Page 40 - 《水产学报》2025年第7期

张东，等 水产学报, 2025, 49(7): 079103

[60] Ouellette N T. A physics perspective on collective animal beha- [65] Berdahl A, Torney C J, Ioannou C C, et al. Emergent sensing of
vior[J]. Physical Biology, 2022, 19(2): 021004. complex environments by mobile animal groups[J]. Science,
[61] Formicki K, Korzelecka-Orkisz A, Tański A. Magnetorecep-
2013, 339(6119): 574-576.
tion in fish[J]. Journal of Fish Biology, 2019, 95(1): 73-91.
[66] Page R A, Bernal X E. The challenge of detecting prey: private
[62] Miller M, De Bie J, Sharkh S M, et al. Behavioural response of
and social information use in predatory bats[J]. Functional Eco-
downstream migrating European eel (Anguilla anguilla) to elec-
logy, 2020, 34(2): 344-363.
tric fields under static and flowing water conditions[J]. Ecolo-
[67] Rasmussen J H, Stowell D, Briefer E F. Sound evidence for
gical Engineering, 2021, 172: 106397.
biodiversity monitoring[J]. Science, 2024, 385(6705): 138-140.
[63] Mathevon N, Krause B L. The voices of nature: how and why
[68] Rutz C, Bronstein M, Raskin A, et al. Using machine learning
animals communicate[M]. Princeton: Princeton University
to decode animal communication[J]. Science, 2023, 381(6654):
Press, 2023.
152-155.
[64] Mukhin A, Chernetsov N, Kishkinev D. Acoustic information
as a distant cue for habitat recognition by nocturnally migrating [69] Oestreich W K, Oliver R Y, Chapman M S, et al. Listening to
passerines during landfall[J]. Behavioral Ecology, 2008, 19(4): animal behavior to understand changing ecosystems[J]. Trends
716-723. in Ecology & Evolution, 2024, 39(10): 961-973.

A study of aquatic animal behavior in the AI era

1*
ZHANG Dong , DUAN Ming 2
1. East China Sea Fisheries Research Institute, Chinese Academy of Fisheries Science, Shanghai 200090, China;
2. Hubei Key Laboratory of Smart Fisheries, State Key Laboratory of Breeding Biotechnology and Sustainable Aquaculture,
Institute of Hydrobiology, Chinese Academy of Sciences, Wuhan 430072, China

Abstract: As the importance of ethology in the management of aquatic animals (including natural resources and aquaculture)
becomes increasingly prominent, traditional manual observation and data analysis methods can no longer meet the industry's
demand for ethological data of aquatic animals. In recent years, with the rapid development of artificial intelligence (AI) tech-
nologies, related technologies have played an increasingly important role in the study on aquatic animal behavior, providing
strong technical support for accelerating research on aquatic animal behavior and its application in the fisheries industry, such
as aquaculture. This paper briefly reviews the latest applications of AI technology in the study of aquatic animal behavior, and
the significant advancement in behavioral research from "manual observation" to "intelligent perception", including automatic
image and video analysis, behavior pattern recognition, behavior prediction, and applications in aquaculture. Finally, the review
discusses the key research directions of aquatic animal behavior in the AI era, providing a reference for researchers in the
related fields. In the future, we should particularly focus on the following fields: ① animal personality which is the core of
behavioral ecology; ② behavior-ecology-physiology-gene data chain; ③ AI model generalization; ④ data standardization.
Key words: aquatic animal; artificial intelligence; behavior; machine learning; internet of things; big data
Corresponding author: ZHANG Dong. E-mail: zdfit63@163.com
Funding projects: Science and Technology Innovation Team Project of Chinese Academy of Fishery Sciences (2023TD56)

https://www.china-fishery.cn 中国水产学会主办 sponsored by China Society of Fisheries
8