AA-TransUNet: Attention Augmented TransUNet For Nowcasting Tasks

TL;DR

This paper introduces AA-TransUNet, a novel deep learning model combining Transformer, U-Net, and attention modules for improved precipitation nowcasting, demonstrating superior performance on multiple meteorological datasets.

Contribution

The paper presents AA-TransUNet, a new model integrating attention mechanisms with TransUNet for enhanced weather prediction accuracy.

Findings

Outperforms existing models on Dutch and French datasets

Provides uncertainty analysis for model predictions

Effective in precipitation and cloud cover nowcasting

Abstract

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.