AA-TransUNet: Attention Augmented TransUNet For Nowcasting Tasks
This work addresses weather forecasting for meteorology, but it is incremental as it adapts an existing model (TransUNet) with known enhancements for a new domain.
The paper tackled precipitation nowcasting by proposing AA-TransUNet, a data-driven model combining TransUNet with attention modules and depthwise-separable convolutions, which outperformed other models on Dutch precipitation and French cloud cover datasets.
Data driven modeling based approaches have recently gained a lot of attention in many challenging meteorological applications including weather element forecasting. This paper introduces a novel data-driven predictive model based on TransUNet for precipitation nowcasting task. The TransUNet model which combines the Transformer and U-Net models has been previously successfully applied in medical segmentation tasks. Here, TransUNet is used as a core model and is further equipped with Convolutional Block Attention Modules (CBAM) and Depthwise-separable Convolution (DSC). The proposed Attention Augmented TransUNet (AA-TransUNet) model is evaluated on two distinct datasets: the Dutch precipitation map dataset and the French cloud cover dataset. The obtained results show that the proposed model outperforms other examined models on both tested datasets. Furthermore, the uncertainty analysis of the proposed AA-TransUNet is provided to give additional insights on its predictions.