Embedding a differentiable Fourier solver as a low-fidelity physics core lets a neural surrogate predict phonon-BTE conductivity of porous nanostructures to ~5% error with 300 BTE simulations and design targets at ~4% average error.
A density-based topology optimization methodology for thermoelectric energy conversion problems
1 Pith paper cite this work, alongside 31 external citations. Polarity classification is still indexing.
1
Pith paper citing it
31
external citations · OpenAlex
fields
physics.comp-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Physics Enhanced Deep Surrogates for the Phonon Boltzmann Transport Equation
Embedding a differentiable Fourier solver as a low-fidelity physics core lets a neural surrogate predict phonon-BTE conductivity of porous nanostructures to ~5% error with 300 BTE simulations and design targets at ~4% average error.