On the Development of Descriptor-Based Machine Learning Models for Thermodynamic Properties: Part 2—Applicability Domain and Outliers

On the Development of Descriptor-Based Machine Learning Models for Thermodynamic Properties: Part 2—Applicability Domain and Outliers

This article investigates the applicability domain (AD) of machine learning (ML) models trained on high-dimensional data, for the prediction of the ideal gas enthalpy of formation and entropy of molecules via descriptors. The AD is crucial as it describes the space of chemical characteristics in whi...

Descripción completa

Detalles Bibliográficos
Autores principales: Cindy Trinh, Silvia Lasala, Olivier Herbinet, Dimitrios Meimaroglou
Formato: Artículo
Lenguaje:English
Publicado: MDPI AG 2023-12-01
Colección:Algorithms
Materias:
machine learning
QSPR/QSAR
high-dimensional data
descriptors
thermodynamic properties
applicability domain
Acceso en línea:https://www.mdpi.com/1999-4893/16/12/573

Internet

https://www.mdpi.com/1999-4893/16/12/573

Ejemplares similares