2023 Fiscal Year Research-status Report
データ科学・計算機化学の融合による有機光電変換材料の創生プラットフォーム
| Project/Area Number |
23KF0250
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
WEAL GEOFFREY 京都大学, 高等研究院, 外国人特別研究員
|
|---|
| Project Period (FY) |
2023-11-15 – 2026-03-31
|
| Keywords | Organic photovoltatics / Exciton diffusion / Excitonic coupling / First-principles / Data / Machine learning / Graph neural network |
|---|
| Outline of Annual Research Achievements |
This project aims to accelerate exciton diffusion simulations in organic photovolatic materials using machine learning and data science. During FY2023, we started the following tasks: (i) creation of a database of organic semiconducting materials, including structure, transition amplitudes, and reorganization energies; (ii) creation of a preliminary graph neural network (GNN) model which can predict transition amplitudes via atomic transition charge predictions.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
The project is progressing exactly as planned.
|
| Strategy for Future Research Activity |
During FY2024, we will complete our GNN model and verify it by comparing to experimental exciton diffusion values. We also aim to grasp the underlying physics of the GNN model by creating simplified theoretical models and performing sensitivity analyses.
|
| Causes of Carryover |
Training of the GNN model has only just started. The necessary computational resources for training the model can be purchased during FY2024, when we enter the final phases of model training.
|
