机器学习加速金属氧化物热化学预测
Nickolas A Joyner1, Sarah Sprouse1, Haizley Herndon1
1Department of Chemistry and Biochemistry, The University of Alabama, Shelby Hall, Tuscaloosa, Alabama 35487-0336, United States.
Journal of chemical theory and computation
|February 20, 2026
概括
机器学习模型准确地预测金属氧化物能量,使大量凝聚力的能量能够更快地计算. 该框架使用规范集群能量 (NCE) 以降低计算成本实现DFT级准确性.
科学领域:
- 计算材料科学科学 计算材料科学
- 机器学习在化学中的应用
- 固态物理 固态物理
背景情况:
- 准确地预测材料的特性,如凝聚性能量,对于发现新材料至关重要.
- 传统的电子结构计算,如密度函数理论 (DFT),在计算上昂贵.
- 机器学习 (ML) 提供了一个加速这些预测的潜在途径.
研究的目的:
- 开发一种机器学习框架,用于预测金属氧化物的正常化聚合能量 (NCE).
- 推断NCE预测以确定凝聚性散装能量.
- 与DFT计算相比,评估不同ML模型的准确性和效率.
主要方法:
- 编制了一个DFT优化的M(II) O结构 (土和3D过渡金属) 的数据集.
- 结构是使用平滑重叠的原子位置 (SOAP) 描述符编码的.
- 核心回归 (KRR),人工神经网络 (ANN) 和基于树的模型进行了训练和评估.
主要成果:
- KRR获得了NCE的最低预测误差 (MAE = 0.619 kcal/mol,R2 = 0.994),其次是ANN.
- 几种氧化物的预测散体凝聚能在DFT值的1.5kcal/mol以内.
- 结合多样化的结构提高了模型的可转移性,证明了ML在准确的热化学预测方面的潜力.
结论:
- 在适度集群数据上训练的机器学习模型可以准确地预测NCE和散装热化学.
- 与传统的DFT计算相比,这种ML方法显著降低了计算成本.
- 该研究强调了编码复杂电子结构的有效性,用于基于机器学习的材料属性预测.
更多相关视频
相关概念视频
Predicting Reaction Outcomes
11.1K
Kinetics describes the rate and path by which a reaction occurs. In contrast, thermodynamics deals with state functions and describes the properties, behavior, and components of a system. It is not concerned with the path taken by the process and cannot address the rate at which a reaction occurs. Although it does provide information about what can happen during a reaction process, it does not describe the detailed steps of what appears on an atomic or a molecular level. On the other hand,...
11.1K
Thermochemical Equations
36.2K
For a chemical reaction (the system) carried out at constant pressure – with the only work done caused by expansion or contraction – the enthalpy of reaction (also called the heat of reaction, ΔHrxn) is equal to the heat exchanged with the surroundings (qp).
36.2K
Thermal Sigmatropic Reactions: Overview
2.6K
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 1,5-hexadiene, referred...
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 1,5-hexadiene, referred...
2.6K


