Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper explores multi-quantile regression as an alternative to MSE/MAE loss for training deep learning precipitation nowcasting models, aiming to improve forecasts of heavy rainfall. They trained a SmaAt-UNet model using a multi-quantile pinball loss and compared its performance against MSE and MAE baselines on a radar precipitation nowcasting task over the Netherlands. Results show that multi-quantile training improves the central deterministic forecast, reducing test-set MSE by 8.6% compared to MSE training, and provides useful upper-quantile outputs for risk assessment.
Trading MSE for multi-quantile regression in a standard nowcasting architecture yields an 8.6% MSE reduction and unlocks risk-sensitive heavy precipitation forecasts.
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}.