Understanding the Efficacy of U-Net & Vision Transformer for Groundwater Numerical Modelling
It addresses groundwater modeling challenges for hydrologists and environmental scientists, but is incremental as it applies existing methods to a specific domain.
This paper compared U-Net, U-Net with Vision Transformers, and Fourier Neural Operator for groundwater modeling, finding that U-Net-based models outperformed FNO in accuracy and efficiency, particularly with sparse data.
This paper presents a comprehensive comparison of various machine learning models, namely U-Net, U-Net integrated with Vision Transformers (ViT), and Fourier Neural Operator (FNO), for time-dependent forward modelling in groundwater systems. Through testing on synthetic datasets, it is demonstrated that U-Net and U-Net + ViT models outperform FNO in accuracy and efficiency, especially in sparse data scenarios. These findings underscore the potential of U-Net-based models for groundwater modelling in real-world applications where data scarcity is prevalent.