FN Archimer Export Format
PT J
TI Auto-encoding GPS data to reveal individual and collective behaviour
BT 
AF Chabert-Liddell, Saint-Clair
   BEZ, Nicolas
   GLOAGUEN, Pierre
   Donnet, Sophie
   MAHEVAS, Stephanie
AS 1:1;2:4;3:;4:1;5:2;
FF 1:;2:;3:;4:;5:PDG-RBE-MARBEC-LHM;
C1 Universite Paris-Saclay, Agroparistech, INRAE, UMR MIA Paris-Saclay, 91120 Palaiseau, France
   Marbec, Univ Montpellier, CNRS, Ifremer, IRD, S`ete, France
   Universite Bretagne Sud, UMR CNRS 6205, LMBA, F-56000 Vannes, France
   Marbec, Univ Montpellier, CNRS, Ifremer, IRD, S`ete, France
C2 UNIV PARIS-SACLAY, FRANCE
   IFREMER, FRANCE
   UBS, FRANCE
   IRD, FRANCE
SI SETE
SE IRD
   PDG-RBE-MARBEC-LHM
UM MARBEC
TC 0
UR https://archimer.ifremer.fr/doc/00866/97815/106900.pdf
LA English
DT Article
DE ;Bhattacharyya;Collective behaviour;Conditional variational autoencoder;Latent representation of trajectories;Network for trajectory data;Fishing vessels clustering
AB We propose an innovative and generic methodology to analyse individual and collective behaviour through individual trajectory data. The work is motivated by the analysis of GPS trajectories of fishing vessels collected from regulatory tracking data in the context of marine biodiversity conservation and ecosystem-based fisheries management. We build a low-dimensional latent representation of trajectories using convolutional neural networks as non-linear mapping. This is done by training a conditional variational autoencoder taking into account covariates. The posterior distributions of the latent representations can be linked to the characteristics of the actual trajectories. The latent distributions of the trajectories are compared with the Bhattacharyya coefficient, which is well-suited for comparing distributions. Using this coefficient, we analyse the variation of the individual behaviour of each vessel during time. For collective behaviour analysis, we build proximity graphs and use an extension of the stochastic block model for multiple networks. This model results in a clustering of the individuals based on their set of trajectories. The application to French fishing vessels enables us to obtain groups of vessels whose individual and collective behaviours exhibit spatio-temporal patterns over the period 2014-2018. 
PY 2023
PD DEC
SO ArXiv
PU Cornell University
DI 10.48550/arXiv.2312.00456
ID 97815
ER

EF