2021 Fiscal Year Final Research Report
Material search system based on collaboration between data science and computational science
Project/Area Number |
19K12007
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 60100:Computational science-related
|
Research Institution | Kanazawa Institute of Technology |
Principal Investigator |
Hayashi Ryoko 金沢工業大学, 工学部, 准教授 (30303332)
|
Project Period (FY) |
2019-04-01 – 2022-03-31
|
Keywords | データマイニング / ケモインフォマティクス / 分子 / 分子間力 |
Outline of Final Research Achievements |
In recent years, in material science, the momentum for researching and developing new materials by utilizing the data accumulated so far and data science and computational science is increasing at home and abroad. This research aims at material search by appropriately combining data science and computational science. In this study, we investigated the classification rules of boiling point and melting point on a trial basis. Melting point and boiling point are basic quantities that indicate the properties of a substance, and many data have been accumulated. It is known that the size and structure of molecules affect the melting point and boiling point, but there is still room for investigation as to how much they affect quantitatively. Therefore, the melting points and boiling points of hydrocarbons and similar molecules were classified using decision trees and random forests.
|
Free Research Field |
データ科学
|
Academic Significance and Societal Importance of the Research Achievements |
物質が固体から液体に変わり始める融点と,液体から気体に変わり始める沸点は,物質の性質を示す基礎的な量である.そのため,古くから多くの物質において融点と沸点は調べられており,データが蓄積されている.融点と沸点は分子の性質を反映しており,分子の大きさや構造が融点と沸点に影響することがある程度知られているが,定量的にはまだ調査の余地があるものと考えられる.そこで本研究では決定木とランダムフォレストで融点と沸点の分類と予測を行い,これまで知られた融点と沸点の性質を定量的に評価できるかどうかを調べた.
|