A first-principles study of ternary metal chalcogenides <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si21.svg" display="inline" id="d1e1775"><mml:mrow><mml:mi mathvariant="normal">Ba</mml:mi><mml:mn>2</mml:mn><mml:mi mathvariant="normal">MnX</mml:mi><mml:mn>3</mml:mn></mml:mrow></mml:math> <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si22.svg" display="inline" id="d1e1787"><mml:mrow><mml:mo>(</mml:mo><mml:mi mathvariant="normal">X</mml:mi><mml:mo linebreak="goodbreak

Rakshit, Medha; Chowdhury, Suman; Majumdar, Arnab; Banerjee, Dipali; Jana, Debnarayan

doi:10.1016/j.commatsci.2023.112526

Cited by 5 publications

(1 citation statement)

References 94 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a work by Ghosal et al [26], tetragonal monolayers of group-V elements (T-Sb, T-P, T-As and T-Bi) have been used to train machine learned potentials by generating datasets depicting forces, stresses, coordinates and energy at each image of the AIMD simulation which has been used to predict phonon bandstructure, phonon density of states and thermoelectric properties of the materials taken in their study. Similar studies on Ba 2 MnSe 3 and germanium sulfide using ML approach and semiclassical Boltzmann transport equation provided results of thermoelectric figure of merit ∼0.74 and 0.73 respectively at 700 K [27,28].…”

Section: Introductionmentioning

confidence: 56%

Bandgap prediction of non-metallic crystals through machine learning approach

Barman,

Dua,

Sarkar

2024

J. Phys.: Condens. Matter

View full text Add to dashboard Cite

The determination of bandgap is the heart of electronic structure of any material and is a crucial factor for thermoelectric performance of it. Due to large amount to data (features) that are related to bandgap are now a days available, it is possible to make use of machine learning approach to predict the bandgap of the material. The study commences by selecting the feature through Pearson correlation study between bandgap and various thermoelectric parameters in non-metallic crystals. Among the forty two parameters available in the dataset, the seebeck coefficient and its corresponding temperatures show high correlation with the bandgap. With these three selected features we have used different machine learning models like multilinear regression, polynomial regression, random forest regression, support vector regression to predict the bandgap. Amongst the different machine learning models considered, random forest regression outperforms the other models to predict the bandgap with R2 value of 97.55 % between actual bandgap and predicted bandgap.

show abstract

Section: Introductionmentioning

confidence: 56%