发表机构
LMU Munich; Munich Center for Machine Learning (MCML)（慕尼黑大学; 慕尼黑机器学习中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出单阶段端到端扩散模型JWS，结合Masked Asynchronous Diffusion与评分规则目标，在SEVIR和MeteoNet基准上实现最优概率降水临近预报，训练推理成本显著降低，最小模型参数少且推理速度超17倍。
AI 中文摘要
生成式扩散模型非常适合概率性降水临近预报，但现有方法通常依赖单独训练的压缩或确定性预报组件，且因迭代去噪导致推理成本高昂。本文提出Just Weather Scoring（JWS），这是一种单阶段端到端扩散模型，通过直接在雷达空间进行预报并支持少步生成解决上述问题。雷达空间建模大幅简化了训练与推理，消除了有损压缩带来的不确定性。JWS结合了Masked Asynchronous Diffusion（一种保留干净上下文并使扩散训练适配高维时空数据的时间步采样方案）与简单的评分规则目标，该目标使训练与概率预报对齐并解锁少步生成。在SEVIR和MeteoNet基准上，JWS实现了最先进的概率预报性能，同时降低了训练与推理成本；即使是最小的模型，也使用少得多的参数保持竞争力，且推理速度提升超过17倍。
英文摘要
Generative diffusion models are well-suited for probabilistic precipitation nowcasting, but existing approaches often rely on separately trained compression or deterministic forecasting components and remain costly at inference due to iterative denoising. We introduce Just Weather Scoring (JWS), a single-stage, end-to-end diffusion model which addresses both issues by forecasting directly in radar space and enabling few-step generation. Radar-space modeling greatly simplifies training and inference and eliminates uncertainty arising from lossy compression. JWS combines Masked Asynchronous Diffusion, a timestep-sampling scheme that preserves clean context while adapting diffusion training to high-dimensional spatio-temporal data, with a simple scoring-rule objective that aligns training with probabilistic forecasting and unlocks few-step generation. On the SEVIR and MeteoNet benchmarks, JWS achieves state-of-the-art probabilistic forecasting performance at reduced training and inference cost. Even our smallest model remains competitive using substantially fewer parameters and more than 17x faster inference.
CommentsProject Page: https://compvis.github.io/jws
