EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics-Enhanced Deep Surrogate for the Phonon Boltzmann Transport Equation

Antonio Varagnolo, Giuseppe Romano, Raphaël Pestourie

ASME Journal of Heat and Mass Transfer · 01.08.2026 · 148 (8)

DOI: 10.1115/1.4071904 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ASME Journal of Heat and Mass Transfer, online erschienen am 10.06.2026. Verfasst von Antonio Varagnolo und 2 weiteren Autor:innen. Die Arbeit nennt 97 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Designing materials with controlled heat flow at the nanoscale is central to advances in micro-electronics, thermoelectrics, and energy-conversion technologies. At these scales, phonon transport follows the Boltzmann Transport Equation (BTE), which captures nondiffusive (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 (AL). 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 nanoscale behavior. PEDS reduces training-data requirements by up to 70% compared with purely data-driven baselines, achieves roughly 5% fractional error (FE) with only 300 high-fidelity BTE simulations, and enables efficient design of porous geometries spanning 12–85 W m−1K−1 with average design errors of 4%. The learned mixing parameter recovers the ballistic–diffusive transition and improves the out-of-distribution robustness. These results show that embedding simple, differentiable low-fidelity physics dramatically increases the surrogate data-efficiency and interpretability, making repeated PDE-constrained optimization practical for nanoscale thermal-materials design.

Förderung

  • National Science Foundation

Zitieren

APA

Varagnolo, A., Romano, G., & Pestourie, R. (2026). Physics-Enhanced Deep Surrogate for the Phonon Boltzmann Transport Equation. ASME Journal of Heat and Mass Transfer, 148(8). https://doi.org/10.1115/1.4071904

Vancouver

Varagnolo A, Romano G, Pestourie R. Physics-Enhanced Deep Surrogate for the Phonon Boltzmann Transport Equation. ASME Journal of Heat and Mass Transfer. 2026;148(8). doi:10.1115/1.4071904

BibTeX
@article{Varagnolo2026,
  author = {Varagnolo, Antonio and Romano, Giuseppe and Pestourie, Raphaël},
  title = {Physics-Enhanced Deep Surrogate for the Phonon Boltzmann Transport Equation},
  journal = {ASME Journal of Heat and Mass Transfer},
  year = {2026},
  volume = {148},
  number = {8},
  doi = {10.1115/1.4071904}
}
Kostenlos starten →