Nowcasting of Tropical Cyclone Wind Fields and Intensity from Geostationary Imagery
Authors: Simon Donike, Pritthijit Nath, Cristina Radin, Arthur Avenas, Ruben Cartuyvels, Emiliano Diaz, William K. Jones, Anna Jungbluth
Organizations: Earth Systems Lab · University of Valencia · University of Cambridge · Max Planck Institute for Marine Microbiology, Bremen, Germany · European Space Agency · Imperial College London
High-resolution tropical cyclone surface wind speeds derived from synthetic aperture radar (SAR) observations can support storm structure and intensity modelling, but remain spatially and temporally sparse and unavailable near-real-time. Geostationary satellites capture cloud tops continuously in space and time, but do not directly resolve surface winds. Here, we present simple neural networks to predict 2D wind fields and storm-scale intensity metrics from geostationary imagery. Through a series of ablation studies, we find that joint prediction of 2D fields and scalar metrics from the model latent space improves the retrieval of the (radius of) maximum wind, especially for rapid intensification events.
Figures & tables
Figure 1: Overview of our modelling pipeline. GEO imagery, spatial context channels, and optionally ERA5 are translated into SAR-derived wind fields via a U-Net. An MLP can be added to the latent space, or after the 2D field output, to predict the maximum and radius of maximum wind ( Vmax , Rmax ), as well as the radii of 34, 50, and 64 kt winds ( R34 , R50 , R64 ).
Table 1: ( 1(a) ) Vmax MAE ( ms−1 ) on the held-out test set. The U-Net only predicts the wind field, all other models additionally predict Vmax , Rmax , R34 , R50 , R64 . RI denotes rapid-intensification observations, bold values are best within each training regime. ( 1(b) ) MAE for the joint U-Net and latent MLP supervision ablations, trained to predict the wind fields and either just Vmax or also Rmax , R34 , R50 , R64 . Vmax is reported in ms−1 and Rmax in km . Note that these metrics were calculated over a reduced test set where the TC centre falls on a valid SAR pixel, as required for radii calculations, lowering the number of storms from 38 to 33. Bold values are the best in each column.
Figure 2: Complete-storm Vmax nowcasts from the latent MLP (model 3) and field-only U-Net (model 1), both without ERA5 input. Shading denotes RI periods. Curves use a centred five-hour rolling mean, while metrics use native predictions.
Figure 3: Wind field reconstruction of a category 5 storm. (a) Geostationary imagery (infrared channel 13), (b) target SAR-derived wind field, and (c) wind field prediction from the latent MLP model. Red crosses mark the IBTrACS storm centre.
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Figure A.1: Field-of-view of the geostationary satellites used in this work. Future work will expand our approach to also include coverage from the Meteosat Second Generation (MSG) satellite to complete coverage over the Indian Ocean.