论文标题
WeatherfusionNet：预测卫星数据的降水
WeatherFusionNet: Predicting Precipitation from Satellite Data
论文作者
论文摘要
在许多生活的许多领域，短期预测降水至关重要。最近，大量的作品用于预测雷达反射率图像。雷达图像仅在具有地面天气雷达的区域可用。因此，我们旨在预测低分辨率卫星辐射图像的高分辨率沉淀。使用称为WeatherFusionNet的神经网络可预测提前八个小时的严重降雨。 WeatherFusionNet是一种U-NET体系结构，可以融合三种处理卫星数据的方式。预测未来的卫星框架，从当前帧中提取降雨信息，并直接使用输入序列。使用呈现的方法，我们在Neurips 2022 Weather4cast Core Challenge中获得了第一名。代码和训练有素的参数可在\ url {https://github.com/datalab-fit-ctu/weather4cast-2022}中找到。
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 \url{https://github.com/Datalab-FIT-CTU/weather4cast-2022}.
