Detecting Stochastic Governing Laws with Observation on Stationary Distributions
arXiv:2302.08036 · doi:10.1016/j.physd.2023.133691
Abstract
Mathematical models for complex systems are often accompanied with uncertainties. The goal of this paper is to extract a stochastic differential equation governing model with observation on stationary probability distributions. We develop a neural network method to learn the drift and diffusion terms of the stochastic differential equation. We introduce a new loss function containing the Hellinger distance between the observation data and the learned stationary probability density function. We discover that the learnt stochastic differential equation provides a fair approximation of the data-driven dynamical system after minimizing this loss function during the training method. The effectiveness of our method is demonstrated in numerical experiments.
arXiv comment52 figures
References in corpus (8)
- Observation of scale invariance and universality in two-dimensional Bose gases
- Sparse learning of stochastic dynamic equations
- Solving Fokker-Planck equation using deep learning
- A Data-Driven Approach for Discovering Stochastic Dynamical Systems with Non-Gaussian Levy Noise
- Approximate Bayes learning of stochastic differential equations
- Discovering mean residence time and escape probability from data of stochastic dynamical systems
- Variational estimation of the drift for stochastic differential equations from the empirical density
- Optimal Transport for Parameter Identification of Chaotic Dynamics via Invariant Measures