AI for Wildlife Conservation
Sat, April 10, 2021

AI for Wildlife Conservation

Since 1970, humanity has wiped out over 60% of the planet’s wildlife. Scientists have warned that Earth has begun a sixth mass extinction as an estimated 30,000 species per year are being driven to extinction / Photo by: givaga via Shutterstock

 

Since 1970, humanity has wiped out over 60% of the planet’s wildlife. Scientists have warned that Earth has begun a sixth mass extinction as an estimated 30,000 species per year are being driven to extinction. Other recent reports showed that humankind has destroyed half of the plants and 83% of all mammals since the dawn of civilization. With the current status of our planet, researchers suggested that it would take five to seven million years for the natural world to recover. 

“This is far more than just being about losing the wonders of nature, desperately sad though that is. This is actually now jeopardizing the future of people. Nature is not a ‘nice to have’—it is our life-support system,” said Mike Barrett, executive director of science and conservation at World Wildlife Fund, an international non-governmental organization founded in 1961, working in the field of wilderness preservation and the reduction of human impact on the environment. 

Cutting-edge technology, like artificial intelligence, is now being used to fight the impacts of global warming. For instance, researchers recently used AI to observe not only elephant behavior in Africa but also human behavior, specifically poacher behavior. Peter Wrege, a Cornell University researcher, stated that AI can process large amounts of information to determine where the elephants are and how many they are. 

According to National Public Radio, an American privately and publicly funded non-profit membership media organization, Wrege had custom audio recorders made and placed them in the rainforest to collect jungle sounds. The team would return to the forest, locate the recorders, change the batteries, put in new audio cards, and start all over again every three months. With thousands of hours of recordings, there’s one problem: sorting through all the recordings to find the elephant voices they wanted.

Thus, the team used AI and machine learning to listen and analyze the data. The findings of the study can be used by the authorities not only to monitor the elephants but also move into areas where poachers may be illegally hunting. This is the latest example of how AI can help in preserving wildlife and our natural resources.

AI in Generating Information

Gathering information about the world’s species, their status, and how we could save them has been an extremely challenging task. Aside from the fact that it takes months or years to get the data, it is often not that accurate. Thus, scientists started using new technologies such as acoustic sensors, cryptic cameras, satellite imagery, and citizen science apps to assess and predict the health and behavior of species and ecosystems. These have also been utilized to determine the threats they face.

According to Mongabay.com, an online site that publishes news on environmental science, energy, and green design and features extensive information on tropical rainforests, AI has allowed scientists to monitor natural systems and make predictions with high accuracy. This is because AI algorithms can classify data from the various types of sensors used by scientists, apply modeling results to create reproducible code, and create user interfaces. 

Gathering information about the world’s species, their status, and how we could save them has been an extremely challenging task. Aside from the fact that it takes months or years to get the data, it is often not that accurate / Photo by: clkraus via Shutterstock

 

There have been several AI applications that are beneficial for conservation science. For instance, researchers from Carnegie Mellon University in Pennsylvania used machine learning and game theory to optimize patrol routes to catch poachers. An AI-infused computer vision was also used by Wild Me, a nonprofit based in Portland, Oregon, to identify individual animals of endangered species while reducing fieldwork and image processing time. At the same time, AI and remote-sensing were used to automate wildlife surveys and machine learning to classify animals’ acoustic activity.

Donald Croll and Bernie Tershy, biologists from the Conservation Action Lab at UC Santa Cruz, started developing acoustic technologies for monitoring seabird populations as a research project. According to Phys.org, an internet news portal that provides the latest news on science, they eventually started a company called Conservation Action Lab to provide wildlife monitoring services.

"We want to increase the efficiency of conservation monitoring. We do these conservation interventions, like removing invasive species from an island, but ongoing monitoring to track how seabird populations recover after the intervention is expensive. AI tools can help us automate that,” Croll said.

Ecosystem Mapping and Predicting Poaching

AI can also be used to facilitate ecosystem mapping as well as to create a bioresource atlas for a country. This was discovered after a Bengaluru-based research organization gathered huge amounts of data but didn’t know how to analyze those data. Nitin Pandit, director of Ashoka Trust for Research in Ecology and the Environment, stated that AI tools have allowed researchers to document biodiversity data.

“AI is helping organizations understand life on Earth—where species are, how many there are, and how their behavior is changing over time as their habitats change,” Lucas Joppa, the chief environmental officer of Microsoft, said. 

According to the Hindustan Times, an online site that provides exclusive top stories of the day, today’s headlines from politics, business, technology, and more, an AI-based tool has also been developed to forecast wildlife poaching based on ranger-collected data and evaluation through field tests. This tool was designed by Fei Fang of Carnegie Mellon University in Pennsylvania and aimed to predict a heat map of poaching threats. Fang stated that it was confirmed that the predictions have resulted in detecting snares and traps and forest rangers catching poachers at a higher rate than before.

“Every snare removed means a potential saving of elephant life. It’s not just about making predictions about poaching threats but PAWS also assists rangers to design the most effective patrol routes, even in tough terrains,” she added. 

These AI tools are proof that technology can do a lot of ways to protect wildlife and conserve our environment. In the next few years, we can expect that more and more of these tools would be developed. 

AI can also be used to facilitate ecosystem mapping as well as to create a bioresource atlas for a country / Photo by: Michal Sarauer via Shutterstock