Physics-Guided Foundation Model for Scientific Discovery: An Application to Aquatic Science

TL;DR

This paper introduces a physics-guided foundation model that combines pre-trained machine learning and physics-based models to improve the modeling of complex scientific systems, demonstrated on aquatic environmental data.

Contribution

It proposes a novel PGFM framework that integrates pre-trained ML models with physics-based models for complex systems involving multiple interacting processes.

Findings

Effective modeling of water temperature and dissolved oxygen in lakes.

Pre-trained model adapts to multiple features guided by physics principles.

Broad applicability to scientific fields using physics-based models.

Abstract

Physics-guided machine learning (PGML) has become a prevalent approach in studying scientific systems due to its ability to integrate scientific theories for enhancing machine learning (ML) models. However, most PGML approaches are tailored to isolated and relatively simple tasks, which limits their applicability to complex systems involving multiple interacting processes and numerous influencing features. In this paper, we propose a \textit{\textbf{P}hysics-\textbf{G}uided \textbf{F}oundation \textbf{M}odel (\textbf{PGFM})} that combines pre-trained ML models and physics-based models and leverages their complementary strengths to improve the modeling of multiple coupled processes. To effectively conduct pre-training, we construct a simulated environmental system that encompasses a wide range of influencing features and various simulated variables generated by physics-based models. The model is pre-trained in this system to adaptively select important feature interactions guided by multi-task objectives. We then fine-tune the model for each specific task using true observations, while maintaining consistency with established physical theories, such as the principles of mass and energy conservation. We demonstrate the effectiveness of this methodology in modeling water temperature and dissolved oxygen dynamics in real-world lakes. The proposed PGFM is also broadly applicable to a range of scientific fields where physics-based models are being used.