mlsanityData to 14 Oct 2026

Integrating Weather Station Data and Radar for Precipitation Nowcasting: SmaAt-fUsion and SmaAt-Krige-GNet

arXiv 2502.16116 ↗First posted 22 Feb 2025cs.LG physics.ao-phcited by 0

Not on the map. Why?

Abstract (arXiv)

Short-term precipitation nowcasting is essential for flood management, transportation, energy system operations, and emergency response. However, many existing models fail to fully exploit the extensive atmospheric information available, relying primarily on precipitation data alone. This study examines whether integrating multi variable weather-station measurements with radar can enhance nowcasting skill and introduces two complementary architectures that integrate multi variable station data with radar images. The SmaAt-fUsion model extends the SmaAt-UNet framework by incorporating weather station data through a convolutional layer, integrating it into the bottleneck of the network; The SmaAt-Krige-GNet model combines precipitation maps with weather station data processed using Kriging, a geo-statistical interpolation method, to generate variable-specific maps. These maps are then utilized in a dual-encoder architecture based on SmaAt-GNet, allowing multi-level data integration. Experimental evaluations were conducted using four years (2016--2019) of weather station and precipitation radar data from the Netherlands. Results demonstrate that SmaAt-Krige-GNet outperforms the standard SmaAt-UNet, which relies solely on precipitation radar data, in low precipitation scenarios, while SmaAt-fUsion surpasses SmaAt-UNet in both low and high precipitation scenarios. This highlights the potential of incorporating discrete weather station data to enhance the performance of deep learning-based weather nowcasting models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 58 references that are in the map. First posted on arXiv 22 Feb 2025.

Builds on

14 of 58 references.

References · 14

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  3. 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 311
  4. 2023Deep Learning for Day Forecasts from Sparse Observationscited by 72
  5. 2020SmaAt-UNet: Precipitation Nowcasting using a Small Attention-UNet Architecturecited by 71
  6. 2021Spatio-temporal graph neural networks for multi-site PV power forecastingcited by 24
  7. 2021Deep Graph Convolutional Networks for Wind Speed Predictioncited by 19
  8. 2020Wind speed prediction using multidimensional convolutional neural networkscited by 17
  9. 2021Multistream Graph Attention Networks for Wind Speed Forecastingcited by 12
  10. 2024GA-SmaAt-GNet: Generative Adversarial Small Attention GNet for Extreme Precipitation Nowcastingcited by 9
  11. 2021TENT: Tensorized Encoder Transformer for Temperature Forecastingcited by 7
  12. 2022Thunderstorm nowcasting with deep learning: a multi-hazard data fusion modelcited by 7
2 more
  1. 2024Graph Dual-stream Convolutional Attention Fusion for Precipitation Nowcastingcited by 7
  2. 2023SAR-UNet: Small Attention Residual UNet for Explainable Nowcasting Taskscited by 6

Built on by

Not cited yet.