UDTR Global Rights of Nature Radar

Deep learning to monitor the deep sea: a category‐oriented automated framework for quantifying animal behavior at hydrothermal vents

Identification

Public canonical key

radar:r-e28de8bd646bd98b808a19046fb5c80e

Authors

Jingyi Chu · Chuyu Li · Xu Liu · Pierre Methou · Chong Chen · Marjolaine Matabos · Jozée Sarrazin · Runsheng Li · Jin Sun

Reported year

2026

Reported language

en

Source type

article

First detected

2026-11-14T02:29:19.552378+00:00

Last metadata observation

2026-11-14T02:29:19.552378+00:00

Last HTTP verification

Not checked

Institutions reported by the source

Laoshan Laboratory · Ocean University of China · Ifremer · Université de Bretagne Occidentale · Biologie et Ecologie des Ecosystèmes Marins Profonds · Japan Agency for Marine-Earth Science and Technology · City University of Hong Kong

Reported affiliation countries

CN · FR · HK · JP

Documentary abstract — original language

Abstract Increasing evidences show that fauna living in deep‐sea ecosystems exhibit various complex behaviors that remain understudied. Although several in situ observatories have been set up around the globe, the use of their imagery data to gain insights into animal behavior across temporal scales remains constrained by the labor‐intensive nature of the analyses. Here, we developed an automated deep‐learning‐based pipeline with multi‐target tracking. Our pipeline integrates YOLOv8 object detection with category‐specific approaches to characterize spatial–temporal behavior patterns (i.e., mobility and trajectory). This pipeline was applied to video imagery from the Lucky Strike hydrothermal vent field, Mid‐Atlantic Ridge as a case study. We tailored tracking methods to three functional mobility groups: Sedentary, Simple Motile, and Complex Motile, represented by the mussel Bathymodiolus azoricus , the shrimp Mirocaris fortunata , and the crab Segonzacia mesatlantica , respectively. Tracking performance was evaluated using standardized multi‐object tracking metrics: the Hungarian algorithm showed strong manual agreement for Sedentary taxa ( r = 0.792), BoTSORT excelled for Simple Motile (HOTA = 0.956, 0.012% identity switches), and DeepSORT achieved best HOTA = 0.727 for Complex Motile. Our results reveal: (1) daily displacement of the mussels, (2) a potential semi‐lunar rhythmic pattern in the movement of the shrimps (14.76‐day periodicity) modulated by the proximity to vent emissions and seasonal factors, and (3) acute stress responses in the crabs linked to localized thermal exposure to hot vent fluids. Our pipeline provides a scalable detection‐tracking‐behavior analysis framework, enabling statistical identification of infra‐monthly behavioral patterns that are difficult to quantify through manual annotations alone. As a result, it can be readily adapted to other deep‐sea ecosystems for standardized multi‐species behavioral monitoring.

Identifiers

OPENALEX

https://openalex.org/W7204082555

DOI

10.1002/lom3.70086

Documentary context

Documentary family

article

Source-reported types

article

Publishers

Wiley

Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.

Sources

OpenAlex · Record 1

• Document · https://doi.org/10.1002/lom3.70086

Documentary status

Relevance pending

Library

This identity is not yet included in the Legal Library.