使用可解释合奏学习方法来预测哈利德佩罗夫斯基特的带隙
Chao Ren1,2,3,4, Yiyuan Wu1,2,3, Jijun Zou1,2
1Jiangxi Province Key Laboratory of Nuclear Physics and Technology, East China University of Technology, Nanchang 330013, China.
Materials (Basel, Switzerland)
|June 19, 2024
概括
机器学习准确地预测化矿带隙,这对太阳能电池和LED至关重要. 集体学习模型,特别是渐变增强决策树,在材料开发中显示出高准确性和稳定性.
科学领域:
- 材料科学 材料科学 材料科学
- 计算化学计算化学
- 固态物理 固态物理
背景情况:
- 化矿具有可调节的带隙,使光电子和能源领域的各种应用成为可能.
- 预测这些带隙对于设计具有理想性质的新型材料至关重要.
研究的目的:
- 使用合体学习模型分析化矿矿带隙.
- 确定影响这些化合物的带隙值的关键因素.
- 验证机器学习模型对材料设计的预测准确性.
主要方法:
- 从有关化物矿的出版文献中汇编了实验数据.
- 采用集体学习,特别是渐变增强决策树,用于带隙预测.
- 分析了元素分子量比,以了解对带隙的离子影响.
主要成果:
- 集体学习模型实现了高精度,梯度增强决策树模型显示RMSE为0.090 eV,R2为93.11%.
- 在X和B位置的离子显著影响带隙.
- 兴奋剂和锡原子杂交有效地减少了带隙.
结论:
- 机器学习,特别是集体学习,有助于预测化 PeroVskite 带隙.
- 开发的模型为加速材料发现提供了强大而准确的方法.
- 这项研究强调了计算方法在推进基于矿的技术方面的潜力.
更多相关视频
04:14Facile Synthesis of Colloidal Lead Halide Perovskite Nanoplatelets via Ligand-Assisted Reprecipitation
Published on: October 1, 2019
12.9K
11:38Influence of Hybrid Perovskite Fabrication Methods on Film Formation, Electronic Structure, and Solar Cell Performance
Published on: February 27, 2017
18.5K
相关概念视频
01:16UV–Vis Spectroscopy: Molecular Electronic Transitions
1.4K
In Ultraviolet–Visible (UV–Vis) spectroscopy, the absorption of electromagnetic radiation is used to probe the electronic structure of molecules. This technique provides insights into molecular electronic transitions, particularly the movement of electrons between different molecular orbitals. Radiation is absorbed if the energy of the electromagnetic radiation passing through the molecule is precisely equal to the energy difference between the excited and ground states. During this...
1.4K
02:27Predicting Molecular Geometry
34.2K
VSEPR Theory for Determination of Electron Pair Geometries
34.2K