# Data-driven Precipitation Nowcasting Using Satellite Imagery

arXiv: https://arxiv.org/abs/2412.11480 · HTML: https://mlsanity.com/paper/2412.11480/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 16 Dec 2024.

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

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Skillful Precipitation Nowcasting using Deep Generative Models of Radar](https://mlsanity.com/paper/2104.00954/) (2021)
- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction](https://mlsanity.com/paper/2003.01460/) (2020)
- [SimVP: Simpler yet Better Video Prediction](https://mlsanity.com/paper/2206.05099/) (2022)
- [PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2103.09504/) (2021)
- [MetNet: A Neural Weather Model for Precipitation Forecasting](https://mlsanity.com/paper/2003.12140/) (2020)
- [Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2206.12126/) (2022)
- [DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting](https://mlsanity.com/paper/2312.06734/) (2023)
- [OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning](https://mlsanity.com/paper/2306.11249/) (2023)
- [SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM](https://mlsanity.com/paper/2308.09891/) (2023)
- [Deterministic Guidance Diffusion Model for Probabilistic Weather Forecasting](https://mlsanity.com/paper/2312.02819/) (2023)
- [Long-Term Typhoon Trajectory Prediction: A Physics-Conditioned Approach Without Reanalysis Data](https://mlsanity.com/paper/2401.15726/) (2024)

## Built on by (most cited first, 6 of 6)

- [Precipitation nowcasting of satellite data using physically-aligned neural networks](https://mlsanity.com/paper/2511.05471/) (2025)
- [QiYao-M: Multimodal Time Series Foundation Model with Role-Aware Modeling of Endogenous and Exogenous Modalities](https://mlsanity.com/paper/2609.34842/) (2026)
- [Enhancing Heavy Rain Nowcasting with Multimodal Data: Integrating Radar and Satellite Observations](https://mlsanity.com/paper/2511.00716/) (2025)
- [PIANO: Physics-informed Dual Neural Operator for Precipitation Nowcasting](https://mlsanity.com/paper/2512.01062/) (2025)
- [Station2Radar: query conditioned gaussian splatting for precipitation field](https://mlsanity.com/paper/2603.00418/) (2026)
- [MAGPIE-Net: Predicting short-duration heavy-rainfall events in station neighborhoods from multitemporal FY-4A AGRI observations](https://mlsanity.com/paper/2608.17753/) (2026)

## Abstract (arXiv)

Accurate precipitation forecasting is crucial for early warnings of disasters, such as floods and landslides. Traditional forecasts rely on ground-based radar systems, which are space-constrained and have high maintenance costs. Consequently, most developing countries depend on a global numerical model with low resolution, instead of operating their own radar systems. To mitigate this gap, we propose the Neural Precipitation Model (NPM), which uses global-scale geostationary satellite imagery. NPM predicts precipitation for up to six hours, with an update every hour. We take three key channels to discriminate rain clouds as input: infrared radiation (at a wavelength of 10.5 μ m), upper- (6.3 μ m), and lower- (7.3 μ m) level water vapor channels. Additionally, NPM introduces positional encoders to capture seasonal and temporal patterns, accounting for variations in precipitation. Our experimental results demonstrate that NPM can predict rainfall in real-time with a resolution of 2 km. The code and dataset are available at https://github.com/seominseok0429/Data-driven-Precipitation-Nowcasting-Using-Satellite-Imagery.