mlsanityData to 7 Oct 2026

SAR-UNet: Small Attention Residual UNet for Explainable Nowcasting Tasks

arXiv 2303.06663 ↗First posted 12 Mar 2023cs.LG physics.ao-phcited by 6

Not on the map. Why?

Abstract (arXiv)

The accuracy and explainability of data-driven nowcasting models are of great importance in many socio-economic sectors reliant on weather-dependent decision making. This paper proposes a novel architecture called Small Attention Residual UNet (SAR-UNet) for precipitation and cloud cover nowcasting. Here, SmaAt-UNet is used as a core model and is further equipped with residual connections, parallel to the depthwise separable convolutions. The proposed SAR-UNet model is evaluated on two datasets, i.e., Dutch precipitation maps ranging from 2016 to 2019 and French cloud cover binary images from 2017 to 2018. The obtained results show that SAR-UNet outperforms other examined models in precipitation nowcasting from 30 to 180 minutes in the future as well as cloud cover nowcasting in the next 90 minutes. Furthermore, we provide additional insights on the nowcasts made by our proposed model using Grad-CAM, a visual explanation technique, which is employed on different levels of the encoder and decoder paths of the SAR-UNet model and produces heatmaps highlighting the critical regions in the input image as well as intermediate representations to the precipitation. The heatmaps generated by Grad-CAM reveal the interactions between the residual connections and the depthwise separable convolutions inside of the multiple depthwise separable blocks placed throughout the network architecture.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 15 of its 34 references that are in the map. First posted on arXiv 12 Mar 2023.

Builds on

15 of 34 references.

References · 15

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2014Going Deeper with Convolutionscited by 4,231
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  6. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  7. 2019ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed datacited by 260
  8. 2020Explainable Deep Learning: A Field Guide for the Uninitiatedcited by 127
  9. 2020SmaAt-UNet: Precipitation Nowcasting using a Small Attention-UNet Architecturecited by 71
  10. 2021Broad-UNet: Multi-scale feature learning for nowcasting taskscited by 25
  11. 2022AA-TransUNet: Attention Augmented TransUNet For Nowcasting Taskscited by 22
  12. 2021Deep Graph Convolutional Networks for Wind Speed Predictioncited by 19
3 more
  1. 2020Deep coastal sea elements forecasting using U-Net based modelscited by 14
  2. 2021Multistream Graph Attention Networks for Wind Speed Forecastingcited by 12
  3. 2020Deep multi-stations weather forecasting: explainable recurrent convolutional neural networkscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2024GA-SmaAt-GNet: Generative Adversarial Small Attention GNet for Extreme Precipitation Nowcastingcited by 9
  2. 2024Interpretable Machine Learning for Weather and Climate Prediction: A Surveycited by 4
  3. 2025SSA-UNet: Advanced Precipitation Nowcasting via Channel Shufflingcited by 2
  4. 2024Self-supervised Spatial-Temporal Learner for Precipitation Nowcastingcited by 0
  5. 2025Integrating Weather Station Data and Radar for Precipitation Nowcasting: SmaAt-fUsion and SmaAt-Krige-GNetcited by 0
  6. 2026SmaAT-QMix-UNet: A Parameter-Efficient Vector-Quantized UNet for Precipitation Nowcastingcited by 0