Molecular dynamics study on the role of Ar ions in the sputter deposition of Al thin films

Abstract

Compressive stresses in sputter deposited thin films are generally assumed to be caused by forward sputtered (peened) built-in particles and entrapped working gas atoms. While the former are assumed to be predominant, the effect of the latter on interaction dynamics and thin film properties is scarcely clarified (concurrent or causative). The overlay of the ion bombardment induced processes renders an isolation of their contribution impracticable. This issue is addressed by two molecular dynamics case studies considering the sputter deposition of Al thin films in Ar working gas. First, Ar atoms are fully retained. Second, they are artificially neglected, as implanted Ar atoms are assumed to outgas anyhow and not alter the ongoing dynamics significantly. Both case studies share common particle dose impinging Al(001) surfaces. Ion energies from 3 to 300 eV and [Formula: see text] flux ratios from 0 to 1 are considered. The surface interactions are simulated by hybrid reactive molecular dynamics/force-biased Monte Carlo simulations and characterized in terms of mass density, Ar concentration, biaxial stress, shear stress, ring statistical connectivity profile, Ar gas porosity, Al vacancy density, and root-mean-squared roughness. Implanted Ar atoms are found to form subnanometer sized eventually outgassing clusters for ion energies exceeding 100 eV. They fundamentally govern a variety of surface processes (e.g., forward sputtering/peening) and surface properties (e.g., compressive stresses) in the considered operating regime.

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

“…The considered plasma-surface interactions relate to a previous simulation study investigating the sputter deposition of Al thin films with Ar working gas, and specifically Ar + ion and Al neutral impingement on an Al(100) surface. The evaluation procedure and physical interpretation is detailed in [39]. In summary, hybrid reactive molecular dynamics/timestamped force-biased Monte Carlo (RMD/tfMC) simulations have been conducted to describe individual surface interactions [36][37][38].…”

“…20 different Ar + ion energies E in Ar + are selected from a square root energy axis in the range of 3 to 300 eV. Al neutrals are assumed to be thermalized (k b T = 7 eV) [39]. The particle fluxes from the plasma to the surface are characterized by the descriptors…”

“…for rings with r nodes; ii) The fraction of nodes at the origin of at least one ring with r nodes P N,r ; iii) The fraction of nodes with r sized rings as shortest closed paths P min,r ; iv) The fraction of nodes with r sized rings as longest closed paths P max,r [39,[42][43][44][45]. The defect structure is characterized by the descriptors D = {R C,r , P N,r , P min,r , P max,r } for r ∈ [3,6].…”

“…In this work, the concept of a machine learning surface surrogate model is advanced byamong other aspects -exploiting hybrid reactive molecular dynamics/time-stamped forcebiased Monte Carlo (RMD/tfMC) simulation data of sputtering and deposition of Al thin films with Ar working gas [36][37][38][39]. The manuscript is structured as follows: In Section II the setup depicting the surface interactions is introduced.…”

“…A hypothesis that will be revisited later by trying to derive one from another. The surface state is further characterized by an additional set of surface properties, A s = {Ar gas porosity φ Ar , Al vacancy density N v Al , root mean square roughness R RMS } [39].…”