QWRF-Net: A Quantum-Wavelet Framework with Rectified Flow for Short-Term Precipitation Nowcasting

2026-08-02

AI Summary

This work addresses the challenge of simultaneously capturing intense precipitation cores and multiscale structures in short-term precipitation forecasting over extended lead times. To this end, the authors propose a novel approach that integrates wavelet-based multiscale decoupling, quantum-inspired differential modulation, and rectified flow-based non-autoregressive generation. Specifically, wavelet decomposition explicitly separates latent variables into multiscale subbands, within which a quantum-inspired modulation mechanism is introduced; future precipitation sequences are then efficiently synthesized using a rectified flow decoder. Evaluated on the KNMI and SEVIR datasets, the method demonstrates state-of-the-art overall performance, with notable improvements in fidelity and accuracy for high-intensity precipitation structures—particularly at moderate-to-high rainfall thresholds and during extreme events.

Abstract

Short-term precipitation nowcasting is important for hydrometeorological early warning, especially when intense convective rainfall may trigger urban flooding, flash floods, and other high-impact hazards. A key challenge in warning-oriented nowcasting is that radar precipitation fields contain strongly coupled multi-scale structures, while forecast quality often degrades at later lead times, making it difficult to preserve intense precipitation cores and their spatial organization over the full warning-relevant horizon. To address this problem, we propose QWRF-Net, a quantum-wavelet framework with rectified flow for short-term precipitation nowcasting. The core idea is to improve the conditional representation of precipitation by explicitly decomposing latent features into wavelet sub-bands and then performing differentiated quantum-inspired modulation in the decomposed latent space, before generating future sequences through a rectified-flow-based non-autoregressive decoder. Experiments on the KNMI radar and SEVIR benchmarks under a unified evaluation protocol show that QWRF-Net achieves favorable overall performance, with relatively consistent gains at medium-to-high precipitation thresholds, on an extreme-event subset, and in preserving intense precipitation cores and fine-scale structures. Ablation results further indicate that wavelet-based scale disentanglement, differentiated sub-band modulation, and flow-based generation provide complementary benefits within the proposed framework. Overall, these results suggest that jointly enhancing multi-scale precipitation representation and stable multi-step generation is a promising direction for warning-oriented short-term precipitation nowcasting. The observed improvements may also provide a more useful precipitation basis for downstream hydrological and warning-related applications.

Problem

• short-term precipitation nowcasting
• multi-scale structures
• intense precipitation cores
• forecast degradation
• radar precipitation fields

Innovation

• quantum-inspired modulation
• wavelet decomposition
• rectified flow
• multi-scale representation
• non-autoregressive generation