Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning
In the past several years, Materials Genome Initiative (MGI) efforts have produced myriad examples of computationally designed materials in the fields of energy storage, catalysis, thermoelectrics, and hydrogen storage as well as large data resources that are used to screen for potentially transform...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
American Chemical Society (ACS)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/129530 |
| _version_ | 1826205984229425152 |
|---|---|
| author | Kim, Edward Huang, Kevin Joon-Ming Saunders, Adam McCallum, Andrew Ceder, Gerbrand Olivetti, Elsa A. |
| author2 | Massachusetts Institute of Technology. Department of Materials Science and Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Materials Science and Engineering Kim, Edward Huang, Kevin Joon-Ming Saunders, Adam McCallum, Andrew Ceder, Gerbrand Olivetti, Elsa A. |
| author_sort | Kim, Edward |
| collection | MIT |
| description | In the past several years, Materials Genome Initiative (MGI) efforts have produced myriad examples of computationally designed materials in the fields of energy storage, catalysis, thermoelectrics, and hydrogen storage as well as large data resources that are used to screen for potentially transformative compounds. The bottleneck in high-Throughput materials design has thus shifted to materials synthesis, which motivates our development of a methodology to automatically compile materials synthesis parameters across tens of thousands of scholarly publications using natural language processing techniques. To demonstrate our framework's capabilities, we examine the synthesis conditions for various metal oxides across more than 12 thousand manuscripts. We then apply machine learning methods to predict the critical parameters needed to synthesize titania nanotubes via hydrothermal methods and verify this result against known mechanisms. Finally, we demonstrate the capacity for transfer learning by using machine learning models to predict synthesis outcomes on materials systems not included in the training set and thereby outperform heuristic strategies. |
| first_indexed | 2024-09-23T13:22:10Z |
| format | Article |
| id | mit-1721.1/129530 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T13:22:10Z |
| publishDate | 2021 |
| publisher | American Chemical Society (ACS) |
| record_format | dspace |
| spelling | mit-1721.1/1295302022-10-01T14:49:27Z Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning Kim, Edward Huang, Kevin Joon-Ming Saunders, Adam McCallum, Andrew Ceder, Gerbrand Olivetti, Elsa A. Massachusetts Institute of Technology. Department of Materials Science and Engineering Massachusetts Institute of Technology. Institute for Data, Systems, and Society In the past several years, Materials Genome Initiative (MGI) efforts have produced myriad examples of computationally designed materials in the fields of energy storage, catalysis, thermoelectrics, and hydrogen storage as well as large data resources that are used to screen for potentially transformative compounds. The bottleneck in high-Throughput materials design has thus shifted to materials synthesis, which motivates our development of a methodology to automatically compile materials synthesis parameters across tens of thousands of scholarly publications using natural language processing techniques. To demonstrate our framework's capabilities, we examine the synthesis conditions for various metal oxides across more than 12 thousand manuscripts. We then apply machine learning methods to predict the critical parameters needed to synthesize titania nanotubes via hydrothermal methods and verify this result against known mechanisms. Finally, we demonstrate the capacity for transfer learning by using machine learning models to predict synthesis outcomes on materials systems not included in the training set and thereby outperform heuristic strategies. National Science Foundation (Award 1534340) Office of Naval Research (Contract N00014-16-1- 2432) 2021-01-22T22:30:19Z 2021-01-22T22:30:19Z 2017-10 2017-10 2019-09-23T13:35:39Z Article http://purl.org/eprint/type/JournalArticle 0897-4756 1520-5002 https://hdl.handle.net/1721.1/129530 Kim, Edward et al. "Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning." Chemistry of Materials 29, 21 (October 2017): 9436–9444 © 2017 American Chemical Society en http://dx.doi.org/10.1021/acs.chemmater.7b03500 Chemistry of Materials Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf American Chemical Society (ACS) ACS |
| spellingShingle | Kim, Edward Huang, Kevin Joon-Ming Saunders, Adam McCallum, Andrew Ceder, Gerbrand Olivetti, Elsa A. Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning |
| title | Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning |
| title_full | Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning |
| title_fullStr | Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning |
| title_full_unstemmed | Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning |
| title_short | Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning |
| title_sort | materials synthesis insights from scientific literature via text extraction and machine learning |
| url | https://hdl.handle.net/1721.1/129530 |
| work_keys_str_mv | AT kimedward materialssynthesisinsightsfromscientificliteratureviatextextractionandmachinelearning AT huangkevinjoonming materialssynthesisinsightsfromscientificliteratureviatextextractionandmachinelearning AT saundersadam materialssynthesisinsightsfromscientificliteratureviatextextractionandmachinelearning AT mccallumandrew materialssynthesisinsightsfromscientificliteratureviatextextractionandmachinelearning AT cedergerbrand materialssynthesisinsightsfromscientificliteratureviatextextractionandmachinelearning AT olivettielsaa materialssynthesisinsightsfromscientificliteratureviatextextractionandmachinelearning |