Transforming Commercial Fishing with Computer Science and Artificial intelligence
The problem of unwanted catches has always been present in fisheries. In the EU, fishers must register all catches and bring them back to shore, which takes up time, space, and is very costly.
This is where artificial intelligence (AI) comes in. Researchers from Wageningen University and Research (WUR) in the Netherlands have joined forces with the Dutch fishing industry to develop an AI-based tool, Fully Documented Fisheries (FDF), funded by the EU.
The tool automatically recognises the size and species of each fish, streamlining the handling of fish and recording of catches on board vessels. Using a video camera that records the fish moving along the conveyor belt from the net unloading area to the hold of the vessel, an on-board AI unit decodes the video images to identify and record the species and size of each fish. This allows the fishers to quickly see if they were catching too many undersized fish or the wrong species, and effectively move to another fishing ground.
This project goes far beyond the existing systems. With this powerful algorithm, FDF makes it possible for the fishers to respect their landing and registration obligations, improve working conditions, and enable the fisheries to be more selective.
FDF not only improves the processing of catches on board and lessens the administrative burden, but it also monitors total catches in real time by size, species and weight, and generates detailed data that can be used for scientific purposes, stock estimates, research, and fisheries policy.
The project blends new technology to improve data collection in commercial fisheries, ultimately leading to sustainable fisheries. As Edwin van Helmond, fisheries biologist at Wageningen University and Research, says: “We have improved data, improved stock assessment, better research, better policy and, ultimately, a better fisheries sector. It’s really a win-win situation”.


