Thread by @JeantetLorene

1/7 #SeaTurtleTalks
Automatic identification of immature green turtle behavior from accelerometer reveals key marine conservation area in the Caribbean

Accelerometer records animal movement & body posture. Signal interpretation can be difficult & limits its use on #seaturtle

2/7 We deployed multi-sensor recorders (accelerometer, gyroscope and time-depth recorder) combined with animal-borne video-recorder to validate the signal on immature green turtles in Martinique.

3/7 From labelled signals, we trained a #deeplearning algorithm, #Vnet, to automatically identify green turtle #behavior.

🚩High ability to detect behaviors with low discriminative signals such as Feeding and Scratching, and precision down to one centi-second. #rblt

4/7 Application: we deployed #accelerometer combined with gyroscope, depth recorder and GPS on 21 immature green turtles in Martinique during 3 to 5 days.

Behaviors were estimated using #Vnet.
#ANTIDOT

5/7 Method allows to know with precision the behaviors expressed by #seaturlte, day & night. Time budget can be estimated.

We observed high variability in the feeding #behavior with turtles who feed a lot while others very little over these 3 days.

#biologging #Vnet

6/7 Behavioral identification coupled with GPS locations allows:

🚩better understanding of habitat use
🚩to identify critical feeding and resting areas for immature green turtles
🚩protecting these areas to limit interactions with human activities. #conservation

7/7 This study shows how #Biologging & #Deeplearning can help understanding #seaturlte #ecology which is crucial for tackling #conservation issues. Thx a lot to all collaborators!

@DamienChevallier @SebastienGeiger @FloraSiegwalt @CNRS @IPHC_Strasbourg
#ForWomeninScience