid Chloride Penetration Test (RCPT) and 360 sorptivity measurements from 60 self-compacting concrete (SCC) mixtures with varying fly ash and silica fume contents and different temperature exposures was analyzed. To reduce reliance on labor-intensive experiments, four hybrid predictive models were developed by integrating XGBoost with metaheuristic optimization algorithms, namely Particle Swarm Optimization (PSO), Whale Optimization Algorithm (WOA), and African Vultures Optimization Algorithm (AVOA). While the primary focus is on enhancing predictive accuracy, with the XGBoost-WOA model achieving the best performance, the modeling framework also provides a foundation for future exploration of the influence of supplementary cementitious materials and curing conditions on SCC durability. Feature importance analysis identified temperature as the most critical variable influencing both RCPT (permutation score: 0.649, SHAP: 110.626) and sorptivity (permutation score: 0.993, SHAP: 2.694). Furthermore, Monte Carlo simulations incorporating ±5% input noise confirmed the accuracy under uncertain input variable. To enhance practical utility, a Python-based GUI was developed using Tkinter, enabling users to predict RCPT and sorptivity values for SCC mixes containing FA and SF. Beyond offering an efficient alternative to traditional laboratory testing, the developed AI models have revealed new correlations between mix composition and durability performance.