Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learning

TL;DR

This paper introduces a physics-informed self-supervised learning approach to infer energy landscapes from system trajectories, enabling accurate energy estimation and evolution prediction without true energy labels.

Contribution

It proposes a novel method combining adaptive codebooks and graph neural Fokker-Planck equations for joint energy estimation and system evolution prediction.

Findings

Energy estimation correlates with ground truth above 0.9

Evolution prediction accuracy exceeds baseline by 17.65%

Method applicable across interdisciplinary systems

Abstract

Energy landscapes play a crucial role in shaping dynamics of many real-world complex systems. System evolution is often modeled as particles moving on a landscape under the combined effect of energy-driven drift and noise-induced diffusion, where the energy governs the long-term motion of the particles. Estimating the energy landscape of a system has been a longstanding interdisciplinary challenge, hindered by the high operational costs or the difficulty of obtaining supervisory signals. Therefore, the question of how to infer the energy landscape in the absence of true energy values is critical. In this paper, we propose a physics-informed self-supervised learning method to learn the energy landscape from the evolution trajectories of the system. It first maps the system state from the observation space to a discrete landscape space by an adaptive codebook, and then explicitly integrates energy into the graph neural Fokker-Planck equation, enabling the joint learning of energy estimation and evolution prediction. Experimental results across interdisciplinary systems demonstrate that our estimated energy has a correlation coefficient above 0.9 with the ground truth, and evolution prediction accuracy exceeds the baseline by an average of 17.65\%. The code is available at github.com/tsinghua-fib-lab/PESLA.