# Precipitation Prediction Using an Ensemble of Lightweight Learners

arXiv: https://arxiv.org/abs/2401.09424 · HTML: https://mlsanity.com/paper/2401.09424/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 30 Nov 2023.

## Builds on (most cited first, 6 of 6)

- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [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)
- [FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators](https://mlsanity.com/paper/2208.05419/) (2022)
- [Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast](https://mlsanity.com/paper/2211.02556/) (2022)
- [WeatherFusionNet: Predicting Precipitation from Satellite Data](https://mlsanity.com/paper/2211.16824/) (2022)

## Built on by (most cited first, 3 of 3)

- [RainPro-8: An Efficient Deep Learning Model to Estimate Rainfall Probabilities Over 8 Hours](https://mlsanity.com/paper/2505.10271/) (2025)
- [A Space-Time Transformer for Precipitation Nowcasting](https://mlsanity.com/paper/2511.11090/) (2025)
- [Dense-Cast: A lightweight ensemble of deep learning architectures for precipitation nowcasting](https://mlsanity.com/paper/2608.06082/) (2026)

## Abstract (arXiv)

Precipitation prediction plays a crucial role in modern agriculture and industry. However, it poses significant challenges due to the diverse patterns and dynamics in time and space, as well as the scarcity of high precipitation events. To address this challenge, we propose an ensemble learning framework that leverages multiple learners to capture the diverse patterns of precipitation distribution. Specifically, the framework consists of a precipitation predictor with multiple lightweight heads (learners) and a controller that combines the outputs from these heads. The learners and the controller are separately optimized with a proposed 3-stage training scheme. By utilizing provided satellite images, the proposed approach can effectively model the intricate rainfall patterns, especially for high precipitation events. It achieved 1st place on the core test as well as the nowcasting leaderboards of the Weather4Cast 2023 competition. For detailed implementation, please refer to our GitHub repository at: https://github.com/lxz1217/weather4cast-2023-lxz.