A distributional regression network acts as a backward operator to produce uncertainty-quantified, multivariate Gaussian retrievals of cloud properties from six solar channels for data assimilation.
Monthly Weather Review , volume =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Online conformal prediction post-processing guarantees calibrated uncertainty coverage for GenCast, NeuralGCM, and AIFS-ENS forecasts of temperature and precipitation including extremes.
Diffusion models recover known ENSO variability structure from synthetic LIM data when given enough samples, but require pre-training on CMIP6 plus fine-tuning to match observations with the ~700 samples available in ERSSTv5.
Raw IFS forecasts outperform raw AIFS for wind speed at all horizons, but post-processing with EMOS or QR reduces the gap, leaving IFS ahead mainly at short leads.
citing papers explorer
-
Using Distributional Regression Networks to Retrieve Cloud Properties from Solar Satellite Channels for Data Assimilation
A distributional regression network acts as a backward operator to produce uncertainty-quantified, multivariate Gaussian retrievals of cloud properties from six solar channels for data assimilation.
-
Rigorous uncertainty quantification of probabilistic AI weather forecasts with conformal prediction
Online conformal prediction post-processing guarantees calibrated uncertainty coverage for GenCast, NeuralGCM, and AIFS-ENS forecasts of temperature and precipitation including extremes.
-
Learning Climate Variability from Scarce Data with Diffusion Models: A Test Case for ENSO
Diffusion models recover known ENSO variability structure from synthetic LIM data when given enough samples, but require pre-training on CMIP6 plus fine-tuning to match observations with the ~700 samples available in ERSSTv5.