mlsanityData to 7 Oct 2026

Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model

arXiv 1706.03458 ↗First posted 12 Jun 2017cs.CVcited by 180

Not on the map. Why?

Abstract (arXiv)

With the goal of making high-resolution forecasts of regional rainfall, precipitation nowcasting has become an important and fundamental technology underlying various public services ranging from rainstorm warnings to flight safety. Recently, the Convolutional LSTM (ConvLSTM) model has been shown to outperform traditional optical flow based methods for precipitation nowcasting, suggesting that deep learning models have a huge potential for solving the problem. However, the convolutional recurrence structure in ConvLSTM-based models is location-invariant while natural motion and transformation (e.g., rotation) are location-variant in general. Furthermore, since deep-learning-based precipitation nowcasting is a newly emerging area, clear evaluation protocols have not yet been established. To address these problems, we propose both a new model and a benchmark for precipitation nowcasting. Specifically, we go beyond ConvLSTM and propose the Trajectory GRU (TrajGRU) model that can actively learn the location-variant structure for recurrent connections. Besides, we provide a benchmark that includes a real-world large-scale dataset from the Hong Kong Observatory, a new training loss, and a comprehensive evaluation protocol to facilitate future research and gauge the state of the art.

Key facts. Cited by 180 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 34; 2022: 35; 2023: 30; 2024: 29; 2025: 22; 2026: 30.

180 papers.

Sort:

By area:

  1. 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 308
  2. 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 261
  3. 2021PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learningcited by 181
  4. 2022Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecastcited by 164
  5. 2022Earthformer: Exploring Space-Time Transformers for Earth System Forecastingcited by 146
  6. 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
  7. 2023PreDiff: Precipitation Nowcasting with Latent Diffusion Modelscited by 96
  8. 2022Approximately Equivariant Networks for Imperfectly Symmetric Dynamicscited by 95
  9. 2022Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learningcited by 84
  10. 2021Video Prediction Recalling Long-term Motion Context via Memory Alignment Learningcited by 62
  11. 2023DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcastingcited by 57
  12. 2021MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motionscited by 54
38 more
  1. 2024CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modellingcited by 52
  2. 2021Meta-Learning Dynamics Forecasting Using Task Inferencecited by 37
  3. 2024VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecastingcited by 35
  4. 2023SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecastingcited by 32
  5. 2023SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTMcited by 32
  6. 2022SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbationcited by 31
  7. 2023A Unified Framework for Event-based Frame Interpolation with Ad-hoc Deblurring in the Wildcited by 27
  8. 2021Broad-UNet: Multi-scale feature learning for nowcasting taskscited by 25
  9. 2023Conformal Contextual Robust Optimizationcited by 25
  10. 2021Climate Modeling with Neural Diffusion Equationscited by 20
  11. 2022MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Predictioncited by 17
  12. 2023Multi-modal learning for geospatial vegetation forecastingcited by 16
  13. 2024Fourier Amplitude and Correlation Loss: Beyond Using L2 Loss for Skillful Precipitation Nowcastingcited by 16
  14. 2025Deep Learning and Foundation Models for Weather Prediction: A Surveycited by 15
  15. 2022Spatial Mixture-of-Expertscited by 14
  16. 2023Graph Neural Rough Differential Equations for Traffic Forecastingcited by 14
  17. 2024Deep learning for precipitation nowcasting: A survey from the perspective of time series forecastingcited by 14
  18. 2021MS-nowcasting: Operational Precipitation Nowcasting with Convolutional LSTMs at Microsoft Weathercited by 12
  19. 2022MSPred: Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networkscited by 12
  20. 2022Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restorationcited by 11
  21. 2023Learning from Predictions: Fusing Training and Autoregressive Inference for Long-Term Spatiotemporal Forecastscited by 11
  22. 2023Physics-aware Machine Learning Revolutionizes Scientific Paradigm for Machine Learning and Process-based Hydrologycited by 11
  23. 2021Nowcasting-Nets: Deep Neural Network Structures for Precipitation Nowcasting Using IMERGcited by 10
  24. 2022Effective Training Strategies for Deep-learning-based Precipitation Nowcasting and Estimationcited by 10
  25. 2024PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modelingcited by 10
  26. 2023DiffESM: Conditional Emulation of Earth System Models with Diffusion Modelscited by 9
  27. 2024GA-SmaAt-GNet: Generative Adversarial Small Attention GNet for Extreme Precipitation Nowcastingcited by 9
  28. 2024Global Tropical Cyclone Intensity Forecasting with Multi-modal Multi-scale Causal Autoregressive Modelcited by 9
  29. 2021Prediction of severe thunderstorm events with ensemble deep learning and radar datacited by 8
  30. 2023PostRainBench: A comprehensive benchmark and a new model for precipitation forecastingcited by 8
  31. 2021Physics-informed generative neural network: an application to troposphere temperature predictioncited by 7
  32. 2021Learning to Transfer for Traffic Forecasting via Multi-task Learningcited by 7
  33. 2024A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approachescited by 7
  34. 2021Learning and Dynamical Models for Sub-seasonal Climate Forecasting: Comparison and Collaborationcited by 6
  35. 2024Precipitation Nowcasting Using Diffusion Transformer with Causal Attentioncited by 6
  36. 2021Deep learning for improved global precipitation in numerical weather prediction systemscited by 5
  37. 2022MS-RNN: A Flexible Multi-Scale Framework for Spatiotemporal Predictive Learningcited by 5
  38. 2022Benchmark Dataset for Precipitation Forecasting by Post-Processing the Numerical Weather Predictioncited by 5

50 most cited of 180 All 180 (JSON)