Assessing groundwater contamination risk is a critical aspect of preventing and managing groundwater pollution. There was a research gap in the investigation of uncertainties in modeling groundwater contamination risks in aquifers. This study addresses this gap using Bayesian Model Averaging (BMA), with a novel focus on risk exposures from geogenic contaminants, such as lead (Pb). This was achieved through the following methodology: (1) assessing aquifer vulnerability using the SPECTR framework; (2) generating a risk index for geogenic contaminants through unsupervised methods; (3) enhancing geogenic risk through three individual models, including Gene Expression Programming (GEP), M5P, and Support Vector Machines (SVM); (4) combining results from individual models using BMA; and (5) examining inherent uncertainties, accounting for both between-model and within-model variances. The model's efficacy was evaluated using measured Pb concentrations within the aquifer. The findings indicated that the unsupervised risk index had an acceptable correlation, while the individual models were accurate and enhanced the predictability of the data. BMA assigned the higher posterior probabilities (weight) to the SVM model, which indicates a positive correlation between the performance criteria of individual models and the weight values. Also, BMA revealed that the modeling uncertainty is influenced by within-model variance, primarily by the kriging interpolation method.
Read full abstract