# WeatherFusionNet: Predicting Precipitation from Satellite Data

arXiv: https://arxiv.org/abs/2211.16824 · HTML: https://mlsanity.com/paper/2211.16824/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 7 references that are in the map.
- First posted on arXiv 30 Nov 2022.

## Builds on (most cited first, 4 of 4)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction](https://mlsanity.com/paper/2003.01460/) (2020)
- [PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2103.09504/) (2021)

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

- [Precipitation Prediction Using an Ensemble of Lightweight Learners](https://mlsanity.com/paper/2401.09424/) (2023)
- [Learning Robust Precipitation Forecaster by Temporal Frame Interpolation](https://mlsanity.com/paper/2311.18341/) (2023)
- [RainAI -- Precipitation Nowcasting from Satellite Data](https://mlsanity.com/paper/2311.18398/) (2023)
- [Enhancing Heavy Rain Nowcasting with Multimodal Data: Integrating Radar and Satellite Observations](https://mlsanity.com/paper/2511.00716/) (2025)
- [A Space-Time Transformer for Precipitation Nowcasting](https://mlsanity.com/paper/2511.11090/) (2025)
- [PIANO: Physics-informed Dual Neural Operator for Precipitation Nowcasting](https://mlsanity.com/paper/2512.01062/) (2025)

## Abstract (arXiv)

The short-term prediction of precipitation is critical in many areas of life. Recently, a large body of work was devoted to forecasting radar reflectivity images. The radar images are available only in areas with ground weather radars. Thus, we aim to predict high-resolution precipitation from lower-resolution satellite radiance images. A neural network called WeatherFusionNet is employed to predict severe rain up to eight hours in advance. WeatherFusionNet is a U-Net architecture that fuses three different ways to process the satellite data; predicting future satellite frames, extracting rain information from the current frames, and using the input sequence directly. Using the presented method, we achieved 1st place in the NeurIPS 2022 Weather4Cast Core challenge. The code and trained parameters are available at urlhttps://github.com/Datalab-FIT-CTU/weather4cast-2022.