A transfer-learning-enhanced reduced-order surrogate for rapid thermal property extraction in patterned FDTR
Authors:
- Bingjia XiaoBXBingjia Xiao
- Tao ChenTCTao Chen
- Puqing JiangPJPuqing Jiang
Preprint
- 3 August 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Patterned-transducer frequency-domain thermoreflectance (FDTR) improves sensitivity to low-thermal-conductivity materials by suppressing lateral heat spreading in the metal transducer, yet the loss of lateral semi-infinite symmetry invalidates analytical models and necessitates expensive finite-element simulations, making iterative fitting computationally prohibitive. This work develops a transfer-learning-enhanced reduced-order surrogate that directly predicts the phase response for rapid inverse fitting. The proposed approach achieves a 534× speedup over COMSOL with sub-degree accuracy (mean RMSE 0.19°), reducing a representative three-parameter fit from over 5 hours to approximately one minute. Experimental validation on Al/SiO2 samples demonstrates consistent extraction of silica thermal conductivities across conventional and patterned configurations, confirming metrological reliability. Transfer learning further extends the surrogate to expanded parameter domains with limited additional high-fidelity data, cutting training data requirements by over 80% while preserving prediction accuracy. The proposed framework provides a practical route for high-throughput thermal characterization in complex geometries where conventional numerical fitting is infeasible.Keywords
This publication has 20 references indexed in Scilit:
- Efficient structure optimization of downhole thermal management system via transfer learning surrogate modelingJournal of Energy Storage, 2026
- Simultaneous measurement of thermal conductivity and heat capacity across diverse materials using the square-pulsed source (SPS) techniqueInternational Communications in Heat and Mass Transfer, 2024
- Reduction of the shallow water system by an error aware POD-neural network method: Application to floodplain dynamicsComputer Methods in Applied Mechanics and Engineering, 2024
- Train small, model big: Scalable physics simulators via reduced order modeling and domain decompositionComputer Methods in Applied Mechanics and Engineering, 2024
- A new spatial-domain thermoreflectance method to measure a broad range of anisotropic in-plane thermal conductivityInternational Journal of Heat and Mass Transfer, 2022
- POD-DL-ROM: Enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decompositionComputer Methods in Applied Mechanics and Engineering, 2022
- Anisotropic thermal conductivity tensor measurements using beam-offset frequency domain thermoreflectance (BO-FDTR) for materials lacking in-plane symmetryInternational Journal of Heat and Mass Transfer, 2021
- Data-driven operator inference for nonintrusive projection-based model reductionComputer Methods in Applied Mechanics and Engineering, 2016
- A comparative study of POD interpolation and POD projection methods for fast and accurate prediction of heat transfer problemsInternational Journal of Heat and Mass Transfer, 2012
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991