TY - GEN A1 - Gergs, Tobias A1 - Borislavov, Borislav A1 - Trieschmann, Jan T1 - Efficient plasma-surface interaction surrogate model for sputtering processes based on autoencoder neural networks T2 - Journal of Vacuum Science & Technology. B N2 - 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 (e.g., substrate and target). 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, MLP) provides approximately 4×106 degrees of freedom, which bears the risk of overfitting the relevant dynamics and complicating the model to an unreliable extent. 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 𝛽-variational autoencoder is trained to reduce the high-dimensional energy-angular distribution of sputtered particles to a low-dimensional latent representation with only two components. In addition to a primary decoder that 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 low-dimensional space has to be learned. While obtaining a competitive performance, the number of degrees of freedom is drastically reduced to 15 111 (0.378% of the MLP) and 486 (0.012% of the MLP) parameters for the primary decoder and the remaining regression network, respectively. The underlying methodology is very general and can easily be extended to more complex physical descriptions (e.g., taking into account dynamical surface properties) with a minimal amount of data required. Y1 - 2022 U6 - https://doi.org/10.1116/6.0001485 SN - 2166-2754 VL - 40 IS - 1 SP - 012802-1 EP - 012802-15 ER - TY - GEN A1 - Gergs, Tobias A1 - Dirkmann, Sven A1 - Mussenbrock, Thomas T1 - Integration of external electric fields in molecular dynamics simulation models for resistive switching devices T2 - Journal of Applied Physics Y1 - 2018 U6 - https://doi.org/10.1063/1.5029877 SN - 0021-8979 SN - 1089-7550 VL - 123 IS - 24 ER - TY - GEN A1 - Schmidt, Frederik A1 - Trieschmann, Jan A1 - Gergs, Tobias A1 - Mussenbrock, Thomas T1 - A generic method for equipping arbitrary rf discharge simulation frameworks with external lumped element circuits T2 - Journal of Applied Physics Y1 - 2019 U6 - https://doi.org/10.1063/1.5091965 SN - 1089-7550 SN - 0021-8979 VL - 125 IS - 17 SP - 173106 ER - TY - GEN A1 - Krüger, Florian A1 - Gergs, Tobias A1 - Trieschmann, Jan T1 - Machine learning plasma-surface interface for coupling sputtering and gas-phase transport simulations T2 - Plasma Sources Science and Technology Y1 - 2019 U6 - https://doi.org/10.1088/1361-6595/ab0246 SN - 1361-6595 SN - 0963-0252 VL - 28 IS - 3 ER -