QuantWeather: Quantile-Aware Probabilistic Forecasting for Subseasonal Precipitation

TL;DR

QuantWeather is a novel probabilistic forecasting framework for subseasonal precipitation that improves calibration, reduces computational costs, and provides reliable uncertainty estimates through a dual-head neural network design.

Contribution

It introduces an end-to-end dual-head model that jointly optimizes probabilistic and deterministic forecasts, enabling efficient and well-calibrated uncertainty estimation.

Findings

QuantWeather outperforms existing methods in probabilistic forecasting skill.

The framework reduces inference-time computational and storage costs.

It supports stochastic sampling for reliable uncertainty quantification.

Abstract

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.