Explainable AI Models for Blast-Induced Air Overpressure Prediction Incorporating Meteorological Effects

Accurate prediction of blast-induced air overpressure (AOp) is vital for environmental management and safety in mining and construction. Traditional empirical models are simple but fail to capture complex meteorological effects, while accurate black-box machine learning models lack interpretability, creating a significant dilemma for practical engineering. This study resolves this by applying explainable AI (XAI) to develop a transparent, “white-box” model that explicitly quantifies how meteorological parameters, wind speed, direction, and air temperature influence AOp. Using a dataset from an urban excavation site, the methodology involved comparing a standard USBM empirical model and a Multivariate Non-linear Regression (MNLR) model against a Symbolic Regression (SR) model implemented with the PySR tool. The SR model demonstrated superior performance on an independent test set, achieving an R2 of 0.771, outperforming both the USBM (R2 = 0.665) and MNLR (R2 = 0.698) models, with accuracy rivaling a previous “black-box” neural network. The key innovation is SR’s ability to autonomously generate an explicit, interpretable equation, revealing complex, non-linear relationships between AOp and meteorological factors. This provides a significant engineering contribution: a trustworthy, transparent tool that enables engineers to perform reliable, meteorologically informed risk assessments for safer blasting operations in sensitive environments like urban areas.