arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1907.10587cond-mat.mtrl-sci
收藏

从机器学习理解锕系化合物的磁性

Understanding Magnetic Properties of Actinide-Based Compounds from Machine Learning

Ayana Ghosh, Filip Ronning, Serge Nakhmanson, Jian-Xin Zhu

摘要:

锕系元素和镧系元素基材料显示出源于巡游或定域f电子的存在的奇异性质,包括非常规的超导性和磁性、隐藏秩序和重费米子行为。由于5 f电子的强相关性质,这些化合物的磁性敏感地依赖于所施加的磁场和压力,以及化学掺杂。然而,锕系元素材料的结构和磁性之间的精确联系目前还不清楚。在这项研究中,我们建立了这样的结构-性质的联系,通过组装和挖掘两个数据集,聚合,分别为铀和镎为基础的二元化合物的家庭的高通量DFT模拟和实验测量的结果。利用各种回归算法来识别材料系统的可访问属性(特征或描述符)之间的相关性,并预测它们的阳离子磁矩和磁有序的一般形式。描述符代表化合物的结构参数和阳离子f-亚壳层占据数被确定为最重要的准确预测。开发的最佳机器学习模型采用随机森林回归算法,可以预测基于锕系元素的系统中的磁矩大小和排序形式,均方根误差为10-20%。

英文摘要:

Actinide and lanthanide-based materials display exotic properties that originate from the presence of itinerant or localized f-electrons and include unconventional superconductivity and magnetism, hidden order; and heavy fermion behavior. Due to the strongly correlated nature of the 5f electrons, magnetic properties of these compounds depend sensitively on applied magnetic field and pressure, as well as on chemical doping. However, precise connection between the structure and magnetism in actinide-based materials is currently unclear. In this investigation, we established such structure-property links by assembling and mining two datasets that aggregate, respectively, the results of high-throughput DFT simulations and experimental measurements for the families of uranium and neptunium based binary compounds. Various regression algorithms were utilized to identify correlations among accessible attributes (features or descriptors) of the material systems and predict their cation magnetic moments and general forms of magnetic ordering. Descriptors representing compound structural parameters and cation f-subshell occupation numbers were identified as most important for accurate predictions. The best machine learning model developed employs the Random Forest Regression algorithm and can predict magnetic moment sizes and ordering forms in actinide-based systems with 10-20% of root mean square error.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑