Articles | Volume 15, issue 18
https://doi.org/10.5194/gmd-15-7051-2022
https://doi.org/10.5194/gmd-15-7051-2022
Development and technical paper
 | 
16 Sep 2022
Development and technical paper |  | 16 Sep 2022

Classification of tropical cyclone containing images using a convolutional neural network: performance and sensitivity to the learning dataset

Sébastien Gardoll and Olivier Boucher

Related authors

Coordinating an operational data distribution network for CMIP6 data
Ruth Petrie, Sébastien Denvil, Sasha Ames, Guillaume Levavasseur, Sandro Fiore, Chris Allen, Fabrizio Antonio, Katharina Berger, Pierre-Antoine Bretonnière, Luca Cinquini, Eli Dart, Prashanth Dwarakanath, Kelsey Druken, Ben Evans, Laurent Franchistéguy, Sébastien Gardoll, Eric Gerbier, Mark Greenslade, David Hassell, Alan Iwi, Martin Juckes, Stephan Kindermann, Lukasz Lacinski, Maria Mirto, Atef Ben Nasser, Paola Nassisi, Eric Nienhouse, Sergey Nikonov, Alessandra Nuzzo, Clare Richards, Syazwan Ridzwan, Michel Rixen, Kim Serradell, Kate Snow, Ag Stephens, Martina Stockhause, Hans Vahlenkamp, and Rick Wagner
Geosci. Model Dev., 14, 629–644, https://doi.org/10.5194/gmd-14-629-2021,https://doi.org/10.5194/gmd-14-629-2021, 2021
Short summary

Related subject area

Climate and Earth system modeling
ZEMBA v1.0: an energy and moisture balance climate model to investigate Quaternary climate
Daniel F. J. Gunning, Kerim H. Nisancioglu, Emilie Capron, and Roderik S. W. van de Wal
Geosci. Model Dev., 18, 2479–2508, https://doi.org/10.5194/gmd-18-2479-2025,https://doi.org/10.5194/gmd-18-2479-2025, 2025
Short summary
Development and evaluation of a new 4DEnVar-based weakly coupled ocean data assimilation system in E3SMv2
Pengfei Shi, L. Ruby Leung, and Bin Wang
Geosci. Model Dev., 18, 2443–2460, https://doi.org/10.5194/gmd-18-2443-2025,https://doi.org/10.5194/gmd-18-2443-2025, 2025
Short summary
TemDeep: a self-supervised framework for temporal downscaling of atmospheric fields at arbitrary time resolutions
Liwen Wang, Qian Li, Qi Lv, Xuan Peng, and Wei You
Geosci. Model Dev., 18, 2427–2442, https://doi.org/10.5194/gmd-18-2427-2025,https://doi.org/10.5194/gmd-18-2427-2025, 2025
Short summary
The ensemble consistency test: from CESM to MPAS and beyond
Teo Price-Broncucia, Allison Baker, Dorit Hammerling, Michael Duda, and Rebecca Morrison
Geosci. Model Dev., 18, 2349–2372, https://doi.org/10.5194/gmd-18-2349-2025,https://doi.org/10.5194/gmd-18-2349-2025, 2025
Short summary
Presentation, calibration and testing of the DCESS II Earth system model of intermediate complexity (version 1.0)
Esteban Fernández Villanueva and Gary Shaffer
Geosci. Model Dev., 18, 2161–2192, https://doi.org/10.5194/gmd-18-2161-2025,https://doi.org/10.5194/gmd-18-2161-2025, 2025
Short summary

Cited articles

Bishop, C. M.: Pattern Recognition and Machine Learning, chap. 1, 32–33 pp., edited by: Jordan, M., Kleinberg, J., and Schölkopf, B., Springer International Publishing, ISBN 0387310738, 2006. a
Bosler, P. A., Roesler, E. L., Taylor, M. A., and Mundt, M. R.: Stride Search: a general algorithm for storm detection in high-resolution climate data, Geosci. Model Dev., 9, 1383–1398, https://doi.org/10.5194/gmd-9-1383-2016, 2016. a, b
Bourdin, S., Fromang, S., Dulac, W., Cattiaux, J., and Chauvin, F.: Intercomparison of four algorithms for detecting tropical cyclones using ERA5, Geosci. Model Dev., 15, 6759–6786, https://doi.org/10.5194/gmd-15-6759-2022, 2022. a, b
Chan, J. C. L.: Comment on “Changes in tropical cyclone number, duration, and intensity in a warming environment”, Science, 311, 1713, https://doi.org/10.1126/science.1121522, 2006. a
Ebert-Uphoff, I. and Hilburn, K.: Evaluation, tuning, and interpretation of neural networks for working with images in meteorological applications, B. Am. Meteorol. Soc., 101, E2149–E2170, https://doi.org/10.1175/BAMS-D-20-0097.1, 2020. a
Download
Short summary
Tropical cyclones (TCs) are one of the most devastating natural disasters, which justifies monitoring and prediction in the context of a changing climate. In this study, we have adapted and tested a convolutional neural network (CNN) for the classification of reanalysis outputs (ERA5 and MERRA-2 labeled by HURDAT2) according to the presence or absence of TCs. We tested the impact of interpolation and of "mixing and matching" the training and test sets on the performance of the CNN.
Share