Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling

TL;DR

This paper presents a physics-guided neural network framework that integrates physics-based models and observational data to improve lake temperature predictions, ensuring scientific consistency and better generalization.

Contribution

It introduces a novel PGNN framework that combines physics-based loss functions with neural networks for scientific modeling tasks.

Findings

Enhanced prediction accuracy for lake temperature modeling.

Improved scientific consistency in neural network outputs.

Better generalizability due to physics-guided training.

Abstract

This paper introduces a framework for combining scientific knowledge of physics-based models with neural networks to advance scientific discovery. This framework, termed physics-guided neural networks (PGNN), leverages the output of physics-based model simulations along with observational features in a hybrid modeling setup to generate predictions using a neural network architecture. Further, this framework uses physics-based loss functions in the learning objective of neural networks to ensure that the model predictions not only show lower errors on the training set but are also scientifically consistent with the known physics on the unlabeled set. We illustrate the effectiveness of PGNN for the problem of lake temperature modeling, where physical relationships between the temperature, density, and depth of water are used to design a physics-based loss function. By using scientific knowledge to guide the construction and learning of neural networks, we are able to show that the proposed framework ensures better generalizability as well as scientific consistency of results. All the code and datasets used in this study have been made available on this link \url{https://github.com/arkadaw9/PGNN}.