# Improvements to short-term weather prediction with recurrent-convolutional networks

arXiv: https://arxiv.org/abs/2111.06240 · HTML: https://mlsanity.com/paper/2111.06240/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 14 references that are in the map.
- First posted on arXiv 11 Nov 2021.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Skillful Precipitation Nowcasting using Deep Generative Models of Radar](https://mlsanity.com/paper/2104.00954/) (2021)
- [AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients](https://mlsanity.com/paper/2010.07468/) (2020)
- [Delving Deeper into Convolutional Networks for Learning Video Representations](https://mlsanity.com/paper/1511.06432/) (2015)
- [Spatiotemporal Weather Data Predictions with Shortcut Recurrent-Convolutional Networks: A Solution for the Weather4cast challenge](https://mlsanity.com/paper/2111.02121/) (2021)
- [A Variational U-Net for Weather Forecasting](https://mlsanity.com/paper/2111.03476/) (2021)

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

- [Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model](https://mlsanity.com/paper/2211.01001/) (2022)
- [Seamless lightning nowcasting with recurrent-convolutional deep learning](https://mlsanity.com/paper/2203.10114/) (2022)
- [A Novel Transformer Network with Shifted Window Cross-Attention for Spatiotemporal Weather Forecasting](https://mlsanity.com/paper/2208.01252/) (2022)
- [Solving the Weather4cast Challenge via Visual Transformers for 3D Images](https://mlsanity.com/paper/2212.02456/) (2022)

## Abstract (arXiv)

The Weather4cast 2021 competition gave the participants a task of predicting the time evolution of two-dimensional fields of satellite-based meteorological data. This paper describes the author's efforts, after initial success in the first stage of the competition, to improve the model further in the second stage. The improvements consisted of a shallower model variant that is competitive against the deeper version, adoption of the AdaBelief optimizer, improved handling of one of the predicted variables where the training set was found not to represent the validation set well, and ensembling multiple models to improve the results further. The largest quantitative improvements to the competition metrics can be attributed to the increased amount of training data available in the second stage of the competition, followed by the effects of model ensembling. Qualitative results show that the model can predict the time evolution of the fields, including the motion of the fields over time, starting with sharp predictions for the immediate future and blurring of the outputs in later frames to account for the increased uncertainty.