FNSDA adapts a Fourier neural operator to new dynamical systems by updating about 90 parameters, matching or beating context-based adaptation baselines on four ODE and PDE benchmarks.
Can machines learn to predict weather? using deep learning to predict gridded 500- hpa geopotential height from historical weather data,
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
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Generalizing to New Dynamical Systems via Frequency Domain Adaptation
FNSDA adapts a Fourier neural operator to new dynamical systems by updating about 90 parameters, matching or beating context-based adaptation baselines on four ODE and PDE benchmarks.