NowcastDiT：扩散变换器是有效的降水临近预报器
NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters
浏览论文内容
中文总结 AI 辅助
本文提出NowcastDiT，证明标准扩散变换器通过动态噪声先验和强化学习适配，即可在降水临近预报中达到最先进性能。
中文摘要 AI 辅助
降水临近预报需要在强烈的时空变异性下提供准确的短期预报。扩散模型非常适合建模复杂的降水分布，然而现有方法往往引入日益专门化的设计，使得标准扩散架构的能力未得到充分探索。我们证明，标准扩散变换器已经为降水临近预报提供了一个简单且可扩展的基础，领域特定的需求可在其设计空间内自然得到满足。基于这一原则，我们开发了NowcastDiT，并通过两种互补的适配来实例化这种灵活性：一种用于时间连贯预报的动态感知噪声先验，以及一种用于气象技能、具有时间步感知奖励的端到端强化学习。在SEVIR和MRMS基准上的实验表明，NowcastDiT在感知质量和气象技能方面均达到了最先进的性能。这些结果表明，标准DiT可以作为降水临近预报的有效基础。
英文摘要
Precipitation nowcasting demands accurate short-term forecasts under strong spatiotemporal variability. Diffusion models are well suited to modeling complex precipitation distributions, yet existing approaches often introduce increasingly specialized designs, leaving the capability of a standard diffusion architecture underexplored. We show that a standard Diffusion Transformer already provides a simple and scalable foundation for precipitation nowcasting, with domain-specific requirements accommodated naturally within its design space. Based on this principle, we develop NowcastDiT and instantiate this flexibility through two complementary adaptations: a dynamics-aware noise prior for temporally coherent forecasts, and end-to-end reinforcement learning with timestep-aware rewards for meteorological skill. Experiments on SEVIR and MRMS benchmarks show that NowcastDiT achieves state-of-the-art performance in both perceptual quality and meteorological skill. These results suggest that standard DiT can serve as an effective foundation for precipitation nowcasting.
发表机构
- Tsinghua University（清华大学）
- Envision Energy（远景能源）
- Kuaishou Technology（快手科技）
机构由 AI 辅助整理，请以论文原文为准。
