机器学习增强的带隙预测低对称度的双层和分层矿
Alireza Sabagh Moeini1, Fatemeh Shariatmadar Tehrani2, Alireza Naeimi-Sadigh3
1Faculty of Physics, Semnan University, P.O. Box: 35195-363, Semnan, Iran.
Scientific reports
|November 5, 2024
概括
机器学习模型准确地预测矿带间隙,为计算方法提供更快的替代方案. 支持向量回归通常是有效的,而XGBoost在双矿中表现出色,确定价值电荷标准偏差作为一个关键预测因素.
科学领域:
- 材料科学 材料科学 材料科学
- 计算化学计算化学
- 数据科学数据科学数据科学
背景情况:
- 密度函数理论 (DFT) 对于材料属性预测至关重要,但在计算上昂贵.
- 由于DFT计算的高成本,发现新型矿受到阻碍.
- 复杂的矿结构,包括低对称的双重和分层类型,存在独特的挑战.
研究的目的:
- 探索机器学习 (ML) 模型作为预测矿带间隙的计算效率高的替代方案.
- 为了比较各种ML回归模型 (SVR,RFR,GBR,XGBoost) 的性能,用于带间隙预测.
- 确定影响复杂矿带隙预测的关键材料特征.
主要方法:
- 使用支持向量回归 (SVR),随机森林回归 (RFR),梯度增强回归 (GBR) 和极端梯度增强 (XGBoost).
- 预测了低对称性的双层和分层矿的直接和间接带间隙.
- 使用平均绝对误差 (MAE),平均平方误差 (MSE) 和R平方 (R2) 度量来评估模型性能.
主要成果:
- 支持向量回归 (SVR) 在预测双层和分层矿的带间隙方面表现出最高的一般有效性.
- 极端梯度增强 (XGBoost) 在将衍生不连续性作为一个特征时,实现了对双矿的卓越精度.
- 价值电荷的标准偏差 ("价值电荷 (std) ") 被确定为所有矿类型中带隙预测中最重要的特征.
结论:
- 机器学习为预测矿带间隙提供了一种高效准确的方法.
- ML通过减少对昂贵的DFT计算的依赖,加速发现新矿材料.
- 特性重要性分析提供了对控制矿电子性质的基本因素的见解.
更多相关视频
08:12Low Pressure Vapor-assisted Solution Process for Tunable Band Gap Pinhole-free Methylammonium Lead Halide Perovskite Films
Published on: September 8, 2017
9.5K
11:38Influence of Hybrid Perovskite Fabrication Methods on Film Formation, Electronic Structure, and Solar Cell Performance
Published on: February 27, 2017
18.4K
相关概念视频
02:35Band Theory
15.0K
When two or more atoms come together to form a molecule, their atomic orbitals combine and molecular orbitals of distinct energies result. In a solid, there are a large number of atoms, and therefore a large number of atomic orbitals that may be combined into molecular orbitals. These groups of molecular orbitals are so closely placed together to form continuous regions of energies, known as the bands.
The energy difference between these bands is known as the band gap.
Conductor, Semiconductor,...
The energy difference between these bands is known as the band gap.
Conductor, Semiconductor,...
15.0K
02:27Predicting Molecular Geometry
34.1K
VSEPR Theory for Determination of Electron Pair Geometries
34.1K
01:01Energy Bands in Solids
742
Isolated atoms have discrete energy levels that are well described by the Bohr model. And, it quantifies the energy of an electron in a hydrogen atom as En. Higher quantum numbers 'n' yield less negative, closer electron energy levels.
Band Formation:
When atoms are brought close together, as in a solid, these discrete energy levels begin to split due to the overlap of electron orbitals from adjacent atoms. This split occurs because of the Pauli exclusion principle, which states...
Band Formation:
When atoms are brought close together, as in a solid, these discrete energy levels begin to split due to the overlap of electron orbitals from adjacent atoms. This split occurs because of the Pauli exclusion principle, which states...
742