Year: 2025
Type: article
Abstract: . Even though tropical cyclones (TCs) are well documented during the intense part of their lifecycle until they start to evanesce, many physical and statistical properties governing them are not well captured by gridded reanalysis or simulated by earth system models. Thus, the tracking of TCs remains a matter of interest for the investigation of observed and simulated tropical cyclones. Two types of cyclone tracking schemes are available. On the one hand, there are trackers that rely on physical and dynamical properties of the TCs and user-prescribed thresholds, which make them rigid. They need numerous variables that are not always available in the models. On the other hand, there are trackers leaning on deep learning which, by nature, need large amounts of data and computing power. Besides, given the number of physical variables needed for the tracking, they can be prone to overfitting, which hinders their transferability to climate models. In this study, the ability of a Random Forest (RF) approach to track TCs with a limited number of aggregated variables is explored. Hence, the tracking is considered as a binary supervised classification problem of TC-free (zero) and TC (one) situations. Our analysis focuses on the Eastern North Pacific and North Atlantic basins, for which, respectively, 514 and 431 observed tropical cyclone track records are available from the IBTrACS database during the 1980–2021 period. For each 6-hourly time step, RF associates TC occurrence or absence (1 or 0) to atmospheric situations described by predictors extracted from the ERA5 reanalysis. Then situations with TC occurrences are joined for reconstructing TC trajectories. Results show the ability and performance of this method for tracking tropical cyclones over both basins, and good temporal and spatial generalization as well. RF has a similar TC detection rate as trackers based on TCs' properties and significantly lower false alarm rate. RF allows us to detect TC situations for a range of predictor combinations, which brings more flexibility than threshold based trackers. Last but not least, this study shed light on the most relevant variables allowing to detect tropical cyclone.
Institutions: Centre National de la Recherche Scientifique, Université de Versailles Saint-Quentin-en-Yvelines, Commissariat à l'Énergie Atomique et aux Énergies Alternatives, Université Paris-Saclay, CEA Paris-Saclay - Etablissement de Saclay, Laboratoire des Sciences du Climat et de l'Environnement, CEA Paris-Saclay, University of Oxford, École Polytechnique, Université Paris Sciences et Lettres, École Normale Supérieure - PSL, Sorbonne Université, Laboratoire de Météorologie Dynamique, London Mathematical Laboratory
Language: English
Subfield: Atmospheric Science
Field: Earth and Planetary Sciences
Domain: Physical Sciences
SDG: Climate action
Open Access status: gold
Estimated APC paid: $1,553
Awards: G1190173965, G1610782679, Collaborative Research: NSFGEO-NERC: Hurricane Risk Amplification and Changing North Atlantic Natural Disasters, Extreme events under climate change, Idex Paris-Saclay, NSFGEO-NERC: HUrricane Risk Amplification and Changing North Atlantic Natural disasters (Huracan), G434337789, G4750045048, G4810098524, G4866930200, G5263632016, IPSL Climate graduate school, G6350981294, Sorbonne Universités à Paris pour l'Enseignement et la Recherche, G7984917345, G8577729007, EXTREME EVENTS: ARTIFICIAL INTELLIGENCE FOR DETECTION AND ATTRIBUTION
OpenAlex ID: W4416594236