Benchmarking machine learning and molecular dynamics methods for the prediction of the thermophysical properties of organic liquids
File(s)
Published online version
Author(s)
Ogbomo, Egheosa
Carman, Fionn
Dini, Daniele
Ewen, James
Type
Journal Article
Abstract
Accurate prediction of thermophysical properties is crucial for the rational design of lubricants and cooling fluids. We compile a database of approximately 4,700 experimental and critically evaluated reference values for the density, viscosity, and thermal conductivity of 835 unique organic molecules in the C10--C50 range. We use this database to train and benchmark a range of machine learning (ML) architectures and molecular representations. XGBoost models trained on molecular descriptors are consistently among the most accurate across all three target properties. Out-of-distribution tests show that unreliable predictions can be flagged from descriptor-space distance and the position of the predicted value within the training range. Equilibrium molecular dynamics (EMD) simulations of eight representative molecules reproduce density accurately but show systematic, chemistry-dependent force-field errors for the viscosity and thermal conductivity. At an inference cost orders of magnitude lower than EMD simulations, the ML models are well suited to high-throughput screening of new candidate molecules for lubricants and other formulated products.
Date Issued
2026-09-29
Date Acceptance
2026-09-18
Citation
Digital Discovery, 2026
ISSN
2635-098X
Publisher
The Royal Society of Chemistry
Journal / Book Title
Digital Discovery
Copyright Statement
© 2026 The Author(s). Published by the Royal Society of Chemistry This article is licensed under a Creative Commons Attribution 4.0 Unported Licence. You can use material from this article in other publications without requesting further permissions from the RSC, provided that the correct acknowledgement is given.
License URL
Publication Status
Published online
Date Publish Online
2026-09-29