Robust prediction of water arsenic levels downstream of gold mines affected by acid mine drainage using hybrid ensemble machine learning and soft computing

Water pollution from hazardous materials, particularly arsenic, downstream of gold mines poses severe environmental and health risks. This study employs a systematic approach to predict water arsenic (WA) levels downstream of gold mines affected by acid mine drainage. WA data from the affected region were collected and preprocessed to standardize the dataset and mitigate overfitting risks. Advanced ensemble machine learning methods, particularly Light Gradient Boosting Machine (LightGBM), with two models developed: a manually-adjusted version and an optimization-based model using Jellyfish Search Optimizer (JSO). The performance of the LightGBM-JSO model was evaluated against a range of ensemble learning models, metaheuristic algorithms, and artificial intelligence techniques. Models were evaluated using mean absolute error (MAE), mean absolute percentage error (MAPE), coefficient of determination (R 2 ), root mean square error (RMSE), weighted mean absolute percentage error (WMAPE), mean relative error (MRE), scattered index (SI), ρ, and the Final Rating (FRa) methodology. The LightGBM-JSO outperformed other models, achieving a training phase MAE of 148.763, MAPE of 62.081, R 2 of 0.996, RMSE of 183.692, WMAPE of 0.08, SI of 0.097, ρ of 0.048, and MRE of − 0.379. In the testing phase, it had an MAE of 19.496, MAPE of 10.686, R 2 of 0.990, RMSE of 37.386, WMAPE of 0.136, SI of 0.241, ρ of 0.121, and MRE of 0.03. Uncertainty analysis confirmed the model's reliability with a prediction interval of ± 0.05 mg/L for arsenic concentration. This study provides evidence to support environmental management decisions, providing valuable insights for regulatory bodies, policymakers, and stakeholders to support sustainable mining practices. • Arsenic levels downstream of gold mines were predicted using advanced machine learning. • LightGBM-JSO outperformed other models in predicting arsenic contamination. • Comprehensive model evaluation confirmed high accuracy and reliability. • Study supports sustainable mining through evidence-based environmental management.