Thermal Conductivity

Thermal conductivity, the ability of a material to transfer heat, is a crucial property studied across diverse scientific and engineering fields. Current research focuses on improving the accuracy and efficiency of predicting thermal conductivity, employing advanced machine learning techniques such as physics-informed neural networks, graph neural networks, and autoencoders to model complex material microstructures and large-scale systems like subsurface geological formations. These models are being applied to enhance the prediction of thermal properties in various materials, from nanofluids to geological strata, improving the design of efficient heat transfer systems and furthering our understanding of Earth's thermal processes. The improved accuracy and efficiency of these predictive models have significant implications for material science, energy applications, and geological modeling.

Papers

May 3, 2024

Introducing a microstructure-embedded autoencoder approach for reconstructing high-resolution solution field data from a reduced parametric space
Rasoul Najafi Koopas, Shahed Rezaei, Natalie Rauter, Richard Ostwald, Rolf Lammering
Supervised Autoencoder Multi Fidelity Thermal Conductivity

March 15, 2024

Thermal Earth Model for the Conterminous United States Using an Interpolative Physics-Informed Graph Neural Network (InterPIGNN)
Mohammad J. Aljubran, Roland N. Horne
Graph Neural Network Interpolation Regime Earth System Model State Specific Decision Making Subsurface Temperature Thermal Conductivity

January 4, 2024

Integration of physics-informed operator learning and finite element method for parametric learning of partial differential equations
Shahed Rezaei, Ahmad Moeineddin, Michael Kaliske, Markus Apel
Partial Differential Equation Finite Element Numerical Discretization Multiphase Flow Heterogeneous Medium Parametric Learning Physic Informed Operator Learning Heat Equation Thermal Conductivity

November 6, 2023

End-to-end Material Thermal Conductivity Prediction through Machine Learning
Yagyank Srivastava, Ankit Jain
Machine Learning Boltzmann Equation Thermal Conductivity

April 26, 2022

Self-scalable Tanh (Stan): Faster Convergence and Better Generalization in Physics-informed Neural Networks
Raghav Gnanasambandam, Bo Shen, Jihoon Chung, Xubo Yue, Zhenyu, Kong
Physic Informed Neural Network Faster Convergence Better Generalization Thermal Conductivity

January 2, 2022

Transfer-learning-based Surrogate Model for Thermal Conductivity of Nanofluids
Saeel S. Pai, Abhijeet Banthiya
Surrogate Model Thermal Conductivity

Thermal Conductivity

Papers

Introducing a microstructure-embedded autoencoder approach for reconstructing high-resolution solution field data from a reduced parametric space

Thermal Earth Model for the Conterminous United States Using an Interpolative Physics-Informed Graph Neural Network (InterPIGNN)

Integration of physics-informed operator learning and finite element method for parametric learning of partial differential equations

End-to-end Material Thermal Conductivity Prediction through Machine Learning

Self-scalable Tanh (Stan): Faster Convergence and Better Generalization in Physics-informed Neural Networks

Transfer-learning-based Surrogate Model for Thermal Conductivity of Nanofluids