Developing Novel Descriptors to Predict Physical Properties of Inorganic Compounds from Compositional Formula
-
- Sakata Fusako
- The University of Tokyo
-
- Kotera Masaaki
- The University of Tokyo
-
- Tanaka Kenichi
- The University of Tokyo
-
- Nakano Hiroshi
- Sony Corporation
-
- Ukita Masakazu
- Sony Corporation
-
- Shirasawa Raku
- Sony Corporation
-
- Tomiya Shigetaka
- Sony Corporation
-
- Funatsu Kimito
- The University of Tokyo
Bibliographic Information
- Other Title
-
- 無機材料の組成式を元にした物性予測のための記述子開発
Abstract
In order to efficiently discover novel materials with desirable properties, it is necessary to develop a method to predict physical properties from only compositional formula. In this study, we constructed a regression model expressing relationship between compositional formula and the physical properties. The composition formula of the inorganic material were converted into descriptors, and were used as explanatory variables. We proposed a total of 387 diverse and general descriptors using the numbers of atomic elements and their parameters such as atomic weight, electronegativity, etc., enabling prediction of various physical properties. As a case study, we built predictive models by random forest regression using our proposed descriptors, and predicted three physical properties, i.e., crystal formation energy, density and refractive index. The obtained R2 values were 0.970, 0.977 and 0.766, respectively. In addition to the successful predictive performance, we were also able to statistically select the descriptors that contributed to the prediction models, and they were reasonable from the viewpoint of chemical knowledge.
Journal
-
- Journal of Computer Aided Chemistry
-
Journal of Computer Aided Chemistry 19 (0), 7-18, 2018
Division of Chemical Information and Computer Sciences The Chemical Society of Japan
- Tweet
Details 詳細情報について
-
- CRID
- 1390001288074061440
-
- NII Article ID
- 130007492788
-
- ISSN
- 13458647
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed