Climate Change Data Portal
| PhAST: Physics-Aware, Scalable, and Task-Specific GNNs for Accelerated Catalyst Design | |
| 发表日期 | 2024 |
| ISSN | 1532-4435 |
| 起始页码 | 25 |
| 卷号 | 25 |
| 英文摘要 | Mitigating the climate crisis requires a rapid transition towards lower -carbon energy. Catalyst materials play a crucial role in the electrochemical reactions involved in numerous industrial processes key to this transition, such as renewable energy storage and electrofuel synthesis. To reduce the energy spent on such activities, we must quickly discover more efficient catalysts to drive electrochemical reactions. Machine learning (ML) holds the potential to efficiently model materials properties from large amounts of data, accelerating electrocatalyst design. The Open Catalyst Project OC20 dataset was constructed to that end. However, ML models trained on OC20 are still neither scalable nor accurate enough for practical applications. In this paper, we propose task -specific innovations applicable to most architectures, enhancing both computational efficiency and accuracy. This includes improvements in (1) the graph creation step, (2) atom representations, (3) the energy prediction head, and (4) the force prediction head. We describe these contributions, referred to as PhAST, and evaluate them thoroughly on multiple architectures. Overall, PhAST improves energy MAE by 4 to 42% while dividing compute time by 3 to 8x depending on the targeted task/model. PhAST also enables CPU training, leading to 40x speedups in highly parallelized settings. Python package: https://phast.readthedocs.io. |
| 英文关键词 | climate change; scientific discovery; material modeling; graph neural networks; electrocatalysts |
| 语种 | 英语 |
| WOS研究方向 | Automation & Control Systems ; Computer Science |
| WOS类目 | Automation & Control Systems ; Computer Science, Artificial Intelligence |
| WOS记录号 | WOS:001203728000001 |
| 来源期刊 | JOURNAL OF MACHINE LEARNING RESEARCH
 |
| 文献类型 | 期刊论文 |
| 条目标识符 | http://gcip.llas.ac.cn/handle/2XKMVOVA/294747 |
| 作者单位 | Inria; Universite Paris Saclay; Universite de Montreal; Intel Corporation; McGill University |
| 推荐引用方式 GB/T 7714 | . PhAST: Physics-Aware, Scalable, and Task-Specific GNNs for Accelerated Catalyst Design[J],2024,25. |
| APA | (2024).PhAST: Physics-Aware, Scalable, and Task-Specific GNNs for Accelerated Catalyst Design.JOURNAL OF MACHINE LEARNING RESEARCH,25. |
| MLA | "PhAST: Physics-Aware, Scalable, and Task-Specific GNNs for Accelerated Catalyst Design".JOURNAL OF MACHINE LEARNING RESEARCH 25(2024). |
| 条目包含的文件 | 条目无相关文件。 | |||||
| 个性服务 |
| 推荐该条目 |
| 保存到收藏夹 |
| 导出为Endnote文件 |
| 谷歌学术 |
| 谷歌学术中相似的文章 |
| 百度学术 |
| 百度学术中相似的文章 |
| 必应学术 |
| 必应学术中相似的文章 |
| 相关权益政策 |
| 暂无数据 |
| 收藏/分享 |
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
