A CNN surrogate with temporal coarse-graining accelerates 10-day advection simulations up to 92x while achieving r² of 0.60-0.98 against the baseline solver.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
physics.ao-ph 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Acceleration of horizontal numerical advection for atmospheric modeling through surrogate modeling with temporal coarse-graining
A CNN surrogate with temporal coarse-graining accelerates 10-day advection simulations up to 92x while achieving r² of 0.60-0.98 against the baseline solver.