Beyond MSE: Improving Precipitation Nowcasting with Multi-Quantile Regression

2026-05-28

AI Summary

This study addresses the tendency of traditional nowcasting models—trained with pointwise loss functions such as mean squared error (MSE)—to produce overly smoothed precipitation forecasts that fail to capture intense rainfall events. The authors reformulate deterministic precipitation nowcasting as a multi-quantile regression problem and, without altering the underlying network architecture, introduce the multi-quantile Pinball loss function into the training of the established SmaAt-UNet model for the first time. This approach simultaneously optimizes central tendency prediction and extreme precipitation risk estimation. Evaluated on the test set, the proposed method reduces MSE by 8.6% compared to the MSE-trained baseline, while its high quantile outputs provide actionable information for risk-sensitive decision-making in heavy rainfall scenarios.

Abstract

Deep-learning precipitation nowcasting models are often optimized using pointwise losses such as mean squared error or mean absolute error, which can lead to overly smooth forecasts and poor representation of heavy rainfall. This study investigates whether the predictive performance of an established deterministic nowcasting architecture can be improved by reformulating training as a multi-quantile regression problem. Using SmaAt-UNet as a core model, we compare MSE, MAE, and multi-quantile pinball-loss training on radar precipitation nowcasting over the Netherlands. The results show that multi-quantile training improves the central deterministic forecast, decreasing test-set MSE by 8.6\% compared to a model trained using MSE, while also producing upper-quantile outputs that are useful for risk-sensitive prediction of heavy precipitation. These findings suggest that quantile regression provides a simple alternative to standard pointwise losses without requiring a new architecture or generative sampling procedure. The implementation of our models and training setup is available on \href{https://github.com/gijsvn/Multi-Quantile-Precipitation-Nowcasting}{GitHub}.

Problem

• precipitation nowcasting
• mean squared error
• quantile regression
• heavy rainfall
• deep learning

Innovation

• multi-quantile regression
• precipitation nowcasting
• pinball loss
• SmaAt-UNet
• uncertainty quantification