CorrectCast
A decoupled residual correction framework for improving precipitation nowcasting accuracy. It freezes the backbone network of a base forecaster and trains only a lightweight corrector to estimate and subtract residuals. It supports multimodal context and scale-aware modulation, and provides a unified correction interface across different forecasting models.
Timeline (last 90 days)
CorrectCast is a decoupled residual correction framework that refines completed forecast outputs while keeping the base forecaster frozen.
CorrectCast trains only a lightweight corrector, providing a unified correction interface for different forecast models.
CorrectCast's corrector is conditioned on the base forecast, historical quantitative precipitation estimates (QPE) and precipitable water vapor (PWV) observations, and uses scale-aware modulation to estimate residual corrections.
On the Mississippi River Basin (MRB) and Contiguous United States (CONUS) datasets, CorrectCast improves six base forecasters (covering extrapolation, deterministic methods and generative methods).
CorrectCast's absolute gain in average CSI is 0.0233 on MRB and 0.0290 on CONUS.
The paper does not discuss the corrector's performance on extreme precipitation events, nor its transferability across different climate regions.
All Facts (6)
CorrectCast is a decoupled residual correction framework that refines completed forecast outputs while keeping the base forecaster frozen.
50%UnverifiedCorrectCast trains only a lightweight corrector, providing a unified correction interface for different forecast models.
50%UnverifiedCorrectCast's corrector is conditioned on the base forecast, historical quantitative precipitation estimates (QPE) and precipitable water vapor (PWV) observations, and uses scale-aware modulation to estimate residual corrections.
50%UnverifiedOn the Mississippi River Basin (MRB) and Contiguous United States (CONUS) datasets, CorrectCast improves six base forecasters (covering extrapolation, deterministic methods and generative methods).
50%UnverifiedCorrectCast's absolute gain in average CSI is 0.0233 on MRB and 0.0290 on CONUS.
50%UnverifiedThe paper does not discuss the corrector's performance on extreme precipitation events, nor its transferability across different climate regions.
50%