A transfer learning framework integrating molecular dynamics and group contribution methods for predicting polymer specific heat capacity
Open Access
- 4 February 2026
- journal article
- research article
- Published by Royal Society of Chemistry (RSC) in Polymer Chemistry
- Vol. 17 (10) , 1028-1051
Abstract
A multi-fidelity transfer learning framework integrates group contribution, molecular dynamics, and experimental data to enable accurate and scalable prediction of polymer specific heat capacities.Keywords
Funding Information
- National Science Foundation (2332270)
- National Science Foundation (2102592)
- National Science Foundation (2146761)
This publication has 51 references indexed in Scilit:
- Discovery of polymers with high bulk modulus and low thermal conductivity using a hybrid generative pipelineChemical Engineering Journal, 2025
- Low‐Frequency Raman Spectroscopy of PolymersMacromolecular Chemistry and Physics, 2025
- Roles of thermal energy storage technology for carbon neutralityCarbon Neutrality, 2023
- Progress on Polymer Dielectrics for Electrostatic Capacitors ApplicationAdvanced Science, 2022
- A review on thermal management of lithium-ion batteries for electric vehiclesEnergy, 2022
- Recent advances in polymer-based thermal interface materials for thermal management: A mini-reviewComposites Communications, 2020
- Machine learning models for the lattice thermal conductivity prediction of inorganic materialsComputational Materials Science, 2019
- Review on heat transfer analysis in thermal energy storage using latent heat storage systems and phase change materialsInternational Journal of Energy Research, 2018
- Fast Parallel Algorithms for Short-Range Molecular DynamicsJournal of Computational Physics, 1995
- Numerical integration of the cartesian equations of motion of a system with constraints: molecular dynamics of n-alkanesJournal of Computational Physics, 1977