# Application of Machine Learning Techniques in the Prediction of Surface Geometry

## TL;DR

This paper explores using machine learning to predict the geometry of a superhard coating material, combining ML with statistical methods to model complex surface patterns.

## Contribution

A novel hybrid model combining RNNs and Monte Carlo simulation is proposed for generating surface geometries, overcoming limitations of traditional statistical approaches.

## Key findings

- ML–stochastic hybrids effectively capture deterministic structures and random fluctuations in surface geometry.
- The proposed model demonstrates effectiveness in generating digital surfaces with similar geometry parameters.
- High computational demands and interpretability challenges are identified as key limitations of ML-based approaches.

## Abstract

The article presents an attempt by the authors to generate a digital representation of the analyzed surface layer of WC-Co-Al2O3 coating deposited by the ESD method. The WC-Co-Al2O3 surface layer is superhard and abrasion-resistant, significantly increasing the exploitation time of working elements. The authors aim to develop a method for generating series of digital surfaces with similar geometry parameters based on data collected through profilometric analysis. Therefore, the advanced integration of machine learning (ML) techniques with classical statistical approaches for modeling and predicting stochastic processes. While traditional models such as ARMA/ARIMA and hidden Markov models (HMMs) offer mathematical rigor, they often impose assumptions of stationarity and linearity, which limits their application to complex, noisy data. This paper proposes a model for surface geometry generation based on experimental data that combines recurrent neural networks (RNNs) and Monte Carlo simulation. Additionally, the study reviews emerging methods, including generative adversarial networks (GANs) for stochastic simulation and expectation-maximization (EM) algorithms for parameter estimation. An empirical case study on WC-Co-AL2O3 surface geometries demonstrates the effectiveness of ML–stochastic hybrids in capturing both deterministic structures and random fluctuations. The findings underscore not only the benefits but also the limitations of such models, including high computational demands and interpretability challenges, while proposing future research directions toward physics-informed ML and explainable AI.