Related papers: Transfer-learning-based Surrogate Model for Therma…

We develop a transferable machine learning model which predicts structural relaxation from amorphous supercooled liquid structures. The trained networks are able to predict dynamic heterogeneity across a broad range of temperatures and time…

Dimensions and molecular structure play pivotal roles in the principle of heat conduction. The dimensional characteristics of solution within nanoscale systems depend on the degrees of confinement. However, the influence of such variations…

Quantitative descriptions of the structure-thermal property correlation have been a bottleneck in designing materials with superb thermal properties. In the past decade, the first-principles phonon calculations using density functional…

In this paper we study the efficacy of combining machine-learning methods with projection-based model reduction techniques for creating data-driven surrogate models of computationally expensive, high-fidelity physics models. Such surrogate…

A supervised machine learning (ML) based computational methodology for the design of particulate multifunctional composite materials with desired thermal conductivity (TC) is presented. The design variables are physical descriptors of the…

Boiling heat transfer occurs in many situations and can be used for thermal management in various engineered systems with high energy density, from power electronics to heat exchangers in power plants and nuclear reactors. Essentially,…

Thermal conductivity measurement techniques for materials with nanoscale dimensions require fabrication of very complicated devices or their applicability is limited to a class of materials. Discovery of new methods with high thermal…

Recent experiments have indicated that employing nanostructures can enhance interfacial heat transport, but the mechanism by which different structural morphologies and dimensions contribute to the full-spectrum phonon interfacial transport…

Recent experimental evidence has clearly demonstrated that nanofluids do not provide the greatly enhanced heat transfer predicted in the past. Despite seemingly conclusive proof there is still a great deal of current mathematical research…

Much research in recent years has focused on using empirical machine learning approaches to extract useful insights on the structure-property relationships of superconductor material. Notably, these approaches are bringing extreme benefits…

As a fundamental requisite for thermotronics, controlling heat flow has been a longstanding quest in solid state physics. Recently, there has been a lot of interest in nanoscale hybrid systems as possible candidates for thermal devices. In…

Existing deep learning-based surrogate models facilitate efficient data generation, but fall short in uncertainty quantification, efficient parameter space exploration, and reverse prediction. In our work, we introduce SurroFlow, a novel…

Micro/nano porous polymeric material is considered a unique industrial material due to its extremely low thermal conductivity, low density, and high surface area. Therefore, it is necessary to establish an accurate thermal conductivity…

Recently, transfer learning and self-supervised learning have gained significant attention within the medical field due to their ability to mitigate the challenges posed by limited data availability, improve model generalisation, and reduce…

Recent work has highlighted the complex influence training hyperparameters, e.g., the number of training epochs, can have on the prunability of machine learning models. Perhaps surprisingly, a systematic approach to predict precisely how…

The ability for groundwater heat pumps to meet space heating and cooling demands without relying on fossil fuels, has prompted their mass roll out in dense urban environments. In regions with high subsurface groundwater flow rates, the…

A semi-analytical model for studying thermal transport at the nanoscale, able to accurately describe both the effect of out of equilibrium transport and the thermal transfer at interfaces, is presented. Our approach is based on the…

Transfer learning is an umbrella term for machine learning approaches that leverage knowledge gained from solving one problem (the source domain) to improve speed, efficiency, and data requirements in solving a different but related problem…

Data-driven prediction of fluid flow and temperature distribution in marine and aerospace engineering has received extensive research and demonstrated its potential in real-time prediction recently. However, usually large amounts of…

Heat transfer between a silver nanoparticle and surrounding water has been studied using molecular dynamics (MD) simulations. The thermal conductance (Kapitza conductance) at the interface between a nanoparticle and surrounding water has…