Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems (2020-03-10T00:00:00.000000Z)

TL;DR

A taxonomy of existing techniques that are able to integrate traditional physics-based modeling approaches with state-of-the-art machine learning (ML) techniques is provided, which uncovers knowledge gaps and potential crossovers of methods between disciplines.

Abstract

There is a growing consensus that solutions to complex science and engineering problems require novel methodologies that are able to integrate traditional physics-based modeling approaches with state-of-the-art machine learning (ML) techniques. This article provides a structured overview of such techniques. Application-centric objective areas for which these approaches have been applied are summarized, and then classes of methodologies used to construct physics-guided ML models and hybrid physics-ML frameworks are described. We then provide a taxonomy of these existing techniques, which uncovers knowledge gaps and potential crossovers of methods between disciplines that can serve as ideas for future research.

Authors

J. Willard

2 papers

X. Jia

3 papers

Shaoming Xu

2 papers

TL;DR

Abstract

Authors

References324 items

Characterizing possible failure modes in physics-informed neural networks

Physical Equation Discovery Using Physics-Consistent Neural Network (PCNN) Under Incomplete Observability

CIRA Guide to Custom Loss Functions for Neural Networks in Environmental Sciences - Version 1

Physics-Informed Neural Networks for Heat Transfer Problems

Deep neural network enabled corrective source term approach to hybrid analysis and modeling

Physics-informed machine learning

Physics-informed neural networks (PINNs) for fluid mechanics: a review

Anatomy-aided deep learning for medical image segmentation: a review

A High-Efficient Hybrid Physics-Informed Neural Networks Based on Convolutional Neural Network

Using Machine Learning to Develop a Predictive Understanding of the Impacts of Extreme Water Cycle Perturbations on River Water Quality

Injecting Knowledge in Data-driven Vehicle Trajectory Predictors

Physics-informed machine learning: case studies for weather and climate modelling

Using physics-informed enhanced super-resolution generative adversarial networks for subfilter modeling in turbulent reactive flows

Physics-Guided Recurrent Graph Model for Predicting Flow and Temperature in River Networks

Quadratic Residual Networks: A New Class of Neural Networks for Solving Forward and Inverse Problems in Physics Involving PDEs

Understanding and Mitigating Gradient Flow Pathologies in Physics-Informed Neural Networks

Physics guided machine learning using simplified theories

Deep Learned Process Parameterizations Provide Better Representations of Turbulent Heat Fluxes in Hydrologic Models

Recent developments in fast and scalable inverse modeling and data assimilation methods in hydrology

Solution of Biharmonic Equation in Complicated Geometries With Physics Informed Extreme Learning Machine

A Climate Downscaling Deep Learning Model considering the Multiscale Spatial Correlations and Chaos of Meteorological Events

AI Poincaré: Machine Learning Conservation Laws from Trajectories

Predicting Water Temperature Dynamics of Unmonitored Lakes With Meta‐Transfer Learning

Graph-based Reinforcement Learning for Active Learning in Real Time: An Application in Modeling River Networks

Unlocking Inverse Problems Using Deep Learning: Breaking Symmetries in Phase Retrieval

Fourier Neural Operator for Parametric Partial Differential Equations

A Physics-Informed Machine Learning Approach for Solving Heat Transfer Equation in Advanced Manufacturing and Engineering Applications

Predicting lake surface water phosphorus dynamics using process-guided machine learning

Obstacle segmentation based on the wave equation and deep learning

A Survey of Constrained Gaussian Process Regression: Approaches and Implementation Challenges

Inductive Graph Neural Networks for Spatiotemporal Kriging

Inverse-designed spinodoid metamaterials

Deep Shape from Polarization

Deep learning of physical laws from scarce data

MESHFREEFLOWNET: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework

First-principles machine learning modelling of COVID-19

Accelerating Physics-Informed Neural Network Training with Prior Dictionaries

Driven by Data or Derived Through Physics? A Review of Hybrid Physics Guided Machine Learning Techniques With Cyber-Physical System (CPS) Focus

Multiresolution Convolutional Autoencoders

Model order reduction assisted by deep neural networks (ROM-net)

Kriging Convolutional Networks

Inverse Problems, Deep Learning, and Symmetry Breaking

B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data

Forecasting Sequential Data using Consistent Koopman Autoencoders

Fusing Physics-based and Deep Learning Models for Prognostics

A theory-guided deep-learning formulation and optimization of seismic waveform inversion

Embedding Hard Physical Constraints in Convolutional Neural Networks for 3D Turbulence

Enforcing Physical Constraints in CNNs through Differentiable PDE Layer

Metaheuristic-based inverse design of materials – A survey

A Comprehensive Survey on Geometric Deep Learning

Incorporating Symmetry into Deep Dynamics Models for Improved Generalization

A Review of Convolutional Neural Networks

Physics-Guided Deep Neural Networks for Power Flow Analysis

Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profiles

TDEFSI

Building high accuracy emulators for scientific simulations with deep neural architecture search

Physics-Informed Neural Networks for Bias Compensation in Corrosion-Fatigue

PhyNet: Physics Guided Neural Networks for Particle Drag Force Prediction in Assembly

The Atmospheric River Tracking Method Intercomparison Project (ARTMIP): Quantifying Uncertainties in Atmospheric River Climatology

Systems biology informed deep learning for inferring parameters and hidden dynamics

Deep Density: circumventing the Kohn-Sham equations via symmetry preserving neural networks

Multiscale Modeling Meets Machine Learning: What Can We Learn?

Physics-induced graph neural network: An application to wind-farm power estimation

Evaluation and machine learning improvement of global hydrological model-based flood simulations

Machine learning for molecular simulation

Physics-Guided Architecture (PGA) of Neural Networks for Quantifying Uncertainty in Lake Temperature Modeling

Process‐Guided Deep Learning Predictions of Lake Water Temperature

Bringing automated, remote‐sensed, machine learning methods to monitoring crop landscapes at scale

Highly-Ccalable, Physics-Informed GANs for Learning Solutions of Stochastic PDEs

Integrating machine learning and multiscale modeling—perspectives, challenges, and opportunities in the biological, biomedical, and behavioral sciences

ConvPDE-UQ: Convolutional neural networks with quantified uncertainty for heterogeneous elliptic partial differential equations on varied domains

Hamiltonian Generative Networks

Symplectic Recurrent Neural Networks

Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control

Blending Diverse Physical Priors with Neural Networks

PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEs