Data-driven discovery of PDEs in complex datasets

Abstract

Many processes in science and engineering can be described by partial differential equations (PDEs). Traditionally, PDEs are derived by considering first principles of physics to derive the relations between the involved physical quantities of interest. A different approach is to measure the quantities of interest and use deep learning to reverse engineer the PDEs which are describing the physical process. In this paper we use machine learning, and deep learning in particular, to discover PDEs hidden in complex data sets from measurement data. We include examples of data from a known model problem, and real data from weather station measurements. We show how necessary transformations of the input data amounts to coordinate transformations in the discovered PDE, and we elaborate on feature and model selection. It is shown that the dynamics of a non-linear, second order PDE can be accurately described by an ordinary differential equation which is automatically discovered by our deep learning algorithm. Even more interestingly, we show that similar results apply in the context of more complex simulations of the Swedish temperature distribution.

References in corpus (1)

• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations

Cited by in corpus (51)

• B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
• Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
• PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domain
• Physics-informed learning of governing equations from scarce data
• A Deep Collocation Method for the Bending Analysis of Kirchhoff Plate
• Unsupervised discovery of interpretable hyperelastic constitutive laws
• Deep Learning in Deterministic Computational Mechanics
• A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic
• Wavefield reconstruction inversion via physics-informed neural networks
• Solving inverse-PDE problems with physics-aware neural networks
• Deep-learning of Parametric Partial Differential Equations from Sparse and Noisy Data
• A neural network multigrid solver for the Navier-Stokes equations
• Deep-learning based discovery of partial differential equations in integral form from sparse and noisy data
• Discovering Sparse Interpretable Dynamics from Partial Observations
• Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learning
• Physics informed deep learning for computational elastodynamics without labeled data
• Solving Allen-Cahn and Cahn-Hilliard Equations using the Adaptive Physics Informed Neural Networks
• Physics-constrained Deep Learning for Robust Inverse ECG Modeling
• Noise-aware Physics-informed Machine Learning for Robust PDE Discovery
• A Method for Computing Inverse Parametric PDE Problems with Random-Weight Neural Networks
• Data-Driven Finite Elements Methods: Machine Learning Acceleration of Goal-Oriented Computations
• Discovery of partial differential equations from highly noisy and sparse data with physics-informed information criterion
• Physics-informed generative neural network: an application to troposphere temperature prediction
• Data-driven Identification of 2D Partial Differential Equations using extracted physical features
• Data-driven PDE discovery with evolutionary approach
• Parsimony-Enhanced Sparse Bayesian Learning for Robust Discovery of Partial Differential Equations
• Physics-integrated machine learning: embedding a neural network in the Navier-Stokes equations. Part I
• Physics-integrated machine learning: embedding a neural network in the Navier-Stokes equations. Part II
• Improved Surrogate Modeling of Fluid Dynamics with Physics-Informed Neural Networks
• System Identification Through Lipschitz Regularized Deep Neural Networks
• Structure Preservation for the Deep Neural Network Multigrid Solver
• A one-dimensional flow model enhanced by machine learning for simulation of vocal fold vibration
• Solving Irregular and Data-enriched Differential Equations using Deep Neural Networks
• A numerically efficient output-only system-identification framework for stochastically forced self-sustained oscillators
• Multi-objective discovery of PDE systems using evolutionary approach
• Hierarchical Learning to Solve Partial Differential Equations Using Physics-Informed Neural Networks
• Robust Data-Driven Discovery of Partial Differential Equations under Uncertainties
• The data-driven physical-based equations discovery using evolutionary approach
• DynaBench: A benchmark dataset for learning dynamical systems from low-resolution data
• Robust discovery of partial differential equations in complex situations
• Discovery of Governing Equations with Recursive Deep Neural Networks
• Deterministic and statistical calibration of constitutive models from full-field data with parametric physics-informed neural networks
• Deep-Learning Discovers Macroscopic Governing Equations for Viscous Gravity Currents from Microscopic Simulation Data
• Hybrid Scheme of Kinematic Analysis and Lagrangian Koopman Operator Analysis for Short-term Precipitation Forecasting
• Physics-informed Spline Learning for Nonlinear Dynamics Discovery
• A Neural Network Ensemble Approach to System Identification
• Model discovery in the sparse sampling regime
• Fully differentiable model discovery
• Object classification in analytical chemistry via data-driven discovery of partial differential equations
• Paradigm Shift Through the Integration of Physical Methodology and Data Science
• Physics-Coupled Spatio-Temporal Active Learning for Dynamical Systems