As the march of technology continues to advance, not only have humans benefited from its advancement, but researchers are finding ways to use new tools to help many vulnerable animal species as well.
Scientists at the Benioff Ocean Science Laboratory collaborated with the Marine Mammal Center to deploy technology-filled buoys off the coast of San Francisco as part of the “Whale Safe” initiative, aimed at combating incidents of whale deaths due to collisions with ships and cargo ships. to the sea
“Whale mortality from ship collisions is one of the main sources of death for endangered whales, there is nothing more tragic than seeing one of these whale ship collision victims.
“About 80 endangered whales on the US West Coast die every year, and that’s too many whales, but this is a solvable problem,” Douglas McCauley, director of the Benioff Ocean Science Laboratory, said in a video posted on his YouTube channel.
The program uses acoustic monitoring instruments enabled by artificial intelligence (AI) to detect the presence of whales in coastal waters, using buoys equipped with hydrophones (underwater microphones that detect whale vocalizations) placed on the ocean floor, which sends the captured data to a small computer on the buoy and then via satellite to scientists for review.
These vocalizations can be used to identify whale species and, when analyzed by the AI algorithm along with other data points such as ocean conditions, recent sightings by trained naturalists, and location data from 104 blue whales tagged by satellite, can help predict presence. of whales in the area and the likelihood of an encounter.
Whale Safe then summarizes this information with data from the Automatic Identification System (AIS), a tracking system used by large vessels and companies to navigate and avoid collisions with each other, to make recommendations for vessels in the shipping lanes likely to cross a whale to adjust its speed, in order to minimize the risk of impact.
More AI-powered conservation efforts
In other parts of the world, conservationists have been using similar AI-powered technology to help protect various endangered species.
Machine learning systems have been trained to spot poachers in places like Zambia’s Kafue National Park to stop illegal fishing, with thermal cameras installed along a 19km stretch across Lake Itezhi -Tezhi to identify illegal boat crossings and alert park rangers, eliminating the need to monitor the area.
Some initiatives use AI systems to observe changes in the environment, such as the loss of surface water in Brazil, and others use it to manage the huge pools of data captured by camera traps and microphones of animals in endangered to identify and monitor their populations.
Google’s conservation efforts along with partners such as the World Wildlife Fund (WWF) and Conservation International have also involved artificial intelligence in this way, with its Wildlife Insights system leveraging photos taken from various projects of camera traps from around the world to understand how populations of people are in danger of extinction. species are changing.
“Camera traps have become an essential tool for studying wildlife. Often deployed in remote areas for long periods, they can take thousands of photos of animals that researchers rarely see up close.
“But sifting through all these images can take weeks, even months. Tagging and analyzing the photos requires extensive training, and uploading and sharing them is a file transfer nightmare,” WWF wrote on its website, and added that the deployment of Wildlife Insights would leverage AI to speed up the process and allow conservationists to act more quickly to protect wildlife.
The Wildlife Insights system has also previously been used to tag and analyze images taken during a mammal and bird monitoring program in the Pasoh Forest Reserve in Negri Sembilan.
Initiatives such as the Protection Assistant for Wildlife Safety (PAWS) developed at the University of Southern California, to protect endangered animals such as elephants, tigers, antelopes, deer, macaques and leopards, to name a few – just a few, have also had successful trials in Uganda and Cambodia since 2014.
Using a machine learning algorithm, the PAWS system takes data from past poaching activity and uses it to predict where poachers are likely to appear.
The algorithm uses these predictions to suggest patrol routes for risky locations, which are also changed after a period of time to be random, preventing poachers from learning patrol patterns.
More recent developments in the use of AI in wildlife conservation efforts also tend to include drone technology, such as the SnotBot, a camera- and petri-dish-equipped drone designed to capture photographs of whales and mucus samples containing DNA, which can provide scientists with valuable data about whales.
Algorithms used to identify poachers and study the population of vulnerable animal species have also been combined with these camera-equipped drones.
This includes the efforts of Madeline Hayes, a drone pilot and graduate student at Boston University in Massachusetts, with her AI model trained to identify and count both jumping penguins and black-fronted albatrosses in the Falkland Islands in the photos captured with drones. as well as projects such as Conservation AI which combines machine algorithms to identify poachers together with images taken by drones.