An MLP predicts the covariance difference between limited and large ensembles and applies an element-wise scaling correction to the EnKF forecast covariance, yielding higher analysis accuracy on Lorenz-63 and Lorenz-96 systems.
Ocean dynamics , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
physics.ao-ph 2years
2026 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
Forward sensitivity analysis via Gaussian process emulators identifies observation regions that serve as strong proxies for accurate Bayesian parameter calibration and reduced posterior uncertainty in Earth system models.
citing papers explorer
-
Enabling High-Accuracy Data Assimilation with Limited Ensembles via Machine Learning-Based Covariance Correction
An MLP predicts the covariance difference between limited and large ensembles and applies an element-wise scaling correction to the EnKF forecast covariance, yielding higher analysis accuracy on Lorenz-63 and Lorenz-96 systems.
-
Connecting the forward problem to the inverse problem in uncertainty quantification of Earth system models using fast emulators
Forward sensitivity analysis via Gaussian process emulators identifies observation regions that serve as strong proxies for accurate Bayesian parameter calibration and reduced posterior uncertainty in Earth system models.