Machine learning based prediction of metal hydrides for hydrogen storage, part I: Prediction of hydrogen weight percent

Alireza Rahnama, Guilherme Zepon, Seetharaman Sridhar

Research output: Contribution to journalArticlepeer-review

11 Scopus citations

Abstract

The openly available database provided by the US Department of Energy on hydrides for hydrogen storage were analyzed through supervised machine learning to rank features in terms of their importance for determining hydrogen storage capacity referred to as hydrogen weight percent. In this part: we employed four models, namely linear regression, neural network, Bayesian linear regression and boosted decision tree to predict the hydrogen weight percent. For each algorithm, the scored labels were compared to the actual values of hydrogen weight percent. Our investigation showed that boosted decision tree regression performed better than the other algorithms achieving a coefficient of determination of 0.83.

Original languageEnglish (US)
Pages (from-to)7337-7344
Number of pages8
JournalInternational Journal of Hydrogen Energy
Volume44
Issue number14
DOIs
StatePublished - Mar 15 2019
Externally publishedYes

Keywords

  • Artificial intelligence
  • Hydrogen storage materials
  • Machine-learning
  • Metal hydrides

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Fuel Technology
  • Condensed Matter Physics
  • Energy Engineering and Power Technology

Fingerprint

Dive into the research topics of 'Machine learning based prediction of metal hydrides for hydrogen storage, part I: Prediction of hydrogen weight percent'. Together they form a unique fingerprint.

Cite this