Fish emergency: where the man/machine integration promotes the sustainability of our seas

The numbers are shocking. Overexploitation of the world’s fish stocks is growing at an alarming rate according to FAO: global fish production is approaching its sustainable limit, with around 90% of the world’s stocks now fully or overfished and a 17% increase in production forecast by 2025.

One of the keys to sustainable fishing is, according to some, the use of human monitors to watch what is being scooped up from the sea. For example, in the United States fishing boats are routinely accompanied by independent observers who track compliance with fishing regulations. In other countries’ waters, it’s a whole different story: in the stretch of sea that goes from Indonesia to Hawaii – the source of the majority of the world’s tuna harvest – a mere 2% of fishing operations are watched by observers. A percentage that is ridiculous for scientists, both to understand the effects intensive fishing is having on the depletion of this area and of imperiled species, and to check how large numbers of valuable fish – including the yellowfin tuna or bigeye tuna varieties – are being harvested illegally.

Can digital tools help in this respect? An article recently published on Fast Company traces a possible scenario, reporting that those government and independent agencies hoping to halt overfishing are turning to some of the same software tools that let social media sites recognize faces in photos.  In this context, we can mention the positive efforts made by Nature Conservancy, a nonprofit environmental association which, by effectively automating part of the job of the human observer, uses cameras to record what creatures are caught and sophisticated software to classify them by species, so as to get a fuller picture of legal harvests and detect unlawful operations.

The process is very similar to the one used every day by companies to have detailed records and predictions of how users behave online; however, in this case, we are dealing with fishing boats and shoals. Nature Conservancy is working with governments in regions at risk, including in Palau, the Marshall Islands in Micronesia and the Solomon Islands in Oceania, to implement these monitoring programmes, capturing video footage of fishing vessels instead of placing observers on each boat. The method still produces huge amounts of raw video that need to be manually analysed by hand, but the objective is to process that video material in a more automated way, thus controlling by hand only the material that is truly worth analysing.

This type of intervention is becoming more and more frequent: for example, the National Oceanic and Atmospheric Administration (NOAA) is investigating using electronic monitoring in fisheries across the U.S. from the Atlantic to the Pacific, such as on smaller boats in Alaska that catch fish like cod and halibut. “We’ve been working to develop electronic monitoring as an alternative to human monitors,” says Chris Rilling at NOAA. “Right now, fishing boats participating in a voluntary pilot program are equipped with cameras and with hard drives that are periodically shipped to the central headquarters for human review, but the agency is developing sets of training data for machine learning algorithms to use, with an eye toward integrating automated classification around 2019.

And even if the machine learning algorithms aren’t perfect, they can still provide valuable data to the scientists who are asked to interpret them correctly. Innovations are also being tested to electronically monitor fish populations while they’re still underwater. For instance, one device that debuted in 2015 uses a low-powered computer and sonar system attached to the seafloor to automatically survey fish populations in a given stretch of water, sending signals to the surface. This summer, this solution will be extended to a remote area of the Arctic usually difficult to access: replacing expensive icebreaker ships, the sensor will remain in place to track fish populations and movements after the winter freeze.

Much remains to be done, yet the progress of the man-machine collaboration is worthy of attention where, as in this case, it is designed to improve the environmental sustainability of the seas which we will leave to future generations.