mlsanityData to 7 Oct 2026

Seamless lightning nowcasting with recurrent-convolutional deep learning

arXiv 2203.10114 ↗First posted 15 Mar 2022physics.ao-ph cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

A deep learning model is presented to nowcast the occurrence of lightning at a five-minute time resolution 60 minutes into the future. The model is based on a recurrent-convolutional architecture that allows it to recognize and predict the spatiotemporal development of convection, including the motion, growth and decay of thunderstorm cells. The predictions are performed on a stationary grid, without the use of storm object detection and tracking. The input data, collected from an area in and surrounding Switzerland, comprise ground-based radar data, visible/infrared satellite data and derived cloud products, lightning detection, numerical weather prediction and digital elevation model data. We analyze different alternative loss functions, class weighting strategies and model features, providing guidelines for future studies to select loss functions optimally and to properly calibrate the probabilistic predictions of their model. Based on these analyses, we use focal loss in this study, but conclude that it only provides a small benefit over cross entropy, which is a viable option if recalibration of the model is not practical. The model achieves a pixel-wise critical success index (CSI) of 0.45 to predict lightning occurrence within 8 km over the 60-min nowcast period, ranging from a CSI of 0.75 at a 5-min lead time to a CSI of 0.32 at a 60-min lead time.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 11 of its 79 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

11 of 79 references.

References · 11

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020Calibrating Deep Neural Networks using Focal Losscited by 353
  4. 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 308
  5. 2021Ensemble deep learning: A reviewcited by 283
  6. 2020A survey of loss functions for semantic segmentationcited by 216
  7. 2019Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentationcited by 162
  8. 2015Delving Deeper into Convolutional Networks for Learning Video Representationscited by 146
  9. 2020Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Networkcited by 68
  10. 2021Spatiotemporal Weather Data Predictions with Shortcut Recurrent-Convolutional Networks: A Solution for the Weather4cast challengecited by 4
  11. 2021Improvements to short-term weather prediction with recurrent-convolutional networkscited by 4

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 1; 2025: 1.

5 papers.

  1. 2023Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantificationcited by 53
  2. 2022Thunderstorm nowcasting with deep learning: a multi-hazard data fusion modelcited by 7
  3. 2023Physically Explainable Deep Learning for Convective Initiation Nowcasting Using GOES-16 Satellite Observationscited by 3
  4. 2024CloudCast -- Total Cloud Cover Nowcasting with Machine Learningcited by 3
  5. 2025Physical Scales Matter: The Role of Receptive Fields and Advection in Satellite-Based Thunderstorm Nowcasting with Convolutional Neural Networkscited by 0