FDTRImageEnhancer: Combining Physics-Informed Deconvolution and Microstructure-Aware Deep Learning to Enhance Thermal Images

TL;DR

FDTRImageEnhancer is a computational framework that combines physics-based modeling and deep learning to improve thermal conductivity mapping from FDTR data, effectively revealing grain boundary effects.

Contribution

It introduces a novel integration of physics-informed neural networks with microstructure-aware clustering to enhance inverse thermal transport analysis.

Findings

Recovers bulk thermal conductivity within 0.5% error on synthetic data.

Qualitatively detects grain boundary effects despite limited resolution.

Provides open-source code and datasets for reproducibility.

Abstract

We present FDTRImageEnhancer, an open-source computational framework that improves thermal conductivity mapping from Frequency Domain ThermoReflectance (FDTR) phase data by integrating a physics-based Gaussian convolution abstraction with microstructure-aware deep learning. The Gaussian kernel models the spatial averaging effects of pump and probe beams, while k-means clustering of high-resolution structural images reduces the parameter space for inverse modeling. A physics-informed neural network jointly minimizes phase-data error and deviation from analytically recovered conductivity maps, enabling the detection of grain boundary thermal conductivity drops visually obscured in conventional FDTR inversions. Demonstrated on finite element-generated synthetic data, the framework recovers bulk values within less than 0.5% error and qualitatively resolves grain boundary effects despite limited image resolution. Full Python code and datasets are provided for reproducibility, with the methodology readily adaptable to other inverse thermal transport problems.