SusTunTech paper at PRADS conference online

PRADS (International Symposium on Practical Design of Ships and Other Floating Structures) is a traditional series of triennial symposia, aiming at an international exchange of new knowledge and achievements with regard to the design, research and development of ships and other floating structures. Dr. Yi Zhou was selected to give a talk and publish a paper about the fuel consumption forecasting models being developed in SusTunTech within a collaboration of Newcastle University, University of Basque Country and AZTI.

Read the original work here:

Ecological Informatics

SusTunTech project identifies and measures tropical tuna species through electronic monitoring

An article written by members of the SusTunTech project, and led by AZTI, on the comparison of monitoring by human observers and electronic monitoring with automatic processing on board tuna vessels reveals that 1) fishery monitoring programs are essential for the effective management of marine resources; 2) monitoring by human observers implies a high cost; 3) electronic monitoring performs effective monitoring and is an alternative or complement to human observers; 4) With this system, fish are first segmented individually using a deep neural network (Mask R-CNN); 5) Those segments are passed through another deep neural network (ResNet50V2) to classify them by species and estimate their size distribution; 6) Fish classification with an accuracy of more than 70% is achieved with this method; 7) Size distribution estimates are aligned with official port measurements.

Read the original work here:

SusTunTech project analyse fishing behaviour to reduce fuel consumption

An article written by members of SusTunTech project, and led by AZTI, about comparing fish aggregating device (FAD) and free-swimming school (FSC) fishing strategies in tropical tuna purse seiner reveal that: 1) Cruising is the most dominant activity in a fishing trip of these fleets; 2) Main engine consumes 75% of the total fuel consumption; 3) FAD fishing often in more fuel intensive due to longer trips aiming at the FADs with higher biomass without considering distance; 4) FAD fishing presents higher success than FSC; 5)  both FAD and FSC fishing are more energy efficient than longline, trolling, or pole and line fisheries for Atlantic tuna, but similar or slightly less efficient than Maldivian pole and liners.

Read the original work here:

Towards a framework for fishing route optimization decision support systems: Review of the state-of-the-art and challenges

Route optimization methods offer an opportunity to the fisheries industry to enhance their efficiency, sustainability, and safety. However, the use of route optimization Decision Support Systems (DSS), which have been widely used in the shipping industry, is limited in the case of fisheries. In the first part, this work describes the fishing routing problems, reviews the state-of-the-art methods applied in the shipping industry, and introduces a general framework for fishing route optimization decision support systems (FRODSS). In the second part, we highlight the existing gap for the application of DSS in fisheries, and how to develop a FRODSS considering the different types of fishing fleets. Finally, and using the diverse Basque fishing fleet as a case study, we conclude that fishing fleets can be summarized into four main groups whose fishing routes could be optimized in a similar way. This characterization is based on their similarities, such us the target species, fishing gear, and the type and distance to the fishing grounds. These four groups are: (i) small-scale coastal fleet; (ii) large-scale pelagic fleet; (iii) large-scale demersal fleet; and (iv) the distant-water fleet. Distant-water vessels are currently the fleet that can more easily benefit from FRODSS, and they are used as an example here. However, the rest of the fleets could also benefit through adequate adaptation to their operation characteristics, driven by their specific fishing gear and target species.

Read the original work here: