Shreyansh Mishra

How effective are physics-informed neural networks compared to machine learning in predicting groundwater flow in complex heterogeneous aquifers?

This study explores the applicability of physics-informed neural networks to synthetic and real-world groundwater case studies, encompassing heterogeneous and homogeneous aquifers with varying boundary conditions and transient states, and reveals that PINNs provide a compelling alternative to classic ML methods, partic...