论文标题
使用3D U-NET和Earthformer的卫星数据预测的超分辨率概率降雨预测
Super-resolution Probabilistic Rain Prediction from Satellite Data Using 3D U-Nets and EarthFormers
论文作者
论文摘要
准确，及时的降雨预测对于决策至关重要，也是一项艰巨的任务。本文提出了一种解决方案，该解决方案赢得了Weather4cast 2022 Neurips竞争的第2奖，它使用3D U-NET和Earthformers赢得了基于多波段卫星图像的8小时概率降雨预测。已经深入探索了输入卫星图像的空间上下文效应，并发现了最佳上下文范围。基于降雨分布不平衡，我们训练了具有不同损失功能的多个模型。为了进一步提高模型性能，使用多模型集合和阈值优化来产生最终的概率降雨预测。实验结果和排行榜得分表明，最佳空间环境，组合损耗函数，多模型集合和阈值优化都提供了适度的模型增益。使用置换测试来分析每个卫星带对雨水预测的影响，结果表明，卫星带表示CloudTop相（8.7 UM）和云顶高（10.8和13.4 UM）是雨水预测的最佳预测指标。源代码可从https://github.com/bugsuse/weather4cast-2022-STAGE2获得。
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.
