Project/Area Number |
21K14675
|
Research Category |
Grant-in-Aid for Early-Career Scientists
|
Allocation Type | Multi-year Fund |
Review Section |
Basic Section 35010:Polymer chemistry-related
|
Research Institution | The Institute of Statistical Mathematics |
Principal Investigator |
Wu Stephen 統計数理研究所, 先端データサイエンス研究系, 准教授 (70804186)
|
Project Period (FY) |
2021-04-01 – 2024-03-31
|
Project Status |
Completed (Fiscal Year 2023)
|
Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2023: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2022: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2021: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
Keywords | polymer informatics / generative models / open source software / ensemble learning / virtual library |
Outline of Research at the Start |
I propose to generate collections of polymer candidates with machine learning that will be openly available in a single user-friendly platform, and will serve as a handy starting point for polymer scientists to tackle various design problems of functional polymers along with their expert knowledge.
|
Outline of Final Research Achievements |
In this study, we developed a method to design and discover new polymers using artificial intelligence (AI). We created various polymer generators using an open-source software called XenonPy. Chemists can use these generators to quickly design new materials based on new polymer structures suggested by AI for any specific industrial applications. As a practical example of this technology, we targeted new material based on liquid crystalline polyimide, which is typically very rare at the moment. We successfully discovered six new material using our technology and all of them have demonstrated high thermal conductivity. These materials have the potential to be useful in future electronics and other industrial applications.
|
Academic Significance and Societal Importance of the Research Achievements |
本プロジェクトの目的は、データサイエンスの専門知識がない材料科学者でも最新の機械学習技術を活用して、新しいポリマー材料の発見を加速できる基盤技術を提供することである。XenonPyというオープンソースソフトウェアを用いて、液晶ポリイミドなどの新材料を発見した。この実証結果が、実際の産業応用でのこの技術の利用への関心を高めることを期待している。この取り組みにより、材料設計のプロセスが効率化され、新材料の迅速な開発が可能になるとともに、持続可能な技術開発に貢献することができる。
|