基于可解释机器学习的热电材料的特征挖掘
Yiyu Liu1, Zilong Mu1, Peichao Hong1
1Research Institute for Biomimetics and Soft Matter, Fujian Provincial Key Lab for Soft Functional Materials Research, Department of Physics, College of Physical Science and Technology, Xiamen University, Xiamen 361005, China. lincx@xmu.edu.cn.
Nanoscale
|December 10, 2024
概括
机器学习通过识别关键性质来加速热电材料的优化. 这种方法减少了试错实验,节省了发现高性能热电材料的时间和资源.
科学领域:
- 材料科学 材料科学 材料科学
- 计算化学的计算化学
- 数据科学数据科学数据科学
背景情况:
- 传统的材料优化在很大程度上依赖于经验数据和广泛的试错,消耗大量的时间和资源.
- 机器学习 (ML) 为材料科学中的复杂优化问题提供了一个强大的替代方案.
研究的目的:
- 确定物理特征与热电材料的热电功率 (zT) 的关系.
- 识别影响实验结果的关键特征,分析间接影响.
主要方法:
- 在热电材料数据库上使用可解释的机器学习方法.
- 采用特征工程来构建和优化基于已识别的关键特征的ML模型.
- 评估不同的特征组合,以确定实验系统的最佳描述符.
主要成果:
- 确定了直接和间接影响实验结果的关键分子特征.
- 通过比较各种特征组合的效率来优化ML模型.
- 确定特定实验系统的最佳特征描述符.
结论:
- 开发的ML模型使热电材料的高通量选成为可能.
- 这种数据驱动的方法显著提高了热电材料实验优化的效率.
相关概念视频
01:43Thermosensation
29.7K
Peripheral thermosensation is the perception of external temperature. A change in temperature (on the surface of the skin and other tissues) is detected by a family of temperature-sensitive ion channels called Transient Receptor Potential, or TRP, receptors. These receptors are located on free nerve endings. Those detecting cold temperatures are closer to the surface of the skin than the nerve endings detecting warmth. These thermoTRP channels, while temperature selective, have relatively...
29.7K
01:16Thermal Sigmatropic Reactions: Overview
1.6K
Sigmatropic rearrangements are a class of pericyclic reactions in which a σ bond migrates from one part of a π system to another. These are intramolecular rearrangements where the total number of σ and π bonds remain unchanged.
Sigmatropic shifts are classified based on an order term [i, j ], where i and j indicate the number of atoms across which each end of the σ bond migrates. Below are examples of a [3,3] sigmatropic shift in...
Sigmatropic shifts are classified based on an order term [i, j ], where i and j indicate the number of atoms across which each end of the σ bond migrates. Below are examples of a [3,3] sigmatropic shift in...
1.6K