QuantWeather: Quantile-Aware Probabilistic Forecasting for Subseasonal Precipitation
For operational weather forecasting, this addresses the computational burden of generating and maintaining reforecast datasets for calibration.
QuantWeather proposes an end-to-end probabilistic forecasting framework for subseasonal precipitation that directly models predictive distributions, achieving superior probabilistic skill while reducing inference-time computational and storage costs compared to post-hoc calibration of ensemble forecasts.
Subseasonal precipitation forecasting is inherently uncertain due to chaotic atmospheric dynamics, making reliable uncertainty estimation essential for real-world applications. Existing approaches typically represent uncertainty through ensemble forecasts rather than directly modeling predictive distributions. However, due to systematic model biases, raw ensemble outputs are often not well calibrated and cannot be directly interpreted as reliable uncertainty estimates. As a result, operational systems rely on post-hoc calibration based on reforecast datasets, which are computationally expensive to generate and maintain. To address these limitations, we propose QuantWeather, an end-to-end probabilistic forecasting framework with a dual-head design. The probabilistic and deterministic heads are supervised with separate objectives and optimized jointly. The framework further supports stochastic sampling, enabling probabilistic outputs even with a single stochastic forward pass and allowing optional multi-sample aggregation. Extensive experiments show that QuantWeather demonstrates superior probabilistic forecasting skill while substantially reducing inference-time computational and storage costs.