Song, X., I. Demirkanli, Z. Hou, X. Lin, M. Karanovic, M. Tonkin, D. Appriou, and R. Mackley.
Advances in Water Resources 202:105002(2025)
Filed Under: General News
Filed Under: General News
A novel approach that integrates analytical solutions for groundwater dynamics with the U-Net deep learning framework is introduced to predict groundwater contaminant plume migration under dynamic pumping conditions. By incorporating the Thiem equation into the input preprocessing, the U-Net model transforms sparse well data into a continuous spatial field that captures the hydraulic impacts of pumping activities. This integration enables the model to leverage both deep learning capabilities and classical physics-based groundwater theories, enhancing prediction accuracy and computational efficiency. For example, in 2D synthetic cases, integrating analytical solutions reduced the root mean squared error (RMSE) from 2.76 µg/L to 0.7 µg/L. In a complex 3D heterogeneous model of the Hanford Site's 200 West P&T facility, the model completed a 12-year simulation in just 600 ms on a single CPU core, achieving an accumulative RMSE of <1.6 µg/L, an improvement of over three orders of magnitude in simulation speed compared to a numerical model. Advancements support rapid evaluations of P&T optimization scenarios, enabling timely and effective decision-making for well placement and system management. Findings highlight the potential of advanced machine learning models to significantly enhance the efficiency and sustainability of groundwater remediation efforts, offering a novel application of the U-Net architecture in environmental science. https://www.sciencedirect.com/science/article/pii/S0309170825001162/pdfft?md5=85822b78bc54ffc8ae8397fa14a3632b&pid=1-s2.0-S0309170825001162-main.pdf