arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.03372cond-mat.mtrl-scics.LG
收藏

双压电材料禁带宽度的机器学习预测

Machine-Learning Prediction of the Computed Band Gaps of Double Perovskite Materials

The University of Melbourne(墨尔本大学);Xiamen University(厦门大学);Beijing University of Technology(北京工业大学)

Junfei Zhang, Yueqi Li, Xinbo Zhou

摘要:

预测功能材料的电子结构对于新器件的工程设计是必不可少的。传统的基于密度泛函理论(DFT)的电子结构预测方法不仅计算量大,而且由于交换相关泛函的近似,计算精度有限。基于机器学习的替代方法作为绕过这些限制的可行替代方案受到了广泛关注,特别是在预测固态带隙方面,这激发了这项研究。在这里,我们构建了一个随机森林回归模型的双钙钛矿材料的带隙,使用1306带隙的数据集计算与GLLBSC(Gritsenko,van Leeuwen,van Lenthe,和Baerends固体相关)功能。在所采用的20个物理特征中,我们发现体积模量、超导温度和阳离子电负性表现出最高的重要性分数,与底层电子结构的物理学相一致。使用前10名的功能,一个模型的准确度为85.6%,均方根误差为0.64 eV,与以前的研究。我们的研究结果在某种意义上是重要的,它们证明了机器学习回归在快速筛选有前途的候选功能材料方面的潜力。

英文摘要:

Prediction of the electronic structure of functional materials is essential for the engineering of new devices. Conventional electronic structure prediction methods based on density functional theory (DFT) suffer from not only high computational cost, but also limited accuracy arising from the approximations of the exchange-correlation functional. Surrogate methods based on machine learning have garnered much attention as a viable alternative to bypass these limitations, especially in the prediction of solid-state band gaps, which motivated this research study. Herein, we construct a random forest regression model for band gaps of double perovskite materials, using a dataset of 1306 band gaps computed with the GLLBSC (Gritsenko, van Leeuwen, van Lenthe, and Baerends solid correlation) functional. Among the 20 physical features employed, we find that the bulk modulus, superconductivity temperature, and cation electronegativity exhibit the highest importance scores, consistent with the physics of the underlying electronic structure. Using the top 10 features, a model accuracy of 85.6% with a root mean square error of 0.64 eV is obtained, comparable to previous studies. Our results are significant in the sense that they attest to the potential of machine learning regressions for the rapid screening of promising candidate functional materials.

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。

↑