Learning Mean-Field Equations from Particle Data Using WSINDy

Abstract

We develop a weak-form sparse identification method for interacting particle systems (IPS) with the primary goals of reducing computational complexity for large particle number $N$ and offering robustness to either intrinsic or extrinsic noise. In particular, we use concepts from mean-field theory of IPS in combination with the weak-form sparse identification of nonlinear dynamics algorithm (WSINDy) to provide a fast and reliable system identification scheme for recovering the governing stochastic differential equations for an IPS when the number of particles per experiment $N$ is on the order of several thousand and the number of experiments $M$ is less than 100. This is in contrast to existing work showing that system identification for $N$ less than 100 and $M$ on the order of several thousand is feasible using strong-form methods. We prove that under some standard regularity assumptions the scheme converges with rate $\mathcal{O}(N^{-1/2})$ in the ordinary least squares setting and we demonstrate the convergence rate numerically on several systems in one and two spatial dimensions. Our examples include a canonical problem from homogenization theory (as a first step towards learning coarse-grained models), the dynamics of an attractive-repulsive swarm, and the IPS description of the parabolic-elliptic Keller-Segel model for chemotaxis.

References in corpus (6)

• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• A mean-field limit for certain deep neural networks
• Extracting Governing Laws from Sample Path Data of Non-Gaussian Stochastic Dynamical Systems
• Learning interaction kernels in mean-field equations of 1st-order systems of interacting particles
• Parameter Estimation for the McKean-Vlasov Stochastic Differential Equation
• Learning particle swarming models from data with Gaussian processes

Cited by in corpus (10)

• Direct Estimation of Parameters in ODE Models Using WENDy: Weak-form Estimation of Nonlinear Dynamics
• Data-driven discovery and extrapolation of parameterized pattern-forming dynamics
• Learning Anisotropic Interaction Rules from Individual Trajectories in a Heterogeneous Cellular Population
• Learning fluid physics from highly turbulent data using sparse physics-informed discovery of empirical relations (SPIDER)
• Random walk models in the life sciences: including births, deaths and local interactions
• Physics-informed active learning with simultaneous weak-form latent space dynamics identification
• Weak Collocation Regression method: fast reveal hidden stochastic dynamics from high-dimensional aggregate data
• Forecasting and predicting stochastic agent-based model data with biologically-informed neural networks
• Online Weak-form Sparse Identification of Partial Differential Equations
• Sparse identification of effective microparticle interaction potential in dusty plasma from simulation data