An efficient plasma-surface interaction surrogate model for sputtering processes based on autoencoder neural networks

TL;DR

This paper introduces a streamlined machine learning surrogate model for sputtering processes that uses autoencoder neural networks to efficiently capture complex plasma-surface interactions with fewer parameters.

Contribution

It develops a convolutional variational autoencoder combined with a regression network, significantly reducing model complexity while accurately representing sputtering dynamics.

Findings

Reduced model parameters to 486, enhancing efficiency.

Achieved competitive performance with fewer degrees of freedom.

Method is adaptable to more complex physical models.

Abstract

Simulations of thin film sputter deposition require the separation of the plasma and material transport in the gas-phase from the growth/sputtering processes at the bounding surfaces. Interface models based on analytic expressions or look-up tables inherently restrict this complex interaction to a bare minimum. A machine learning model has recently been shown to overcome this remedy for Ar ions bombarding a Ti-Al composite target. However, the chosen network structure (i.e., a multilayer perceptron) provides approximately 4 million degrees of freedom, which bears the risk of overfitting the relevant dynamics and complicating the model to an unreliable extend. This work proposes a conceptually more sophisticated but parameterwise simplified regression artificial neural network for an extended scenario, considering a variable instead of a single fixed Ti-Al stoichiometry. A convolutional $\beta$-variational autoencoder is trained to reduce the high-dimensional energy-angular distribution of sputtered particles to a latent space representation of only two components. In addition to a primary decoder which is trained to reconstruct the input energy-angular distribution, a secondary decoder is employed to reconstruct the mean energy of incident Ar ions as well as the present Ti-Al composition. The mutual latent space is hence conditioned on these quantities. The trained primary decoder of the variational autoencoder network is subsequently transferred to a regression network, for which only the mapping to the particular latent space has to be learned. While obtaining a competitive performance, the number of degrees of freedom is drastically reduced to 15,111 and 486 parameters for the primary decoder and the remaining regression network, respectively. The underlying methodology is general and can easily be extended to more complex physical descriptions with a minimal amount of data required.