Abstract
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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Xu, H., Guo, X., Zhang, Y., Zhong, J., Wang, J., & Long, M. (2026). NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters. https://omanscience.com/en/articles/nowcastdit-diffusion-transformers-are-effective-precipitation-nowcasters
MLA 9
Xu, Haoran, et al. "NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters." https://omanscience.com/en/articles/nowcastdit-diffusion-transformers-are-effective-precipitation-nowcasters.
Chicago (author–date)
Xu, Haoran, Xingzhuo Guo, Yuchen Zhang, Jincheng Zhong, Jianmin Wang, and Mingsheng Long. 2026. "NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters." https://omanscience.com/en/articles/nowcastdit-diffusion-transformers-are-effective-precipitation-nowcasters.
Harvard
Xu, H., Guo, X., Zhang, Y., Zhong, J., Wang, J. and Long, M. (2026) 'NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters', Available at: https://omanscience.com/en/articles/nowcastdit-diffusion-transformers-are-effective-precipitation-nowcasters.
Vancouver
Xu H, Guo X, Zhang Y, Zhong J, Wang J, Long M. NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters. https://omanscience.com/en/articles/nowcastdit-diffusion-transformers-are-effective-precipitation-nowcasters
IEEE
H. Xu, X. Guo, Y. Zhang, J. Zhong, J. Wang, and M. Long, "NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters," https://omanscience.com/en/articles/nowcastdit-diffusion-transformers-are-effective-precipitation-nowcasters.