Enhancing the Forecasting Capability of Multi-Model Blending Algorithms for Extreme Precipitation via Joint Use of Station and Gridded Observations

2026-07-06

AI Summary

This study addresses the persistent challenges in numerical weather prediction (NWP) models—namely, the underestimation of extreme precipitation intensity and spatial displacement errors—which are often exacerbated by conventional multi-model blending that diffuses rainfall areas and smooths peak values. To overcome these limitations, the authors propose a novel two-stage fusion framework based on U-Net architecture: first performing probabilistic classification of precipitation occurrence, followed by quantitative reconstruction of rainfall amounts. The approach integrates six leading NWP models and innovatively embeds observations from 2,411 Chinese national meteorological stations directly into the loss function, enabling joint supervision over both grid points and station locations to simultaneously constrain spatial structure and peak intensity. Evaluated on independent data from the 2025 flood season, the method improves the Threat Score (TS) for heavy rain (≥50 mm) by 38.4% over the best individual model and achieves a TS exceeding 0.1 for extreme precipitation (≥100 mm)—a notable milestone—demonstrating substantially enhanced forecast accuracy and practical utility.

Abstract

Accurate extreme precipitation forecasting is critical for disaster mitigation but remains challenging for numerical weather prediction (NWP) models due to systemic intensity underestimation and spatial displacement. Traditional precipitation multi-model blending algorithms perform pixel-by-pixel blending on the forecast field based on weights, which may lead to the expansion of precipitation areas and the smoothing of extreme values. This study proposes an U-Net based two-stage framework: probability classification followed by value reconstruction, to blend forecasts from six major NWP models. A novel station-grid joint supervision mechanism is introduced by integrating observations from 2411 national meteorological stations in China into the loss function, simultaneously constraining spatial structures and peak intensities. Evaluations using independent samples from the 2025 flood season demonstrate that our model significantly outperforms both individual NWPs and current operational products. For rainstorms (>=50 mm), the Threat Score (TS) improved by 38.4% compared to the best NWP. Notably, for extreme events (>=100 mm) driven by extratropical cyclones and the subtropical high, the model successfully elevated the TS to above 0.1, transforming forecasts from having negligible reference value into those with certain operational utility. Furthermore, the model exhibits data-driven spatial correction capabilities, effectively realigning systematic rainbelt displacements with actual precipitation centers. The inclusion of station observations specifically enhanced the TS for rainstorms by 10.4% and effectively balanced the Bias. These results highlight the efficacy of multi-source joint supervision in enhancing the capture of extreme precipitation events.

Problem

• extreme precipitation
• numerical weather prediction
• multi-model blending
• systematic bias
• spatial displacement

Innovation

• multi-model blending
• U-Net
• station-grid joint supervision
• extreme precipitation forecasting
• spatial displacement correction