Machine learning based charge mobility prediction for organic semiconductors
Problem
Quantum-chemical calculation of transfer integrals for all molecular pairs in organic semiconductors is computationally unaffordable, blocking charge mobility prediction.
Why it matters
Cheap, accurate mobility prediction could accelerate development of organic electronic materials.
What the AI did
Machine learning models based on artificial neural networks predict transfer integrals for four organic semiconductor molecules, using tested features, labels, and a data augmentation scheme.
Results
Determination coefficient of 0.97 and mean absolute error of 4.5 meV for QT; similar accuracy for pentacene, rubrene, and DNTT.
Impact
Abstract claims transfer integral prediction becomes accurate and efficient, replacing costly quantum calculations.
Record
| Venue | The Journal of Chemical Physics |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Tianhao Tan, Dong Wang |
| Citations | 26 (OpenAlex, at import time) |
| References | 40 |
| Model or method | artificial neural networks |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1063/5.0134379 |
| Open access | closed |
| Keywords | machine learning, organic semiconductors, charge mobility, transfer integral, neural networks |
Importance rating
real but narrower advance
Cheap, accurate transfer-integral prediction replaces unaffordable quantum calculations and could accelerate organic electronic materials development; a genuinely new capability but niche materials domain.
More in Engineering & Materials
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Scaling deep learning for materials discovery | 2023 | 1,471 |
8
|
| 2 | Application of Machine Learning in Material Synthesis and Property Prediction | 2023 | 165 |
7
|
| 3 | Machine learning-guided discovery of ionic polymer electrolytes for lithium metal batteries | 2023 | 115 |
7
|
| 4 | Machine Learning for Structural Health Monitoring of Aerospace Structures: A Review | 2025 | 44 |
7
|
| 5 | Power System Transient Stability Assessment Based on Machine Learning Algorithms and Grid Topology | 2023 | 42 |
7
|