GENERIC-FNO: Embedding Energy Conservation and Entropy Production into Fourier Neural Operators
Researchers have developed GENERIC-FNO, a novel neural operator designed to embed the principles of nonequilibrium thermodynamics directly into function space. This model uniquely integrates reversible, energy-conserving dynamics with irreversible, entropy-producing dynamics, a feat not previously achieved in neural operators. GENERIC-FNO learns energy and entropy functionals and enforces exact structural guarantees, demonstrating high precision and outperforming existing baselines on various physical dynamics. AI
IMPACT Advances fundamental AI capabilities for simulating complex physical systems with guaranteed thermodynamic consistency.