Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910237380837376 |
|---|---|
| author | Barroso-Luque, Luis Shuaibi, Muhammed Fu, Xiang Wood, Brandon M. Dzamba, Misko Gao, Meng Rizvi, Ammar Zitnick, C. Lawrence Ulissi, Zachary W. |
| author_facet | Barroso-Luque, Luis Shuaibi, Muhammed Fu, Xiang Wood, Brandon M. Dzamba, Misko Gao, Meng Rizvi, Ammar Zitnick, C. Lawrence Ulissi, Zachary W. |
| contents | The ability to discover new materials with desirable properties is critical for numerous applications from helping mitigate climate change to advances in next generation computing hardware. AI has the potential to accelerate materials discovery and design by more effectively exploring the chemical space compared to other computational methods or by trial-and-error. While substantial progress has been made on AI for materials data, benchmarks, and models, a barrier that has emerged is the lack of publicly available training data and open pre-trained models. To address this, we present a Meta FAIR release of the Open Materials 2024 (OMat24) large-scale open dataset and an accompanying set of pre-trained models. OMat24 contains over 110 million density functional theory (DFT) calculations focused on structural and compositional diversity. Our EquiformerV2 models achieve state-of-the-art performance on the Matbench Discovery leaderboard and are capable of predicting ground-state stability and formation energies to an F1 score above 0.9 and an accuracy of 20 meV/atom, respectively. We explore the impact of model size, auxiliary denoising objectives, and fine-tuning on performance across a range of datasets including OMat24, MPtraj, and Alexandria. The open release of the OMat24 dataset and models enables the research community to build upon our efforts and drive further advancements in AI-assisted materials science. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_12771 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models Barroso-Luque, Luis Shuaibi, Muhammed Fu, Xiang Wood, Brandon M. Dzamba, Misko Gao, Meng Rizvi, Ammar Zitnick, C. Lawrence Ulissi, Zachary W. Materials Science Artificial Intelligence Computational Physics The ability to discover new materials with desirable properties is critical for numerous applications from helping mitigate climate change to advances in next generation computing hardware. AI has the potential to accelerate materials discovery and design by more effectively exploring the chemical space compared to other computational methods or by trial-and-error. While substantial progress has been made on AI for materials data, benchmarks, and models, a barrier that has emerged is the lack of publicly available training data and open pre-trained models. To address this, we present a Meta FAIR release of the Open Materials 2024 (OMat24) large-scale open dataset and an accompanying set of pre-trained models. OMat24 contains over 110 million density functional theory (DFT) calculations focused on structural and compositional diversity. Our EquiformerV2 models achieve state-of-the-art performance on the Matbench Discovery leaderboard and are capable of predicting ground-state stability and formation energies to an F1 score above 0.9 and an accuracy of 20 meV/atom, respectively. We explore the impact of model size, auxiliary denoising objectives, and fine-tuning on performance across a range of datasets including OMat24, MPtraj, and Alexandria. The open release of the OMat24 dataset and models enables the research community to build upon our efforts and drive further advancements in AI-assisted materials science. |
| title | Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models |
| topic | Materials Science Artificial Intelligence Computational Physics |
| url | https://arxiv.org/abs/2410.12771 |