Bayesian optimization for stable properties amid processing fluctuations in sputter deposition

TL;DR

This paper presents a Bayesian optimization method to efficiently identify sputter deposition parameters that produce molybdenum thin films with targeted residual stress and resistance, while reducing sensitivity to process fluctuations.

Contribution

The study introduces a Bayesian optimization framework tailored for sputter deposition, incorporating prior knowledge to enhance robustness against stochastic variations in thin film properties.

Findings

Bayesian optimization successfully finds optimal process parameters.

The method reduces susceptibility of films to stochastic fluctuations.

It achieves desired residual stress and resistance in fewer experiments.

Abstract

We introduce a Bayesian optimization approach to guide the sputter deposition of molybdenum thin films, aiming to achieve desired residual stress and sheet resistance while minimizing susceptibility to stochastic fluctuations during deposition. Thin films are pivotal in numerous technologies, including semiconductors and optical devices, where their properties are critical. Sputter deposition parameters, such as deposition power, vacuum chamber pressure, and working distance, influence physical properties like residual stress and resistance. Excessive stress and high resistance can impair device performance, necessitating the selection of optimal process parameters. Furthermore, these parameters should ensure the consistency and reliability of thin film properties, assisting in the reproducibility of the devices. However, exploring the multidimensional design space for process optimization is expensive. Bayesian optimization is ideal for optimizing inputs/parameters of general black-box functions without reliance on gradient information. We utilize Bayesian optimization to optimize deposition power and pressure using a custom-built objective function incorporating observed stress and resistance data. Additionally, we integrate prior knowledge of stress variation with pressure into the objective function to prioritize films least affected by stochastic variations. Our findings demonstrate that Bayesian optimization effectively explores the design space and identifies optimal parameter combinations meeting desired stress and resistance specifications.