mlsanityData to 14 Oct 2026

Temporal Context Conditioning for Seasonality-Aware Precipitation Nowcasting of High-Intensity Rainfall

arXiv 2606.09959 ↗First posted 8 Jun 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Precipitation nowcasting is increasingly being approached with deep learning models that learn directly from recent radar observations. Although such models can efficiently capture short-term precipitation motion, they often lack broader contextual information about the meteorological conditions under which rainfall develops. This paper investigates whether lightweight temporal context can improve radar-based nowcasting, particularly for high-intensity rainfall. We propose the Time-Aware Small-Attention U-Net (TA-SmaAt-UNet), which extends the core SmaAt-UNet model with temporal conditioning layers that use cyclical encodings of time-of-day and time-of-year to modulate intermediate feature representations. Experiments on KNMI radar precipitation data show that temporal conditioning is most beneficial for rare, high-intensity precipitation events, while also improving the representation of seasonal variability and predicted rainfall-intensity distributions. A layer conductance analysis further indicates that the added temporal conditioning layers are actively used by the model despite their small parameter cost. These findings suggest that simple, physically motivated temporal context can improve the realism and reliability of deep learning-based precipitation nowcasts. The implementation of our models and training setup is available on hrefhttps://github.com/gijsvn/TA-SmaAt-UNetGitHub.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 31 references that are in the map. First posted on arXiv 8 Jun 2026.

Builds on

19 of 31 references.

References · 19

  1. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  2. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  3. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  4. 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 311
  5. 2017Deep Learning for Precipitation Nowcasting: A Benchmark and A New Modelcited by 182
  6. 2022Earthformer: Exploring Space-Time Transformers for Earth System Forecastingcited by 152
  7. 2020MetNet: A Neural Weather Model for Precipitation Forecastingcited by 131
  8. 2020SmaAt-UNet: Precipitation Nowcasting using a Small Attention-UNet Architecturecited by 71
  9. 2021Broad-UNet: Multi-scale feature learning for nowcasting taskscited by 25
  10. 2022AA-TransUNet: Attention Augmented TransUNet For Nowcasting Taskscited by 22
  11. 2020A review of radar-based nowcasting of precipitation and applicable machine learning techniquescited by 19
  12. 2021Deep Graph Convolutional Networks for Wind Speed Predictioncited by 19
7 more
  1. 2020Wind speed prediction using multidimensional convolutional neural networkscited by 17
  2. 2021Symbolic regression for scientific discovery: an application to wind speed forecastingcited by 16
  3. 2021Multistream Graph Attention Networks for Wind Speed Forecastingcited by 12
  4. 2024GA-SmaAt-GNet: Generative Adversarial Small Attention GNet for Extreme Precipitation Nowcastingcited by 9
  5. 2022Thunderstorm nowcasting with deep learning: a multi-hazard data fusion modelcited by 7
  6. 2024Precipitation Nowcasting Using Physics Informed Discriminator Generative Modelscited by 7
  7. 2022Deep-Learning-Based Precipitation Nowcasting with Ground Weather Station Data and Radar Datacited by 3

Built on by

Not cited yet.