Machine learning models for predicting density of sodium-ion battery materials

¹ Department of Physics, University of Limpopo, Private bag x 1106, Sovenga, 0727, South Africa
² Next Generation Enterprises and Institutions, Council for Scientific and Industrial Research, P.O. Box 395, Pretoria, 0001, South Africa
³ National Institute for Theoretical and Computational Sciences, NITheCS, Gauteng, 2000, South Africa

^* Corresponding author: mabelkmonareng@gmail.com

Abstract

With the unprecedented amounts of material data generated from high-throughput density functional theory, machine learning provides the ability to accelerate the discovery and design of new materials. In this work, machine learning regression techniques are applied to a large amount of data from Materials Project Database, to develop machine learning models capable of accurately predicting the densities of sodium-ion battery cathode materials. Different machine learning regression models are successfully developed and validated. Feature vectors derived from the properties of materials’ chemical compounds are evaluated. Extra trees regressor model is found to be the best model in predicting the density with an accuracy of 0.95 and 0.09 g/cm³ coefficient of determination and mean square error, respectively.