Explanation and optimization of ML for coagulant dosing in Water treatment plant using XAI(eXplainable AI)
Hongeun Park, Yunhwan Nam, Ho-Hyun Lee, Sungyun Kim · Research Square · 2024
Abstract In the water treatment process, determining the appropriate dosing of coagulants is crucial for both ensuring water quality and optimizing operational costs. Traditional methods predominantly rely on heuristic approaches or manual calibrations. However, the actual reactions between various water qualities and chemicals are intricate and nonlinear, often making it challenging to stably secure the targeted water quality. In particular, due to industrialization-induced water pollution and rapid climate change, conventional automated water treatment systems alone are insufficient to adequately respond. This research introduces an innovative approach for clarifying and optimizing the dosing of coagulants in water treatment plants using Explainable Artificial Intelligence (XAI), specifically the SHAP and ICE techniques. These methods allow for a nuanced understanding of feature contributions and individual predictions. Our findings suggest that the XAI-driven approach not only improves the accuracy of coagulant dosing but also offers valuable insights to operators, promoting more informed decision-making. The integration of machine learning and XAI in the water treatment field promises a future of more efficient, transparent, and responsible operations.