Physics-separating artificial neural networks for predicting initial stages of Al sputtering and thin film deposition in Ar plasma discharges

TL;DR

This paper introduces physics-separating neural networks that incorporate evolving surface states and defect structures to accurately model plasma-surface interactions during Al sputtering and thin film deposition.

Contribution

It presents a novel machine learning surrogate model that accounts for dynamic surface states and defects, improving fidelity over static models.

Findings

The model accurately describes fundamental sputtering processes.

It can be applied to both simulation and experimental data.

High physical fidelity in plasma-surface interaction modeling.

Abstract

Simulations of Al thin film sputter depositions rely on accurate plasma and surface interaction models. Establishing the latter commonly requires a higher level of abstraction and means to dismiss the fundamental atomic fidelity. Previous works on sputtering processes addressed this issue by establishing machine learning surrogate models, which include a basic surface state (i.e., stoichiometry) as static input. In this work, an evolving surface state and defect structure are introduced to jointly describe sputtering and growth with physics-separating artificial neural networks. The data describing the plasma-surface interactions stem from hybrid reactive molecular dynamics/time-stamped force bias Monte Carlo simulations of Al neutrals and Ar$^+$ ions impinging onto Al(001) surfaces. It is demonstrated that the fundamental processes are comprehensively described by taking the surface state as well as defect structure into account. Hence, a machine learning plasma-surface interaction surrogate model is established that resolves the inherent kinetics with high physical fidelity. The resulting model is not restricted to input from modeling and simulation, but may similarly be applied to experimental input data.