Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation
2026-03-11 • Machine Learning
Machine LearningArtificial IntelligenceComputer Vision and Pattern Recognition
AI summaryⓘ
The authors introduce NeFTY, a new method to create detailed 3D maps of how heat moves inside materials by using temperature changes measured on the surface. Unlike older methods that simplify heat flow or struggle with complicated math, their approach uses a neural network combined with precise physics rules to better capture how heat spreads in three dimensions. This method helps find hidden defects inside materials more accurately and works efficiently even for large, detailed scans. Tests on simulated data show it does a better job than previous techniques.
Neural FieldThermal TomographyTransient Heat DiffusionInverse Heat ConductionPhysics-Informed Neural NetworksDifferentiable Physics Solver3D ReconstructionThermographySubsurface Defect DetectionNumerical Solver
Authors
Tao Zhong, Yixun Hu, Dongzhe Zheng, Aditya Sood, Christine Allen-Blanchette
Abstract
We propose Neural Field Thermal Tomography (NeFTY), a differentiable physics framework for the quantitative 3D reconstruction of material properties from transient surface temperature measurements. While traditional thermography relies on pixel-wise 1D approximations that neglect lateral diffusion, and soft-constrained Physics-Informed Neural Networks (PINNs) often fail in transient diffusion scenarios due to gradient stiffness, NeFTY parameterizes the 3D diffusivity field as a continuous neural field optimized through a rigorous numerical solver. By leveraging a differentiable physics solver, our approach enforces thermodynamic laws as hard constraints while maintaining the memory efficiency required for high-resolution 3D tomography. Our discretize-then-optimize paradigm effectively mitigates the spectral bias and ill-posedness inherent in inverse heat conduction, enabling the recovery of subsurface defects at arbitrary scales. Experimental validation on synthetic data demonstrates that NeFTY significantly improves the accuracy of subsurface defect localization over baselines. Additional details at https://cab-lab-princeton.github.io/nefty/