A machine learning based Bayesian optimization solution to nonlinear responses in dusty plasmas

TL;DR

This paper introduces a machine learning approach utilizing Bayesian optimization to efficiently determine the equations of motion for dust particles in plasmas, effectively matching simulated and experimental nonlinear response data.

Contribution

It presents a novel machine learning-based Bayesian optimization method for nonlinear response analysis in dusty plasmas, improving parameter estimation efficiency.

Findings

Efficient parameter optimization for nonlinear plasma responses

Accurate matching of simulated and experimental nonlinear curves

Enhanced understanding of plasma-grain interactions

Abstract

Nonlinear frequency response analysis is a widely used method for determining system dynamics in the presence of nonlinearities. In dusty plasmas, the plasma-grain interaction (e.g., grain charging fluctuations) can be characterized by a single particle nonlinear response analysis, while grain-grain nonlinear interactions can be determined by a multi-particle nonlinear response analysis. Here, a machine learning-based method to determine the equation of motion in the nonlinear response analysis for dust particles in plasmas is presented. Searching the parameter space in a Bayesian manner allows an efficient optimization of the parameters needed to match simulated nonlinear response curves to experimentally measured nonlinear response curves.