用多个机器学习模型预测基和OH之间的基位点的气抽象速率常数
Lei Zhang1, Lili Ye1, Fan Wang1
1School of Chemical Engineering, Dalian University of Technology, Dalian, Liaoning 116024, China.
机器学习准确地预测了碳化合物燃烧的抽取速率常数. 一个Feedforward神经网络 (FNN) 模型在预测基基 (OH) 通过基激素 (OH) 进行初级基缩方面表现出卓越的性能.
科学领域:
- 计算化学计算化学
- 化学动力学 化学动力学
- 机器学习应用 机器学习应用
背景情况:
- 通过基 (OH) 抽取的反应在大气和燃烧化学中至关重要.
- 准确预测这些反应的速率常数对于建模复杂的化学过程至关重要.
- 确定速率常数的传统方法可能是计算密集和耗时的.
研究的目的:
- 开发和评估机器学习 (ML) 模型,用于预测初级酸抽象速率常数.
- 为了研究前神经网络 (FNN),支持向量回归 (SVR) 和高斯过程回归 (GPR) 的有效性.
- 引入一种新的特征选择策略,集成描述符预处理和模型特定优化.
主要方法:
- 使用了三个ML模型:FNN,SVR和GPR.
- 实施了新的特征选择策略,包括描述符预处理和包装方法.
- 通过使用离开一个分组 (LOGO) 和K-fold交叉验证技术验证模型性能.
主要成果:
- 使用七个选定的描述符的FNN模型,表现优于SVR和GPR.
- 通过LOGO交叉验证,FNN实现了39.06%的平均百分比偏差,通过十倍交叉验证达到19.1%.
- 经过训练的FNN模型准确地预测了较大的基的速率常数,遵循修改后的阿雷尼乌斯方程.
结论:
- 机器学习,特别是FNN,为预测抽象速率常数提供了可靠和高效的方法.
- 拟议的特征选择策略提高了化学动力学ML模型的性能.
- 这项工作支持ML的应用,用于生成碳化合物燃烧化学的关键动力参数.
更多相关视频
12:08Catalytic Reactions at Amine-Stabilized and Ligand-Free Platinum Nanoparticles Supported on Titania During Hydrogenation of Alkenes and Aldehydes
Published on: June 24, 2022
12:11Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry
Published on: April 8, 2020
相关概念视频
Reduction of Alkenes: Catalytic Hydrogenation
Metals like palladium, platinum, and nickel are commonly used in their solid forms — fine powder on an inert surface. As these catalysts remain insoluble in the reaction mixture, they are referred to as heterogeneous catalysts.
The hydrogenation process takes place on the...
Acid-Catalyzed Hydration of Alkenes
Factors Affecting α-Alkylation of Ketones: Choice of Base
The reaction involving bases like EtO− whose conjugate acid EtOH (pKa = 15.9) is stronger than the ketone (pKa = 19.2) results in an equilibrium mixture with higher ketone concentration. As a consequence,...
Radical Anti-Markovnikov Addition to Alkenes: Mechanism
The mechanism starts with chain initiation, which involves two steps. In the first chain initiation step, a weak peroxide bond is homolytically cleaved upon mild heating to form two alkoxy radicals. In the second initiation step, a hydrogen atom is abstracted by the alkoxy...
Reduction of Alkenes: Asymmetric Catalytic Hydrogenation
The metal catalyst used can be either heterogeneous or homogeneous. When hydrogenation of an alkene generates a chiral center, a pair of enantiomeric products is expected to form. However, an enantiomeric excess of one of the products can be facilitated using an enantioselective reaction or an...
Regioselectivity of Electrophilic Additions-Peroxide Effect
