Small in size and with a distinctive rounded dorsal fin, Māui’s dolphins are one of the rarest and most threatened dolphins at sea, with a known population of just 54. Decades of fishing practices, such as gillnetting off the west coast of New Zealand in the South Pacific, have brought this subspecies to the brink of extinction.
Now scientists and conservationists are using a combination of drones, artificial intelligence, and cloud technologies to learn more about these rare marine mammals. They say the solution can also be applied to study other species struggling to survive in the world’s oceans.
The effort is part of a growing trend toward using AI and other technologies to more effectively collect and analyze data for environmental conservation. For example, Microsoft AI for Earth‘s partner, Conservation metrics, combines machine learning, remote sensing, and scientific expertise to increase the scale and effectiveness of wildlife studies. NatureServeanother partner organization, leverages Esri ArcGIS tools and Microsoft cloud computing to generate high-resolution habitat maps for endangered species.
Scientists and conservationists with the non-profit group MAUI63 are using AI and other tools to support the conservation of Māui’s dolphins, named for the Polynesian demigod, Māui.
Māui’s dolphins play an important role in the ecological and spiritual fabric of New Zealand – the Maori name for New Zealand. They inhabit the waters off the west coast of the country’s North Island, also known as the north islandwhich translates as “the fish of Māui”.
Weighing in at 50 kilograms and measuring up to 1.7 meters when fully grown, Māui’s dolphins are one of the smallest members of the marine dolphin family and among the most elusive. They have white, gray and black markings and black rounded dorsal fins. Unlike human facial features, the markings do not vary between animals, which means that people cannot be identified with the naked eye. Conventional ways of monitoring and studying these fast-moving animals at sea have proven problematic and expensive. The researchers admit that relatively little is known about their behavior, particularly in winter when weather conditions deteriorate.
Now, MAUI63 believes it has a solution: an AI-powered drone that can efficiently find, track, and identify dolphins. The goal of their work, according to co-founder and marine biologist Professor Rochelle Constantine, is “to bring certainty to our uncertainty.”
“Currently all we know about them is from the summer. We know practically nothing about them in winter,” she says.
Constantine, along with technology and innovation specialist Tane van der Boon and drone enthusiast Willy Wang, formed MAUI63 in 2018. At the time, the Māui dolphin population was estimated at 63 individuals. That number has since dropped to 54.
Over drinks in a pub, Van der Boon, the group’s chief executive, and Wang came up with the idea of harnessing drones, machine learning and cloud computing to study dolphins. “I was getting interested in learning the computer; I actually saw how teaching computers to see is pretty amazing stuff. All the things that we could start to figure out and do really intrigued me,” he says.
The rounded fins of Māui’s dolphins differ from the more pointed fins of other dolphins. That meant existing computer vision models weren’t fit for identifying Māui’s dolphins. So van der Boon spent “a couple of months of nights and weekends” teaching himself how to build a model. He then painstakingly tagged images of Māui dolphins from Internet images to train him to identify them.
It was the first challenge of many. Four years of development, testing, and fundraising followed. The team also had to gain specialist qualifications to fly their 4.5 meter wingspan drone at sea. They saw their first Māui dolphins earlier this year.
“It was quite exciting. We were sitting in the van, the drone was 10 miles offshore, and we could see the AI spotting dolphins as we circled them,” says van der Boon.
The development has been aided by funding from New Zealand’s Cloud and AI Country scheme, which includes funding for projects with sustainable social impact, as well as support from Microsoft Philanthropies ANZ. The solution combines an 8K ultra-high definition still camera and a Full HD gimbal camera with an object detection model to detect dolphins and an open source algorithm originally developed for facial recognition. Hosted on Microsoft Azure, it collects data that will be used to identify individual animals by the shape and size of their dorsal fins and any scratches or marks on them.
MAUI63 is also developing an application called Sea Spotter, funded by Microsoft, which uses Azure functions to allow people to upload photos of Māui sightings and use an artificial intelligence algorithm to learn which individual they saw. According to conservationists, being able to identify the Māui dolphin’s habitat is crucial to understanding how to protect it against threats.
Constantine says the risk of Māui’s dolphins being caught bycatch in fishing boat nets is now “extremely low” thanks to a marine sanctuary that was established around their known habitat in 2008 and expanded in 2020. No However, they can go outside. these protected areas. That is why MAUI63 is working on an integration project with fishing companies to finally notify their crews of sightings made by the drone in real time.
Another threat is toxoplasmosis, a disease caused by a parasite that lives in cat feces. It enters the marine food chain through runoff from land, causing stillbirths and the death of marine mammals. “If you understand where dolphins are regularly, you can start to look at areas where toxoplasmosis might be entering the water and maybe something can be done about it,” van der Boon says.
The objective of MAUI63 is to provide scientifically sound information to conservation decision makers. “We are just trying to collect the data and make it available to anyone who needs it. We are not here to make decisions about how you should or should not protect yourself. That is key for us because everyone has very different views on it,” says van der Boon. At this stage, he says, it’s far from certain that MAUI63’s work will help prevent extinction, but what everyone can agree is that it’s worth a try.
Māui’s dolphins hold special significance to many indigenous Maori: they are considered guardian (tutors) who helped guide the waka (canoes) of their ancestors when they first came to New Zealand hundreds of years ago.
Environmental scientist Dr. Aroha Spinks says protecting them is essential to increasing the mauri, or life force, of the environment. “From a Maori point of view, which is also supported by science, the health of the environment affects the health and well-being of people,” he says.
MAUI63 plans to make their learnings and technology available to people who work with other marine species, as a potential project in Antarctica with the European Union Environmental Council. Constantine hopes the high-tech approach will be as innovative for other researchers as it has been for her. “It makes a world of difference to my world and the conversations I can have, and the information we can provide to governments and the public about how to make conservation decisions that really matter.”
Top Image: MAUI63 uses a combination of drones, artificial intelligence, and cloud technologies to learn more about Maui’s dolphins. Video courtesy of MAUI63.