| 夏杰桢,曹蓉,吴琪.化学通报,2022,85(10):1224-1232. |
| 机器学习结合密度泛函理论计算在材料科学中的研究进展 |
| Research Progress of Machine Learning Combined with DFT Calculation in Materials Science |
| 投稿时间：2022-02-11 修订日期：2022-03-20 |
| DOI： |
| 中文关键词: 材料学 密度泛函理论(DFT)计算 机器学习(ML) |
| 英文关键词:Materials science, Density functional theory (DFT) calculations, Machine learning (ML) |
| 基金项目: |
|
| 摘要点击次数: 2817 |
| 全文下载次数: 0 |
| 中文摘要: |
| 近年来，材料科学研究中密度泛函理论(DFT)计算与机器学习相结合的方法呈现爆炸式增长的趋势。本文综述了密度泛函理论(DFT)及其高通量方法产生的大量计算数据与机器学习相结合的原理和意义，从DFT计算的基本原理出发，重点介绍了机器学习(ML)方法的流程、常用的算法及其在催化材料预测热门研究方向中的应用，最后剖析了这个新兴领域目前存在的研究问题、挑战以及未来的发展前景。 |
| 英文摘要: |
| In recent years, methods of combining density functional theory (DFT) calculations with machine learning in materials science research have shown an explosive growth trend. This paper mainly reviewed the principle and significance of the combination of a large amount of computational data generated by density functional theory (DFT) calculation as well as its high-throughput method with machine learning. Starting from the basic principle of DFT calculation, the machine learning (ML) method is mainly introduced. The process, commonly used algorithms and their application in the popular research direction of catalytic material prediction, and finally analyzed the current research problems, challenges and future development prospects of this emerging field. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |