Classification of tropical cyclones observed by satellites in the Southwest Indian Ocean basin using the 2D-CNN model

Harimino Andriamalala RAJAONARISOA, Adolphe Andriamanga RATIARISON

Abstract


The aim of this work was to model the images of tropical cyclones seen from the meteorological satellites using the 2D-CNN model. The work remained within the framework of the classification problem. More specifically, the experiment consisted of training, then testing and validating a 2D-CNN model that predicts the class of the cyclone image using a set of images of tropical cyclones obtained by satellites. The model only took into account 2 classes. The first (respectively the second) class contains images of cyclones with a wind force less than 34Kt (respectively greater than or equal to 34Kt). In fact, the cyclone begins to be named as soon as the force of the wind that accompanies it is greater than or equal to 34Kt. The simulations were done for each value of the batch size corresponding to the power of 2, namely 2, 4, 8, 16, 32, 64, 128 and 254. For each of these batch size values, the simulations were evaluated using the evolution of the mean curve between training and test data as a function of the epoch. The best classification model was obtained by running the simulation with a batch size of 64 at the 25th epoch with a model reliability rate of 97%.

Keywords


Batch size, Southwest Indian Ocean Basin , Image classification, Tropical cyclone, 2D-CNN, Epoch.

Full Text:

PDF

References


A. M. F. Lagmay, K. A. S. Aracan, and V. Malano, “Impacts of Typhoon Haiyan (Yolanda) and local perspectives on disaster risk reduction and climate change adaptation,” Int. J. Disaster Risk Reduct., vol. 13, pp. 335–347, 2015. [Online]. Available: https://doi.org/10.1016/j.ijdrr.2015.07.009

K. Emanuel, Divine Wind: The History and Science of Hurricanes. Oxford, U.K.: Oxford Univ. Press, 2005.

M. Ranaivoson Rapatsalahy, “Caractérisation des impacts des cyclones sur le littoral du sud-ouest de l'océan Indien par télédétection,” Projet de thèse, Université de La Réunion, 2023. [Online]. Available: https://theses.fr/s386160Theses

Météo-France, “Centre Météorologique Régional Spécialisé- La Réunion,” Mar. 21, 2022. [Online]. Available: https://meteofrance.re/fr/actualites/centre-meteorologique-regional-specialise-la-reunionmeteofrance.re

Organisation météorologique mondiale, The SouthWest Indian Ocean cyclone basin, 2013. [Online]. Available: https://severeweather.wmo.int/TCFW/RAI_Training/Cyc_Bassin_SWI_oct2013_LANGLADE.pdf

F. Roux and N. Viltard, “Les cyclones tropicaux,” La Météorologie, vol. 38, no. 2, pp. 45–60, 2002.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Adv. Neural Inf. Process. Syst., vol. 25, pp. 1097–1105, 2012. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf

Météo-France, “Prévision saisonnière d'activité cyclonique dans le Sud-Ouest de l'océan Indien : Saison 2024-2025,” Oct. 31, 2024. [Online]. Available: https://meteofrance.re/fr/climat/prevision-saisonniere-dactivite-cyclonique-dans-le-sud-ouest-de-locean-indien-saison-2024

Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016. [Chap. 8: Optimization for Training Deep Models, Online]. Available: https://www.deeplearningbook.org/

L. Prechelt, “Early stopping — But when?,” in Neural Networks: Tricks of the Trade, G. Orr and K.-R. Müller, Eds. Berlin, Germany: Springer, 1998, pp. 55–69. [Online]. Available: https://doi.org/10.1007/3-540-49430-8_3

A. Krogh and J. A. Hertz, “A simple weight decay can improve generalization,” in Adv. Neural Inf. Process. Syst., pp. 950–957, 1992.

C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 2818–2826. [Online]. Available: https://doi.org/10.1109/CVPR.2016.308

L. Li, Z. Shuai, J. Hu, and Y. Zhang, “Classification of Tropical Cyclone Intensity Based on Deep Learning and YOLO V5,” in Advances in Artificial Intelligence and Security (ICAIS 2022), X. Sun, X. Zhang, Z. Xia, and E. Bertino, Eds., Commun. Comput. Inf. Sci., vol. 1586, pp. 280–291. Springer, 2022. [Online]. Available: https://doi.org/10.1007/978-3-031-06767-9_23

C. Kumler-Bonfanti, J. Stewart, D. Hall, and M. Govett, “Tropical and Extratropical Cyclone Detection Using Deep Learning,” arXiv preprint arXiv:2005.09056, 2020. [Online]. Available: https://arxiv.org/abs/2005.09056

C. Kar and S. Banerjee, “Tropical Cyclones Classification from Satellite Images Using Blocked Local Binary Pattern and Histogram Analysis,” in Soft Computing Techniques and Applications, S. Borah, R. Pradhan, N. Dey, and P. Gupta, Eds. Springer, vol. 1248, pp. 431–440, 2021. [Online]. Available: https://doi.org/10.1007/978-981-15-7394-1_38




DOI: http://dx.doi.org/10.52155/ijpsat.v51.2.7327

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 Harimino Andriamalala RAJAONARISOA

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.