Physics Enhanced Deep Surrogates for the Phonon Boltzmann Transport Equation

TL;DR

This paper presents a physics-enhanced deep surrogate model for the phonon Boltzmann Transport Equation that combines a differentiable Fourier solver with neural networks, significantly reducing data needs and improving accuracy for nano-scale heat transport simulations.

Contribution

The introduction of PEDS, a physics-informed surrogate that integrates a Fourier solver with neural networks and active learning, offering high accuracy with fewer high-fidelity simulations.

Findings

Reduces training data by up to 70% compared to purely data-driven models.

Achieves about 5% fractional error with only 300 high-fidelity simulations.

Enables efficient design of porous geometries with average errors of 4%.

Abstract

Designing materials with controlled heat flow at the nano-scale is central to advances in microelectronics, thermoelectrics, and energy-conversion technologies. At these scales, phonon transport follows the Boltzmann Transport Equation (BTE), which captures non-diffusive (ballistic) effects but is too costly to solve repeatedly in inverse-design loops. Existing surrogate approaches trade speed for accuracy: fast macroscopic solvers can overestimate conductivities by hundreds of percent, while recent data-driven operator learners often require thousands of high-fidelity simulations. This creates a need for a fast, data-efficient surrogate that remains reliable across ballistic and diffusive regimes. We introduce a Physics-Enhanced Deep Surrogate (PEDS) that combines a differentiable Fourier solver with a neural generator and couples it with uncertainty-driven active learning. The Fourier solver acts as a physical inductive bias, while the network learns geometry-dependent corrections and a mixing coefficient that interpolates between macroscopic and nano-scale behavior. PEDS reduces training-data requirements by up to 70% compared with purely data-driven baselines, achieves roughly 5% fractional error with only 300 high-fidelity BTE simulations, and enables efficient design of porous geometries spanning 12-85 W m$^{-1}$ K$^{-1}$ with average design errors of 4%. The learned mixing parameter recovers the ballistic-diffusive transition and improves out of distribution robustness. These results show that embedding simple, differentiable low-fidelity physics can dramatically increase surrogate data-efficiency and interpretability, making repeated PDE-constrained optimization practical for nano-scale thermal-materials design.