Deep learning of electrochemical CO2 conversion literature reveals research trends and directions

Jiwoo Choi, Kihoon Bang, Suji Jang, Jaewoong Choi, Juanita Ordonez, David Buttler, Anna Hiszpanski, T. Yong-Jin Han, Seok Su Sohn, Byungju Lee, Kwang Ryeol Lee, Sang Soo Han, Donghun Kim

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)

Abstract

Large-scale and openly available material science databases are mainly composed of computer simulation results rather than experimental data. Some examples include the Materials Project, Open Quantum Materials Database, and Open Catalyst 2022. Unfortunately, building large-scale experimental databases remains challenging due to the difficulties in consolidating locally distributed datasets. In this work, focusing on the catalysis literature of CO2 reduction reactions (CO2RRs), we present a machine learning (ML)-based protocol for selecting highly relevant papers and extracting important experimental data. First, we report a document embedding method (Doc2Vec) for collecting papers of greatest relevance to the specific target domain, which yielded 3154 CO2RR-related papers from six publishers. Next, we developed named entity recognition (NER) models to extract twelve entities related to material names (catalyst, electrolyte, etc.) and catalytic performance (Faradaic efficiency, current density, etc.). Among several tested models, the MatBERT-based approach achieved the highest accuracy, with an average F1-score of 90.4% and an F1-score of 95.2% in a boundary relaxation evaluation scheme. The accurate and accelerated NER-based data extraction from a large volume of catalysis literature enables temporal trend analyses of the CO2RR catalysts, products, and performances, revealing the potentially effective material space in CO2RRs. While this work demonstrates the effectiveness of our ML-based text mining methods for specifically CO2RR literature, the methods and approach are applicable to and may be used to accelerate the development of other catalytic chemical reactions.

Original languageEnglish
Pages (from-to)17628-17643
Number of pages16
JournalJournal of Materials Chemistry A
Volume11
Issue number33
DOIs
Publication statusPublished - 2023 Jul 19

Bibliographical note

Funding Information:
This work was supported by the National Center for Materials Research Data (NCMRD) through the National Research Foundation of Korea funded by the Ministry of Science and ICT (NRF-2021M3A7C2089739) and KIST institutional projects (2E32531 and 2E32533). This work was performed under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344 and was supported by the LLNL-LDRD Program Under Project No. 22-ERD-027. LLNL-JRNL-846352.

Publisher Copyright:
© 2023 The Royal Society of Chemistry.

ASJC Scopus subject areas

  • General Chemistry
  • Renewable Energy, Sustainability and the Environment
  • General Materials Science

Fingerprint

Dive into the research topics of 'Deep learning of electrochemical CO2 conversion literature reveals research trends and directions'. Together they form a unique fingerprint.

Cite this