CFE-CMStatistics 2024: Start Registration
View Submission - CFECMStatistics2024
A1557
Title: Bats monitoring: A classification procedure of bats behaviors based on Hawkes processes Authors:  Romain Lacoste - CNRS UMR 8050 Gustave Eiffel University (France) [presenting]
Christophe Denis - Paris 1 Pantheon-Sorbonne University (France)
Charlotte Dion - Sorbonne Universite (France)
Laure Sansonnet - AgroParisTech / INRA (France)
Yves Bas - National Museum of Natural History (France)
Abstract: We are interested in classifying the commuting and foraging behaviour of bats at delimited geographical areas, namely sites, throughout France. To predict the majority behaviour on these sites, echolocation call data is used, recorded as part of Vigie-Chiro participatory project. As the temporal distribution of calls is a relevant indicator of behaviour, providing an adequate model of this distribution is a matter of great interest. Given the self-exciting dynamics observed in foraging behaviour, we propose to model bat calls by Hawkes processes. Specifically, the start time of each call emitted on a site is considered an event of a Hawkes process. Taking advantage of this modelling, a suitable procedure is used that relies on the empirical risk minimization principle to discriminate between the two classes. Then, the performance of the procedure is assessed on synthetic data through comprehensive numerical experiments. The overall methodology is evaluated with a goodness-of-fit test. Finally, the results obtained are presented in the real data set. The classification results are convincing, and the relevance of the method is shown, which could contribute to a better understanding of behavioral determinants and open up broad perspectives in spatial ecology.