Posted in | News | Remote Monitoring

Eco-Friendly System for Identifying Fish Stocks to Control Over-Fishing

An autonomous system for spotting schools of fish, including information related to their movements in deep waters and their size, is being developed under project SYMBIOSIS, an international scientific initiative with support from the European Union’s Horizon 2020 program.

The project expects to achieve a positive impact on marine biology research, conservation, and policy-making for fisheries in Europe and worldwide. (Image credit: IMDEA Networks Institute)

The project is being headed by the University of Haifa, and two groups of researchers from IMDEA Networks Institute in Madrid are contributing to the attempts to develop the system. The SYMBIOSIS system combines optical and acoustic technologies that do not need human interference, and will be in a position to transmit real-time warnings to coastal stations. These data will help in contriving ocean fishing policies and in improving the protection of the marine environment.

The system will be environmentally friendly, not only in its operation which will be non-invasive and won’t impact the marine ecosystem, but more importantly because it will provide reliable information about the condition of marine fish stocks. At present, it’s virtually impossible to collect such information without investing enormous resources. Using the latest optical and acoustic technology, we hope to change attitudes towards marine resources,” explained Dr Roee Diamant of the School of Marine Sciences at the University of Haifa, who has been coordinating the initiative.

Since the 20th century, the advancement of fishing technology has led to the increasing awareness that one of the most critical problems faced by marine ecosystems is fishing. Certain predictions indicate that if over-fishing is left uncontrolled, the global fish stocks might decline terribly by 2048. Fishing authorities worldwide are looking to control over-fishing by enforcing new regulations based on fish stocks. However, very few techniques are currently available for monitoring fish stocks in real time. In a majority of the techniques, surface boats endeavor to spot fish stocks with the help of sonars.

Dr Diamant states that these techniques mandate the use of substantial resources and staff to monitor and interpret the findings of the sonars. As a result, their viability is limited in terms of the cost-benefit. Moreover, when sonars are used, the search for fish stocks is usually restricted to narrow areas—such as those underneath the ship from which the sampling is done—thereby impairing any ensuing decision-making. The restricted statistics that this short-term and random sampling of the marine environment offers indicates that the process is subject to a number of sampling errors.

The Symbiosis system integrates acoustic and optical technologies to monitor the marine environment, specifically the size of the fish stock, within a radius of 1 km. It operates in a completely autonomous way, gathering underwater data over longer periods of time and sending this information to a coastal center. The focus of the study is to identify six large fish species that are specifically high in demand from the fishing industry: two species of tuna, scad (a species of mackerel; Trachurus mediterraneus), Atlantic mackerel (Scomber scombrus), mahi-mahi (Coryphaena hippurus), and swordfish (Xiphias gladius). This will offer authorities with concrete and actionable information.

The system includes a processing sequence, the first step of which is acoustic discovery and classification of fish, depending on their typical speed and movement properties. Acoustic sensors also evaluate the size as well as the total biomass of the fish in the region. Upon identifying one of the six chosen species, the acoustic system activates the optical system, which includes a number of cameras and advanced data processing with different image identification algorithms using deep learning. As soon as the optical system confirms the identification of one of the species, it transmits the information initially through underwater acoustic communications, and subsequently by radio communications to a coastal station.

The focus of the scientists from IMDEA Networks is to design an efficient fish localization system and to visually recognize the selected fish species. The two groups from the Madrid-based research institute are the Ubiquitous Wireless Networks laboratory headed by Dr Paolo Casari, IMDEA PI and Scientific Manager for the project; and the Global Computing Group headed by Dr Antonio Fernandez Anta.

Using acoustics to localize specific fish species is very challenging. Firstly, the acoustic processing chain has to incorporate cost-effective components, and it needs to be highly energy-efficient. The signal processing algorithms deployed in the acoustic fish identification system have to strike a good tradeoff between complexity and accuracy. On top of this, the underwater environment contains many background acoustic noise sources and reflectors, and the signals from fish around the SYMBIOSIS system will be much weaker than acoustic interference coming from the environment. The algorithms need to be robust enough to cope with these shortcomings.

Dr Paolo Casari

For optics, the marine environment is characterized by low visibility and elements in the water volume that distorts the image. The big challenge is to secure good detection performances and to minimize false alarms. This needs to happen autonomously in a deep-sea environment, where there’s practically no possibility of human intervention.

Dr Diamant

The optical classification of fish species has its own particular challenges, too. There are very few pre-classified images available with which to train the deep-learning classifier. And many of the images that are available were taken under very different visibility conditions to those the system will encounter. In SYMBIOSIS, we are dealing with this uncertainty by leveraging public databases of fish pictures, many of them provided by scuba divers and underwater photographers. To address the lack of a large image dataset, we are starting with pre-trained neural networks for object recognition, and we’ll add more images from SYMBIOSIS test environments once we enter the experimental phase of the project.

Dr Fernández Anta

The European Commission’s research and innovation program, Horizon 2020, selected SYMBIOSIS for funding. Four institutions are taking part in the SYMBIOSIS project: the University of Haifa, Israel (coordinator); IMDEA Networks Institute in Madrid, Spain; Wireless & More company from Italy; and EvoLogics Gmbh from Germany. As part of the project, novel discovery and classification algorithms will be developed, dedicated hardware will be applied, and a huge number of marine trials will be completed. The project involves the development of a prototype that includes a network of cameras, a system of acoustic sensors, advanced processing units, and an energy unit for enabling autonomous activity.

The aim of the project is to sample the prototype system’s performances in three distinctive marine environments: deep Mediterranean, shallow Mediterranean, and a tropical environment in the Canary Islands. The project will be functional until November 2020 and will provide innovative solutions to enable distributed and large-scale monitoring of the marine environment, with a positive effect on marine biology studies, conservation, and policy-making for fisheries in Europe and across the globe.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type