“We got another big shipment coming in!” the scruffy voice of a port authority officer barked over the noise of the coastal harbor. Orders being barked, the deafening sound of flies, bellowing boat horns and engines… the commotion was nonstop. Such was the life of enforcement and customs personnel whose purpose was to protect threatened animals in both legal and illegal trades. Horns, scales, jaws, fins – the list of what to look out for and identify was seemingly endless!
More than two decades after the adoption of the International Plan of Action for Conservation and Management of Sharks (IPOA-SHARKS) in 1999, the globalized market for shark products is largely unknown. One thing, however, that always stands out is the shark fins. Depending on what species they come from, they can come with one heck of a price tag. And while many countries and Regional Fisheries Management Organizations have banned finning (the practice of removing a shark’s fins and discarding its carcass at sea) since 2004, shark products can still be sold… both legally and illegally.
Legally, the fins and trunks are separated upon landing of the whole animal. Due to this, there is an ongoing need to identify these shark products along the supply chain, especially if they are a listed in the appendices of the Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES). The identification of fins in fisheries landings before they enter international trade is a major limitation for CITES compliance. And while it seems like it has a simple solution – “Just identify the dang thing!” as one anonymous commentator on Twitter joked – shark fin species identification is complex, especially in a global context.
“Being able to detect fins of species listed in the CITES Appendices in case they are already detached at the landing sites, is a first step necessary to detect the sustainability and legality of the capture, necessary to issue the certification needed for their shipment and full traceability,” explained Monica Barone, fisheries resources consultant and shark specialist for the Food and Agriculture Organization of the United Nation (FAO). Carlotta Mazzoldi, Professor of the Department of Biology, University of Padova, agrees: “Any conservation action needs a full understanding of the actual threat to the species. Inclusion of shark species in CITES does not ensure the actual enforcement of these regulations if no effective controls are performed.”
Official CITES statistics of import and export of shark commodities largely under-report species and quantities traded on the basis of catch data and analysis of trade contents. Enter iSharkFin. FAO and the University of Vigo started a collaboration in 2014 to develop the system, based on a machine learning technology that can learn from different data inputs. “In the case of iSharkFin, the algorithm learns by adding sets of fins with new morphological features, thereby increasing identification performance. The software iSharkFin V1.0, launched in 2015, was designed as a user interface to both predict an identification for an unknown dorsal fin based on current inputs, and to generate the new data inputs to further train the learning algorithm. Successive versions have been released with refinements, the most recent (V1.4) allowing users to select qualitative variables such as the fin’s tip colour to refine subsets of morphometric variables,” the authors of this new study illustrate.
Barone and her team reported on the current performance of the iSharkFin system, which aims to allow users to identify the species of a wet shark dorsal fin from its image. Using photographs of over a thousand wet dorsal fins from 39 shark species, collected in 12 countries, they trained the algorithm over a four-year period. “Tools for CITES enforcement, such as iSharkFin must reach a significant degree of reliability. This is important for the credibility of the tool, and to convince front-line customs officers and others around the globe to start working with it,” said co-author Frederik Mollen, authorized CITES expert for sharks and rays. “For us, as developers of the tool, we wanted to be transparent about its performances. It also gave us the opportunity to check the strengths and weaknesses of subsequent versions of the tool, and to make it perform even better in the future.”
The hope is that by continually training the iSharkFin system, it can correctly predict new cases. As the researchers fed the program more and more images, the accuracy that iSharkFin showed was variable but did increase, reaching 85.3% and 59.1% at genus and species level respectively. The accuracy in predicting CITES-listed sharks versus unlisted sharks was 94.0% based on the 39 species currently represented in the baseline.
Promising… but iSharkFin won’t be enough to identify shark fins that are being traded legally and illegally. So-authors and shark fin identification experts Lindsay Marshall and Jenny Giles say: “It is a problem that will need to be tackled from many angles using many resources. Expertise is crucial. We have been able to identify CITES species vs non-CITES species within our dataset with a good degree of reliability. [For] CITES, this will be a handy screening tool when developed for specific settings. With regard to enforcement, the specimens will still need to be subject to expert forensic identification using either morphology or DNA.”
While this latest study is quite technical and is intended for those working with wet dorsal fins in fisheries landings, the authors hope it can increase the awareness of the public about the source of the food they eat. “I think that this paper may further raise public awareness about the conservation of shark species and our responsibility as consumers. Our choices may support and even push towards conservation actions or, on the contrary, incentivize the trade of endangered species,” concludes Mazzoldi.