Active learning with surrogate models identifies storm-tide producing tropical cyclones in a large downscaled catalog with high precision and far fewer hydrodynamic simulations than batch training.
The selected value of k cov- ers 99% of the cumulative energy of the singular values, ensuring k <Rank(Σ)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.ao-ph 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LASSE: Learning Active Sampling for Storm Tide Extremes in Non-Stationary Climate Regimes
Active learning with surrogate models identifies storm-tide producing tropical cyclones in a large downscaled catalog with high precision and far fewer hydrodynamic simulations than batch training.