Infer dynamics in experimental dusty plasma trajectories by machine learning

Advanced machine learning models have been developed to infer governing equations from time series, but they are mostly tested on simulated data since experimental data are not labeled. Additionally, experimental data may involve drift and non-Gaussian noise, which is difficult to simulate. To bridge this divide, we benchmark the prediction of simple machine learning models using the stochastic motion of micron-sized dust particles levitated in a plasma. The particles often experience conservative and non-conservative complex forces which are not well-understood. Importantly, we label the data using an alternative experimental method involving mechanical perturbation. In experiments with a single particle, machine learning predicts the forces as precisely as in simulated data. Experiments with many particles reveal the interaction force, which is related to the particle charge and plasma Debye length, and are difficult to measure in-situ. Nevertheless, our results show that machine learning can accurately predict the system parameters when the digitally-imaged random motion of the particles is less than 2 pixels.