Super-resolution Probabilistic Rain Prediction from Satellite Data Using 3D U-Nets and EarthFormers
This work addresses rain prediction for weather forecasting, but it is incremental, building on existing models with optimizations for a specific competition.
The paper tackled 8-hour probabilistic rain prediction from satellite data, achieving second place in the Weather4cast 2022 NeurIPS competition by using 3D U-Nets and EarthFormers, with methods like optimal spatial context and multi-model ensemble providing modest gains.
Accurate and timely rain prediction is crucial for decision making and is also a challenging task. This paper presents a solution which won the 2 nd prize in the Weather4cast 2022 NeurIPS competition using 3D U-Nets and EarthFormers for 8-hour probabilistic rain prediction based on multi-band satellite images. The spatial context effect of the input satellite image has been deeply explored and optimal context range has been found. Based on the imbalanced rain distribution, we trained multiple models with different loss functions. To further improve the model performance, multi-model ensemble and threshold optimization were used to produce the final probabilistic rain prediction. Experiment results and leaderboard scores demonstrate that optimal spatial context, combined loss function, multi-model ensemble, and threshold optimization all provide modest model gain. A permutation test was used to analyze the effect of each satellite band on rain prediction, and results show that satellite bands signifying cloudtop phase (8.7 um) and cloud-top height (10.8 and 13.4 um) are the best predictors for rain prediction. The source code is available at https://github.com/bugsuse/weather4cast-2022-stage2.