# Hardness Prediction of MoNbTaW Alloy Films Based on Machine Learning and Interpretability Analysis

## TL;DR

This paper uses machine learning to predict the hardness of a complex alloy film and identifies key factors influencing its performance.

## Contribution

A novel ML framework using ridge regression and three optimized features for accurate hardness prediction in MoNbTaW HEA films.

## Key findings

- The ML model achieved high accuracy with R2 of 0.86 in cross-validation and 0.88 on the validation set.
- Three physical features (δG, Λ, and Ω) were identified as most predictive of hardness in MoNbTaW alloy films.
- The model reveals how constituent elements and features influence hardness, aiding HEA design.

## Abstract

Machine learning (ML) offers a powerful paradigm for accelerating performance prediction of high-entropy alloys (HEAs). The present study proposed an ML framework based on the ridge regression algorithm for predicting the hardness of MoNbTaW HEA films. By comparing various feature-screening strategies, an optimized feature set comprising three features, namely δG, Λ, and Ω, was selected from 20 candidate physical features. The model based on this feature set exhibited strong predictive performance. In 10-fold cross-validation, R2 was 0.86, RMSE was 0.41 GPa and MAE was 0.31 GPa. On the reserved validation set, R2 was 0.88, RMSE was 0.37 GPa, and MAE was 0.31 GPa. The model further revealed the influence trends of constituent elements and key features on hardness. By using ML to mine useful information from a dataset of HEA film samples prepared via magnetron sputtering, this work provides an approach for rapid and cost-effective design of HEAs.