Physics Guided Recurrent Neural Networks For Modeling Dynamical Systems: Application to Monitoring Water Temperature And Quality In Lakes

TL;DR

This paper presents a physics-guided recurrent neural network framework that integrates scientific knowledge and physical constraints to improve modeling of dynamical systems, demonstrated on lake temperature and water quality prediction.

Contribution

It introduces a hybrid physics-data modeling approach that incorporates physical knowledge as constraints in training recurrent neural networks for dynamical systems.

Findings

Enhanced prediction accuracy over purely data-driven models

Improved scientific consistency of the results

Effective modeling of lake temperature and water quality

Abstract

In this paper, we introduce a novel framework for combining scientific knowledge within physics-based models and recurrent neural networks to advance scientific discovery in many dynamical systems. We will first describe the use of outputs from physics-based models in learning a hybrid-physics-data model. Then, we further incorporate physical knowledge in real-world dynamical systems as additional constraints for training recurrent neural networks. We will apply this approach on modeling lake temperature and quality where we take into account the physical constraints along both the depth dimension and time dimension. By using scientific knowledge to guide the construction and learning the data-driven model, we demonstrate that this method can achieve better prediction accuracy as well as scientific consistency of results.