A neural network that predicts divergence-free mantle flow velocities from temperature can replace the Stokes solver in 2D convection simulations, enabling stable rollouts and up to 89x speedup with only 94 training simulations.
, author Tosi , N
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.EP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Physics-based machine learning for mantle convection simulations
A neural network that predicts divergence-free mantle flow velocities from temperature can replace the Stokes solver in 2D convection simulations, enabling stable rollouts and up to 89x speedup with only 94 training simulations.