Leveraging Domain Adaptation for Accurate Machine Learning Predictions of New Halide Perovskites
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916100153802752 |
|---|---|
| author | Gupta, Dipannoy Das Bare, Zachary J. L. Yew, Suxuen Adhikari, Santosh DeCost, Brian Zhang, Qi Musgrave, Charles Sutton, Christopher |
| author_facet | Gupta, Dipannoy Das Bare, Zachary J. L. Yew, Suxuen Adhikari, Santosh DeCost, Brian Zhang, Qi Musgrave, Charles Sutton, Christopher |
| contents | We combine graph neural networks (GNN) with an inexpensive and reliable structure generation approach based on the bond-valence method (BVM) to train accurate machine learning models for screening 222,960 halide perovskites using statistical estimates of the DFT/PBE formation energy (Ef), and the PBE and HSE band gaps (Eg). The GNNs were fined tuned using domain adaptation (DA) from a source model, which yields a factor of 1.8 times improvement in Ef and 1.2 - 1.35 times improvement in HSE Eg compared to direct training (i.e., without DA). Using these two ML models, 48 compounds were identified out of 222,960 candidates as both stable and that have an HSE Eg that is relevant for photovoltaic applications. For this subset, only 8 have been reported to date, indicating that 40 compounds remain unexplored to the best of our knowledge and therefore offer opportunities for potential experimental examination. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10998 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Domain Adaptation for Accurate Machine Learning Predictions of New Halide Perovskites Gupta, Dipannoy Das Bare, Zachary J. L. Yew, Suxuen Adhikari, Santosh DeCost, Brian Zhang, Qi Musgrave, Charles Sutton, Christopher Materials Science We combine graph neural networks (GNN) with an inexpensive and reliable structure generation approach based on the bond-valence method (BVM) to train accurate machine learning models for screening 222,960 halide perovskites using statistical estimates of the DFT/PBE formation energy (Ef), and the PBE and HSE band gaps (Eg). The GNNs were fined tuned using domain adaptation (DA) from a source model, which yields a factor of 1.8 times improvement in Ef and 1.2 - 1.35 times improvement in HSE Eg compared to direct training (i.e., without DA). Using these two ML models, 48 compounds were identified out of 222,960 candidates as both stable and that have an HSE Eg that is relevant for photovoltaic applications. For this subset, only 8 have been reported to date, indicating that 40 compounds remain unexplored to the best of our knowledge and therefore offer opportunities for potential experimental examination. |
| title | Leveraging Domain Adaptation for Accurate Machine Learning Predictions of New Halide Perovskites |
| topic | Materials Science |
| url | https://arxiv.org/abs/2401.10998 |