# DiffSR: Learning Radar Reflectivity Synthesis via Diffusion Model from Satellite Observations

arXiv: https://arxiv.org/abs/2411.06714 · HTML: https://mlsanity.com/paper/2411.06714/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 11 Nov 2024.

## Builds on (most cited first, 13 of 13)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution](https://mlsanity.com/paper/1908.06382/) (2019)
- [HAT: Hybrid Attention Transformer for Image Restoration](https://mlsanity.com/paper/2309.05239/) (2023)
- [ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution](https://mlsanity.com/paper/2303.08714/) (2023)
- [A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds](https://mlsanity.com/paper/2205.04910/) (2022)
- [Learning A Low-Level Vision Generalist via Visual Task Prompt](https://mlsanity.com/paper/2408.08601/) (2024)
- [Development and Interpretation of a Neural Network-Based Synthetic Radar Reflectivity Estimator Using GOES-R Satellite Observations](https://mlsanity.com/paper/2004.07906/) (2020)
- [RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank](https://mlsanity.com/paper/2107.09427/) (2021)
- [GRIDS: Grouped Multiple-Degradation Restoration with Image Degradation Similarity](https://mlsanity.com/paper/2407.12273/) (2024)
- [SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolution](https://mlsanity.com/paper/2402.17133/) (2024)
- [SRViT: Vision Transformers for Estimating Radar Reflectivity from Satellite Observations at Scale](https://mlsanity.com/paper/2406.16955/) (2024)

## Built on by (most cited first, 4 of 4)

- [RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts](https://mlsanity.com/paper/2508.12291/) (2025)
- [Diffusion Models for Future Networks and Communications: A Comprehensive Survey](https://mlsanity.com/paper/2508.01586/) (2025)
- [Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation](https://mlsanity.com/paper/2512.21643/) (2025)
- [Earth Science Foundation Models: From Perception to Reasoning and Discovery](https://mlsanity.com/paper/2605.12542/) (2026)

## Abstract (arXiv)

Weather radar data synthesis can fill in data for areas where ground observations are missing. Existing methods often employ reconstruction-based approaches with MSE loss to reconstruct radar data from satellite observation. However, such methods lead to over-smoothing, which hinders the generation of high-frequency details or high-value observation areas associated with convective weather. To address this issue, we propose a two-stage diffusion-based method called DiffSR. We first pre-train a reconstruction model on global-scale data to obtain radar estimation and then synthesize radar reflectivity by combining radar estimation results with satellite data as conditions for the diffusion model. Extensive experiments show that our method achieves state-of-the-art (SOTA) results, demonstrating the ability to generate high-frequency details and high-value areas.