Page 60 - Read Online

Tang et al. J. Mater. Inf. 2025, 5, 38 Journal of
DOI: 10.20517/jmi.2025.05
Materials Informatics

Research Article Open Access

Effects of nonlinearity and inter-feature coupling in
machine learning studies of Nb alloys with center-

environment features

1,#
1,#
Yuchao Tang , Bin Xiao , Manabu Ihara 2 , Sergei Manzhos 2,* , Yi Liu 1,*
1
Materials Genome Institute, Shanghai Engineering Research Center for Integrated Circuits and Advanced Display Materials,
Shanghai University, Shanghai 200444, China.
2
School of Materials and Chemical Technology, Institute of Science Tokyo, Tokyo 152-8552, Japan.
#
Authors contributed equally.
* Correspondence to: Prof. Yi Liu, Materials Genome Institute, Shanghai Engineering Research Center for Integrated Circuits and
Advanced Display Materials, Shanghai University, 333 Nanchen Road, Shanghai 200444, China. E-mail: yiliu@shu.edu.cn; Dr.
Sergei Manzhos, School of Materials and Chemical Technology, Institute of Science Tokyo, Meguro-ku, Tokyo 152-8552, Japan.
E-mail: Manzhos.s.aa@m.titech.ac.jp
How to cite this article: Tang, Y.; Xiao, B.; Ihara, M.; Manzhos, S.; Liu, Y. Effects of nonlinearity and inter-feature coupling in
machine learning studies of Nb alloys with center-environment features. J. Mater. Inf. 2025, 5, 38. https://dx.doi.org/10.20517/
jmi.2025.05

Received: 19 Feb 2025 First Decision: 24 Mar 2025 Revised: 8 Jun 2025 Accepted: 11 Jun 2025 Published: 18 Jun 2025

Academic Editor: Lei Shen Copy Editor: Pei-Yun Wang Production Editor: Pei-Yun Wang

Abstract
Prediction of materials properties from descriptors of chemical composition and structure with machine learning
(ML) methods has been emerging as a viable approach to materials design and is a major component of the
materials informatics field. However, as both experimental and computed data may be costly, one often has to
work with limited data, which increases the risk of overfitting. Combining various datasets to improve sampling on
the one hand and designing optimal ML models from small datasets on the other, can be used to address this issue.
Center-environment (CE) features were recently introduced and showed promise in predicting formation energies,
structural parameters, band gaps, and adsorption properties of various materials. Here, we consider the prediction
of formation energies of Nb and Nb-Nb Si eutectic alloys substituted with various alloying elements in the Nb and
5 3
Nb Si phases using CE features - a typical alloy system where the data can be naturally divided into subsets based
5 3
on the types of substitutional sites. We explore effects of dataset combination and of the functional form of the
dependence of the target property on the features. We show that combining the subsets, despite the increased
amount of data, can complicate rather than facilitate ML, as different subsets do not increase the density of
sampling but sample different parts of space with different distribution patterns, and also have different optimal

© The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution 4.0
International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, sharing,
adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as
long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and
indicate if changes were made.

www.oaepublish.com/jmi