A Machine Learning (Bayesian Optimization) Based Solution to the Nonlinear Response Analysis in Dusty Plasma .
ORAL
Abstract
A machine learning based method for solving nonlinear response analysis for a single dust particle inside the plasma sheath of a complex plasma is presented. By matching the simulated response curves (both primary response and secondary response) to the corresponding experimentally measured counterparts in a Bayesian manner, the parameters characterizing the plasma environment can be derived efficiently. It will be shown that a correction to the parameters of higher order nonlinearities derived from perturbation method is indicated by this numerical method..
* This material is based upon work supported by the National Science Foundation and NASA under NSF Grants No. 1740203 and 1707215, NASA contract 1571701 and JPL subcontract 1647194.
–
Authors
-
Zhiyue Ding
CASPER, Baylor University
-
Truell Hyde
Baylor University, CASPER, Baylor University