Prediction of Pressure-Composition-Temperature Curves of AB2-Type Hydrogen Storage Alloys by Machine Learning

Jeong Min Kim, Taejun Ha, Joonho Lee, Young Su Lee, Jae Hyeok Shim

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)


Pressure-composition-temperature (PCT) curves for hydrogen absorption and desorption of AB2-type hydrogen storage alloys at arbitrary temperatures are predicted by three machine learning models such as random forest, K-nearest neighbor and deep neural network (DNN). Two data generation methods are adopted to increase the number of data points. A new form of the PCT curve functions is suggested to fit experimental data, which greatly helps improve the prediction accuracy. A van’t Hoff type equation is used to generate unmeasured temperature data, which improves the model performance on the PCT behavior at various temperatures. The results indicate that a DNN is the best model for predicting the PCT behavior with a high average correlation value R2 = 0.93070. Graphical Abstract: [Figure not available: see fulltext.]

Original languageEnglish
Pages (from-to)861-869
Number of pages9
JournalMetals and Materials International
Issue number3
Publication statusPublished - 2023 Mar

Bibliographical note

Funding Information:
This study has been supported by the KIST Institutional Program (Project No. 2E31851) and the Energy Technology Development Program (Project No. 20213030040400) funded by the Ministry of Trade, Industry and Energy of Korea.

Publisher Copyright:
© 2022, The Author(s) under exclusive licence to The Korean Institute of Metals and Materials.


  • Deep neural network
  • Hydrogen sorption
  • Hydrogen storage alloy
  • Machine learning
  • Pressure-composition-temperature curve

ASJC Scopus subject areas

  • Condensed Matter Physics
  • Mechanics of Materials
  • Metals and Alloys
  • Materials Chemistry


Dive into the research topics of 'Prediction of Pressure-Composition-Temperature Curves of AB2-Type Hydrogen Storage Alloys by Machine Learning'. Together they form a unique fingerprint.

Cite this