Belle Carl E, Aksakalli Vural, Russo Salvy P
ARC Centre of Excellence in Exciton Science, RMIT University, Melbourne 3000, Australia.
School of Science, RMIT University Australia, 124 La Trobe Street, 3000, Melbourne, Australia.
J Cheminform. 2021 May 27;13(1):42. doi: 10.1186/s13321-021-00518-y.
For photovoltaic materials, properties such as band gap [Formula: see text] are critical indicators of the material's suitability to perform a desired function. Calculating [Formula: see text] is often performed using Density Functional Theory (DFT) methods, although more accurate calculation are performed using methods such as the GW approximation. DFT software often used to compute electronic properties includes applications such as VASP, CRYSTAL, CASTEP or Quantum Espresso. Depending on the unit cell size and symmetry of the material, these calculations can be computationally expensive. In this study, we present a new machine learning platform for the accurate prediction of properties such as [Formula: see text] of a wide range of materials.
对于光伏材料而言，诸如带隙[公式：见正文]等特性是材料能否执行所需功能的关键指标。计算[公式：见正文]通常使用密度泛函理论（DFT）方法，不过使用诸如GW近似等方法可进行更精确的计算。常用于计算电子特性的DFT软件包括VASP、CRYSTAL、CASTEP或Quantum Espresso等应用程序。根据材料的晶胞大小和对称性，这些计算在计算上可能成本高昂。在本研究中，我们提出了一个新的机器学习平台，用于准确预测多种材料的诸如[公式：见正文]等特性。
