Machine learning surrogates for efficient hydrologic modeling: Insights from stochastic simulations of managed aquifer recharge

TL;DR

This paper explores the use of machine learning surrogates to significantly reduce computational time in hydrologic modeling, enabling faster uncertainty analysis and decision-making.

Contribution

It introduces a hybrid workflow combining process-based models with ML surrogates and evaluates various architectures for groundwater flow simulation.

Findings

ML surrogates achieve under 10% mean absolute percentage error.

Surrogates provide order-of-magnitude runtime savings.

Normalization and data reduction improve model accuracy and efficiency.

Abstract

Process-based hydrologic models are invaluable tools for understanding the terrestrial water cycle and addressing modern water resources problems. However, many hydrologic models are computationally expensive and, depending on the resolution and scale, simulations can take on the order of hours to days to complete. While techniques such as uncertainty quantification and optimization have become valuable tools for supporting management decisions, these analyses typically require hundreds of model simulations, which are too computationally expensive to perform with a process-based hydrologic model. To address this gap, we assess a hybrid modeling workflow in which a process-based model is used to generate an initial set of simulations and a machine learning (ML) surrogate model is then trained to perform the remaining simulations required for downstream analysis. As a case study, we apply this workflow to simulations of variably saturated groundwater flow at a prospective managed aquifer recharge site. We compare the accuracy and computational efficiency of several ML architectures, including deep convolutional networks, recurrent neural networks, vision transformers, and networks with Fourier transforms. Our results demonstrate that ML surrogate models can achieve under 10% mean absolute percentage error and yield order-of-magnitude runtime savings over process-based models. Building on these findings, we examine the impacts of key modeling choices on surrogate model accuracy and efficiency. Results show that a normalized loss function improves training stability, while min-max data normalization can significantly reduce error up to a factor of 10 when compared to other treatments such as Z-score and no normalization. Downsampling input features using an autoencoder also decreases memory requirements by training with tensors 4% their original size. By reducing computational costs and...