Inferring Global Dynamics of a Black-Box System Using Machine Learning

TL;DR

This paper introduces a machine learning approach to uncover the global dynamics of black-box systems from time series data, without needing explicit equations, demonstrated on variable star evolution.

Contribution

The novel method maps the training process of a machine learning model to the target system's dynamics, revealing its properties without explicit equations.

Findings

Successfully inferred the dynamical stages of a variable star

Predicted future evolution of the star based on current data

Demonstrated the method's potential for various black-box systems

Abstract

We present that, instead of establishing the equations of motion, one can model-freely reveal the dynamical properties of a black-box system using a learning machine. Trained only by a segment of time series of a state variable recorded at present parameters values, the dynamics of the learning machine at different training stages can be mapped to the dynamics of the target system along a particular path in its parameter space, following an appropriate training strategy that monotonously decreases the cost function. This path is important, because along that, the primary dynamical properties of the target system will subsequently emerge, in the simple-to-complex order, matching closely the evolution law of certain self-evolved systems in nature. Why such a path can be reproduced is attributed to our training strategy. This particular function of the learning machine opens up a novel way to probe the global dynamical properties of a black-box system without artificially establish the equations of motion, and as such it might have countless applications. As an example, this method is applied to infer what dynamical stages a variable star has experienced and how it will evolve in future, by using the light curve observed presently.