Broad-UNet: Multi-scale feature learning for nowcasting tasks
This addresses accurate short-term weather prediction for human activities, but it is incremental as it builds on the UNet model.
The paper tackles weather nowcasting by treating it as an image-to-image translation problem using satellite imagery, introducing Broad-UNet, which achieves more accurate predictions for precipitation maps and cloud cover compared to other architectures.
Weather nowcasting consists of predicting meteorological components in the short term at high spatial resolutions. Due to its influence in many human activities, accurate nowcasting has recently gained plenty of attention. In this paper, we treat the nowcasting problem as an image-to-image translation problem using satellite imagery. We introduce Broad-UNet, a novel architecture based on the core UNet model, to efficiently address this problem. In particular, the proposed Broad-UNet is equipped with asymmetric parallel convolutions as well as Atrous Spatial Pyramid Pooling (ASPP) module. In this way, The the Broad-UNet model learns more complex patterns by combining multi-scale features while using fewer parameters than the core UNet model. The proposed model is applied on two different nowcasting tasks, i.e. precipitation maps and cloud cover nowcasting. The obtained numerical results show that the introduced Broad-UNet model performs more accurate predictions compared to the other examined architectures.