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

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}.

Cited by in corpus (31)

• Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
• Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
• Thermodynamics-based Artificial Neural Networks for constitutive modeling
• Deep Learning of Subsurface Flow via Theory-guided Neural Network
• Theory-guided hard constraint projection (HCP): a knowledge-based data-driven scientific machine learning method
• A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic
• Physics-informed neural networks for solving forward and inverse problems in complex beam systems
• DeepMoD: Deep learning for Model Discovery in noisy data
• Physics-informed neural networks of the Saint-Venant equations for downscaling a large-scale river model
• Learning in Sinusoidal Spaces with Physics-Informed Neural Networks
• Predicting Water Temperature Dynamics of Unmonitored Lakes with Meta Transfer Learning
• Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction
• Injecting Knowledge in Data-driven Vehicle Trajectory Predictors
• Capabilities of Deep Learning Models on Learning Physical Relationships: Case of Rainfall-Runoff Modeling with LSTM
• Physics-informed machine learning for Structural Health Monitoring
• Three-dimensional deep learning-based reduced order model for unsteady flow dynamics with variable Reynolds number
• Information fusion and machine learning for sensitivity analysis using physics knowledge and experimental data
• Predicting dark matter halo formation in N-body simulations with deep regression networks
• Physics-guided neural networks for feedforward control with input-to-state stability guarantees
• A Lagrangian Dual-based Theory-guided Deep Neural Network
• PCNN: A physics-constrained neural network for multiphase flows
• Physics-Guided Neural Networks for Feedforward Control: An Orthogonal Projection-Based Approach
• Uncertainty quantification of two-phase flow in porous media via coupled-TgNN surrogate model
• Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying Non-Autonomous Dynamical Systems
• Bridging the Gap: Machine Learning to Resolve Improperly Modeled Dynamics
• Deep Neural Networks to Correct Sub-Precision Errors in CFD
• Generating artificial digital image correlation data using physics-guided adversarial networks
• Composed Physics- and Data-driven System Identification for Non-autonomous Systems in Control Engineering
• Including Physics in Deep Learning -- An example from 4D seismic pressure saturation inversion
• Unifying Model-Based and Neural Network Feedforward: Physics-Guided Neural Networks with Linear Autoregressive Dynamics
• Informed Machine Learning, Centrality, CNN, Relevant Document Detection, Repatriation of Indigenous Human Remains