NEW software will go a long way out collecting data about great white sharks.
Gone are the days that the absence of standardised procedures hampered efforts to manage and protect these species.
A marine biologist, an applied mathematician and a software developer from Stellenbosch University have combined their expertise to develop a custommade software package which may offer a solution to this problem.
Dr Sara Andreotti, a marine biologist in the department of botany and zoology, has collected more than 5000 photographic images of the dorsal fins of white sharks along the South African coastline as part of her research.
The trailing edge of the dorsal fin provides a unique identifier, analogous to a human fingerprint and over six years she manually built a database with information on when and where an individual white shark was sighted.
“I nearly lost my mind. I quickly realised that in the long term updating the database was going to consume more and more of my time.
“That is when I headed over to the applied mathematics division and asked for help. I was stunned when they were excited about my data,” she said. Prof Ben Herbst, a specialist in machine learning and Dr Pieter Holtzhausen, a software engineer studying for a PhD in applied mathematics, were excited to work with Andreotti’s database.
“We used an algorithmic technique called dynamic time-warping to match the fingerprints. With this technique, any data that can be turned into a linear sequence can be analysed.
This technique is often used in speech recognition software,” Holtzhausen said, While working with Michael Meyer, a marine scientist from the department of environmental affairs and shark activist conservationist Michael Rutzen from Shark Diving Unlimited, Andreotti realised the software needed some tweaking to fit the ideal of sustaining a large database for the long-term monitoring of the great white shark population.
“The software had to be capable of quickly matching the fin identification of a newly photographed shark with a possible existing match in the database and to automatically update the shark’s ID catalogue.
“The database also had to be userfriendly and structured in such a way that different researchers can use it over .