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

Gardoll, Sébastien; Boucher, Olivier

doi:https://doi.org/10.5194/gmd-15-7051-2022

Articles | Volume 15, issue 18

https://doi.org/10.5194/gmd-15-7051-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-15-7051-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 15, issue 18

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

Data sets

Classification of tropical cyclone containing images using a convolutional neural network: performance and sensitivity to the learning dataset Sébastien Gardoll and Olivier Boucher https://doi.org/10.5281/zenodo.6881020

Model code and software

Classification of tropical cyclone containing images using a convolutional neural network: performance and sensitivity to the learning dataset Sébastien Gardoll and Olivier Boucher https://doi.org/10.5281/zenodo.6881020

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.