Predicting MXene Properties via Machine Learning

Abstract

MXenes are a recently discovered class of 2-D materials which possess a diverse set of electrical, chemical, and physical properties, and have a wide range of applications, including batteries, photovoltaics, and chemical sensors. The properties of a given MXene are determined by its chemical composition, and there are likely an infinite number of possible MXenes. Unfortunately, each MXene is costly and time-consuming to synthesize, and there is a need for machine learning (ML) models which can accurately predict MXene properties and guide synthesis of MXenes with desirable properties. To address this issue, we created interpretable ML models that accurately predict the following MXene properties which have not been previously predicted with ML: Work Function, Fermi Level, Heat of Formation, Density of States at Fermi Level (Density of States), and whether a MXene is magnetic. Our model predicts these properties for novel MXenes which have yet to be synthesized in the lab, and does so using only standard elemental information of the constituent atoms of a given MXene material as input. To train our model, we used experimental data from MXenes synthesized in the lab in previous works and data computed using Density Functional Theory (DFT). To create our model, we first applied Sparse Principal Components Analysis (SPCA) to reduce model dimension while preserving the interpretability of features. Then, Random Forest and XGBoost models were created to predict the specified MXene target properties and to output a feature importance score for input features. XGBoost models had the lowest root-mean-squared-error (RMSE) for each target property, with RMSE values as follows: Work Function, 0.308 J; Heat of Formation, 0.128 eV/atom; Fermi Level, 0.46 eV; Density of States, 1.984 eV−1.