To main content

Discovering Thermoelectric Materials Using Machine Learning: Insights and Challenges

Abstract

This work involves the use of combined forces of data-driven machine learning models and high fidelity density functional theory for the identification of new potential thermoelectric materials. The traditional method of thermoelectric material discovery from an almost limitless search space of chemical compounds involves expensive and time consuming experiments. In the current work, the density functional theory (DFT) simulations are used to compute the descriptors (features) and thermoelectric characteristics (labels) of a set of compounds. The DFT simulations are computationally very expensive and hence the database is not very exhaustive. With an anticipation that the important features can be learned by machine learning (ML) from the limited database and the knowledge could be used to predict the behavior of any new compound, the current work adds knowledge related to (a) understanding the impact of selection of influence of training/test data, (b) influence of complexity of ML algorithms, and (c) computational efficiency of combined DFT-ML methodology.

Category

Academic article

Client

  • Research Council of Norway (RCN) / 194068
  • Research Council of Norway (RCN) / 269326
  • Research Council of Norway (RCN) / nn2615k
  • Research Council of Norway (RCN) / NN2615K
  • Notur/NorStore / NN2615K

Language

English

Affiliation

  • SINTEF Digital / Mathematics and Cybernetics
  • SINTEF Industry / Sustainable Energy Technology

Year

2018

Published in

Lecture Notes in Computer Science (LNCS)

ISSN

0302-9743

Publisher

Springer

Volume

11139 LNCS

Page(s)

392 - 401

View this publication at Cristin