| 研究課題/領域番号 |
23KF0250
|
|---|
| 研究機関 | 京都大学 |
|---|
研究代表者 |
|
|---|
| 研究分担者 |
WEAL GEOFFREY 京都大学, 高等研究院, 外国人特別研究員
|
|---|
| 研究期間 (年度) |
2023-11-15 – 2026-03-31
|
| キーワード | Organic photovoltatics / Exciton diffusion / Excitonic coupling / First-principles / Data / Machine learning / Graph neural network |
|---|
| 研究実績の概要 |
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.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
2: おおむね順調に進展している
理由
The project is progressing exactly as planned.
|
| 今後の研究の推進方策 |
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.
|
| 次年度使用額が生じた理由 |
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.
|
