Differentiable Physics-Neural Models enable Learning of Non-Markovian Closures for Accelerated Coarse-Grained Physics Simulations

Documenti analoghi

• Hybrid Quantum Physics-informed Neural Network: Towards Efficient Learning of High-speed Flows
  di: Leong, Fong Yew, et al.
  Pubblicazione: (2025)
• NeuralFVM: Neural-physics-based Finite Volume Method for Turbulent Flows Using the $k$-$ω$ Model
  di: Xue, Tingkai, et al.
  Pubblicazione: (2026)
• Physics-Constrained Neural Closure for Lattice Boltzmann Large-Eddy Simulation
  di: Khan, Muhammad Idrees, et al.
  Pubblicazione: (2026)
• Two-point Turbulence Closures in Physical Space
  di: Zambrano, Noah, et al.
  Pubblicazione: (2025)
• Neural-Network-based Viscosity Closure for Non-Newtonian Multiphase Flows
  di: Murugaiyan, Suresh, et al.
  Pubblicazione: (2026)