Applications of physics-informed scientific machine learning in subsurface science: A survey

TL;DR

This survey reviews recent advances in physics-informed scientific machine learning applied to subsurface geosystems, emphasizing improvements in accuracy, interpretability, and scalability for better geoscientific decision-making.

Contribution

It systematically analyzes how domain-aware SciML models are developed and applied to enhance geosystem management, highlighting strategies to improve model performance and trustworthiness.

Findings

Enhanced ML models improve geosystem monitoring accuracy.

Physics-informed approaches increase model interpretability.

Scalability strategies enable application to large-scale geosystems.

Abstract

Geosystems are geological formations altered by humans activities such as fossil energy exploration, waste disposal, geologic carbon sequestration, and renewable energy generation. Geosystems also represent a critical link in the global water-energy nexus, providing both the source and buffering mechanisms for enabling societal adaptation to climate variability and change. The responsible use and exploration of geosystems are thus critical to the geosystem governance, which in turn depends on the efficient monitoring, risk assessment, and decision support tools for practical implementation. Fast advances in machine learning (ML) algorithms and novel sensing technologies in recent years have presented new opportunities for the subsurface research community to improve the efficacy and transparency of geosystem governance. Although recent studies have shown the great promise of scientific ML (SciML) models, questions remain on how to best leverage ML in the management of geosystems, which are typified by multiscality, high-dimensionality, and data resolution inhomogeneity. This survey will provide a systematic review of the recent development and applications of domain-aware SciML in geosystem researches, with an emphasis on how the accuracy, interpretability, scalability, defensibility, and generalization skill of ML approaches can be improved to better serve the geoscientific community.