New AI Study Shows We're Getting Better at Wildlife Conservation
Wed, April 21, 2021

New AI Study Shows We're Getting Better at Wildlife Conservation



Multiple studies have shown the troubling extent of many environmental crises across the world, but also shed light on the ways we can still protect our wildlife and rehabilitate what’s left. The World Wildlife Fund’s Living Planet Report revealed that the number of wild animals on Earth has halved in the past 40 years. Marine animal populations have also fallen by 40% overall, with turtles suffering in particular. But, the biggest declines in animal numbers have been seen in low-income, developing nations.

"Science is showing us the harsh reality of our forests, oceans, and rivers are enduring at our hands. Inch by inch and species by species, shrinking wildlife numbers, and wild places are an indicator of the tremendous impact and pressure we are exerting on the planet, undermining the very living fabric that sustains us all: nature and biodiversity,” Marco Lambertini, director of WWF International, said. 

Based on an analysis of more than 3,000 species’ populations, the researchers were able to categorize the causes of wildlife declines. The number one cause is exploitation (37%), followed by habitat degradation/change (31%), habitat loss (13%), and climate change (7%). Common threats to wildlife include logging, unsustainable agriculture, transportation, residential or commercial development, mining, and more. These threats have also been shrinking some of Earth’s most iconic ecosystems. For instance, 20% of the Amazon rainforest has disappeared in just 50 years, while about half of all shallow-water corals have been lost in the last 30 years.

According to The Guardian, a British daily newspaper, the report had also calculated humanity’s “ecological footprint.” It revealed that the global population is catching fish faster than the oceans can restock, cutting down trees faster than they regrow, emitting more climate-warming carbon dioxide than oceans and forests can absorb, and pumping water from rivers and aquifers faster than rainfall can replenish them.

"The statistics are scary, but all hope is not lost. We have an opportunity to design a new path forward that allows us to co-exist sustainably with the wildlife we depend upon. Our report sets out an ambitious agenda for change. We are going to need your help to achieve it,” Ken Norris, science director for the Zoological Society of London, said. 



AI in Wildlife Research

With the increasing decline of wildlife, experts have to rely on modern technologies, such as artificial intelligence, to monitor and protect the animals. Efforts to apply AI technology to the farthest reaches of the natural world have become so evident that it has become a necessity for many studies and experiments. AI tools and systems have also become more in demand with the advent of cheaper, more efficient, and more powerful hardware. 

With AI, researchers can teach a computer to complete a task with a huge dataset in a faster and more accurate away. The computer takes the data and learns the patterns of the data in order to predict, classify, or modify any subsequent input. For instance, conservationists would traditionally use camera traps to help them track, monitor, and better understand the ecosystem’s health and biodiversity of wildlife in remote areas. These devices are left in these areas for weeks or months. But with AI technology, researchers can now classify these animals in real-time, to detect people where they shouldn’t be, and even to identify individual animals.

"There's a perfect storm of AI and camera trap technology in terms of understanding animals from images. I think it's literally a revolution underway in terms of auto-identification of animals, whether it's from still cameras or video,” Robert Long, a conservation biologist at Seattle's Woodland Park Zoo, said. 

Many tech giants are also utilizing AI to help with conservation efforts. Microsoft’s AI for Earth, for instance, is a $50 million project that provides researchers access to AI tools to solve environmental challenges. It has been using Wildbook, a software program developed by Portland-based conservation tech nonprofit Wild Me, to help researchers automatically identify individual animals by their unique coat patterns or other hallmark features. Last 2018, it released an “intelligent agent” or bot that extracts whale shark videos on YouTube, which are often uploaded by tourists and divers sharing their vacation footage.

According to National Geographic, an American pay television network and flagship channel that is owned by National Geographic Partners, the data collected was able to help experts decide to increase the whale shark’s status from “vulnerable” to “endangered” in the IUCN Red List of Threatened Species, a global database that tracks and assigns conservation statuses.



Status of Wildlife Conservation

Many environmental and wildlife studies can show how scientists have utilized AI to better understand our wildlife and improve our conservation efforts. In a recent study, researchers used machine learning to analyze more than 4,000 studies on species reintroduction across four decades. It evaluated the outcomes of conservation programs by assessing the study abstracts with a form of AI that identifies positive and negative emotions expressed in a text called sentiment analysis. 

The team identified 4,313 species reintroduction studies published from 1987 to 2016 with searchable abstracts using the database Web of Science. They were able to build a model that could give each abstract an overall score based on several "off-the-shelf" sentiment analysis lexicons. The researchers also looked at the most common indicators of positive sentiment in their results to ensure their results were accurate, such as words like "success," "protect," "growth," "support," "help," and "benefit.” For negative sentiments, they looked for words like "threaten," "loss," "risk," "threat," "problem," and "kill." 

“Machine learning, and natural language processing, in particular, has the ability to sift through results and shine a light on success stories that others can learn from,” study author Kyle Van Houtan, the chief scientist at Monterey Bay Aquarium, said.

According to Science Daily, an American website that aggregates press releases and publishes lightly edited press releases about science, these words guided the researchers to indicate success and failure in studies. The trends they saw suggested greater conservation success. “Over time, there’s a lot less uncertainty in the assessment of sentiment in the studies, and we see reintroduction projects become more successful — and that’s a big takeaway,” Houtan said. 

Houtan added that investing in AI development would be worthwhile and help scientists working on some of the planet’s most pressing challenges. “We want to connect people with ideas, capacity, and technical solutions they might not otherwise encounter so we can bring some progress to these seemingly intractable problems,” he said.