View in EDS

Elemental frequency-based supervised classification approach for the search of novel topological materials.

Saved in:

Bibliographic Details
Title:	Elemental frequency-based supervised classification approach for the search of novel topological materials.
Authors:	Ralte, Zodinpuia¹ (AUTHOR), Kumar, Ramesh¹ (AUTHOR), Singh, Mukhtiyar¹ (AUTHOR) msphysik09@gmail.com
Source:	Modelling & Simulation in Materials Science & Engineering. 2026, Vol. 34 Issue 3, p1-16. 16p.
Subjects:	Supervised learning, Materials science, Support vector machines, Topological insulators, Machine learning, Random forest algorithms
Abstract:	The machine learning (ML) based approaches efficiently solve the goal of searching the best materials candidate for the targeted properties. The search for topological materials (TMs) using traditional first-principles and symmetry-based methods often require lots of computing power or is limited by the crystalline symmetries. In this study, we present frequency-based statistical descriptors for ML-driven TM's classification that is independent of crystallographic symmetry of wave functions. This approach predicts the topological nature of a material based on its chemical formula. With a balanced dataset of 3880 materials, we have achieved classification accuracies of 82% with the support vector machine model and 83% with the random forest model, where both models have trained on common frequency based features. We have verified the performances of the models using 5-fold cross-validation approach. Moreover, we have validated the models on a dataset of unseen binary compounds and have efficiently identified 22 common materials using both the models. Next, we used the first-principles approach to provide preliminary evidence for the topological candidates via band inversions at time-reversal invariant momenta points. Therefore, we have demonstrated that the implications of frequency-based descriptors is a practical and less complex way to find novel TMs with certain physical post-processing filters. This approach lays the groundwork for scalable, data-driven topological property screening of complex materials. [ABSTRACT FROM AUTHOR]
	Copyright of Modelling & Simulation in Materials Science & Engineering is the property of IOP Publishing and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	The machine learning (ML) based approaches efficiently solve the goal of searching the best materials candidate for the targeted properties. The search for topological materials (TMs) using traditional first-principles and symmetry-based methods often require lots of computing power or is limited by the crystalline symmetries. In this study, we present frequency-based statistical descriptors for ML-driven TM's classification that is independent of crystallographic symmetry of wave functions. This approach predicts the topological nature of a material based on its chemical formula. With a balanced dataset of 3880 materials, we have achieved classification accuracies of 82% with the support vector machine model and 83% with the random forest model, where both models have trained on common frequency based features. We have verified the performances of the models using 5-fold cross-validation approach. Moreover, we have validated the models on a dataset of unseen binary compounds and have efficiently identified 22 common materials using both the models. Next, we used the first-principles approach to provide preliminary evidence for the topological candidates via band inversions at time-reversal invariant momenta points. Therefore, we have demonstrated that the implications of frequency-based descriptors is a practical and less complex way to find novel TMs with certain physical post-processing filters. This approach lays the groundwork for scalable, data-driven topological property screening of complex materials. [ABSTRACT FROM AUTHOR]
ISSN:	09650393
DOI:	10.1088/1361-651X/ae4b5d