Stochastic Physics-Informed Neural Ordinary Differential Equations

Abstract

Stochastic differential equations (SDEs) are used to describe a wide variety of complex stochastic dynamical systems. Learning the hidden physics within SDEs is crucial for unraveling fundamental understanding of these systems' stochastic and nonlinear behavior. We propose a flexible and scalable framework for training artificial neural networks to learn constitutive equations that represent hidden physics within SDEs. The proposed stochastic physics-informed neural ordinary differential equation framework (SPINODE) propagates stochasticity through the known structure of the SDE (i.e., the known physics) to yield a set of deterministic ODEs that describe the time evolution of statistical moments of the stochastic states. SPINODE then uses ODE solvers to predict moment trajectories. SPINODE learns neural network representations of the hidden physics by matching the predicted moments to those estimated from data. Recent advances in automatic differentiation and mini-batch gradient descent with adjoint sensitivity are leveraged to establish the unknown parameters of the neural networks. We demonstrate SPINODE on three benchmark in-silico case studies and analyze the framework's numerical robustness and stability. SPINODE provides a promising new direction for systematically unraveling the hidden physics of multivariate stochastic dynamical systems with multiplicative noise.

References in corpus (15)

• Practical Bayesian Optimization of Machine Learning Algorithms
• Deep learning for time series classification: a review
• B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Analysis of data sets of stochastic systems
• Layering and position-dependent diffusive dynamics of confined fluids
• A Survey of Stochastic Simulation and Optimization Methods in Signal Processing
• Coexistence and Exclusion of Stochastic Competitive Lotka-Volterra Models
• Comment on "Indispensable Finite Time Correlations for Fokker-Planck Equations from Time Series Data"
• Coarse-Grained Kinetic Computations for Rare Events: Application to Micelle Formation
• An Iterative Procedure for the Estimation of Drift and Diffusion Coefficients of Langevin Processes
• Ballistic Phase of Self-Interacting Random Walks
• Pair diffusion, hydrodynamic interactions, and available volume in dense fluids

Cited by in corpus (3)

• Forecasting with an N-dimensional Langevin Equation and a Neural-Ordinary Differential Equation
• Physics-informed time series analysis with Kolmogorov-Arnold Networks under Ehrenfest constraints
• Neural Ordinary Differential Equations for Learning and Extrapolating System Dynamics Across Bifurcations