Data Driven Insight Into Fish Behaviour and Their Use for Precision Aquaculture

Frontiers in Animal Science

Chris Webb¹  Jon Grant²  Caitlin L. Stockwell²  Giulia Micallef³  Fearghal O'Donncha⁴  Paulito Palmes⁴  Sonia Rey Planellas⁵  Ramon Filgueira⁶ 

[1] Cooke Aquaculture, Orkney, United Kingdom;Department of Oceanography, Dalhousie University, Halifax, NS, Canada;Gildeskål Research Station, Inndyr, Norway;IBM Research Europe, Dublin, Ireland;Institute of Aquaculture, University of Stirling, Stirling, Scotland;Marine Affairs Program, Dalhousie University, Halifax, NS, Canada;

关键词: machine learning;    hydroacoustic;    aquaculture;    AutoML;    IoT;   

DOI  :  10.3389/fanim.2021.695054

来源: DOAJ

【 摘 要 】

Aquaculture, or the farmed production of fish and shellfish, has grown rapidly, from supplying just 7% of fish for human consumption in 1974 to more than half in 2016. This rapid expansion has led to the growth of Precision Aquaculture concept that aims to exploit data-driven management of fish production, thereby improving the farmer's ability to monitor, control, and document biological processes in farms. Fundamental to this paradigm is monitoring of environmental and animal processes within a cage, and processing those data toward farm insight using models and analytics. This paper presents an analysis of environmental and fish behaviour datasets collected at three salmon farms in Norway, Scotland, and Canada. Information on fish behaviour were collected using hydroacoustic sensors that sampled the vertical distribution of fish in a cage at high spatial and temporal resolution, while a network of environmental sensors characterised local site conditions. We present an analysis of the hydroacoustic datasets using AutoML (or automatic machine learning) tools that enables developers with limited data science expertise to train high-quality models specific to the data at hand. We demonstrate how AutoML pipelines can be readily applied to aquaculture datasets to interrogate the data and quantify the primary features that explains data variance. Results demonstrate that variables such as temperature, wind conditions, and hour-of-day were important drivers of fish motion at all sites. Further, there were distinct differences in factors that influenced in-cage variations driven by local variables such as water depth and ambient environmental conditions (particularly dissolved oxygen). The framework offers a transferable approach to interrogate fish behaviour within farm systems, and quantify differences between sites.

【 授权许可】

Unknown