With Humans Indoors, Animals Go Wild


Across the globe, wildlife is exploring empty places usually occupied by people.

As humans are remaining indoors in response to the coronavirus pandemic, it appears that wildlife around the world took notice of our absence. There seems to be a never-ending list of animals becoming emboldened during this time to explore areas that are typically heavily populated: Buffalo have taken to the deserted highways in India. Mountain lions have rested in trees in Boulder, Colorado. Wild boar walk the streets of Barcelona while peacocks strut along open streets in Brazil.

Rats in New York City have somehow become even more confident in their quest for food. And a groundhog appeared to stare down two dogs watching through a window while eating a piece of pizza, which probably doesn’t have anything to do with the lockdown, but was a welcome distraction on social media nonetheless.

The Washington Post reports that a tribe of goats overtook the streets of Wales. Video taken by resident Andrew Stuart shows the animals nonchalantly roaming the empty streets and helping themselves to a meal of hedges and flower gardens.

According to SFGate, an employee from Yosemite National Park claims that since the park closed to the public in late March, the sightings of large animals including bears, bobcats, and coyotes have gone up fourfold.

“It’s not like [bears] aren’t usually here,” Yosemite employee Dane Peterson tells SFGate, “it’s that they usually hang back at the edges, or move in the shadows.”

In Mexico, crocodiles that generally stay hidden in lagoons near the beaches in La Ventanilla, Oaxaca, have been coming out in the open since the beaches were closed to the public about two weeks ago, Mexico News Daily reports.

Endangered sea turtles have also taken advantage of empty beaches to nest in Brazil and Florida. It’s too early to tell how lockdown measures will affect sea turtle numbers when it is time for the eggs to hatch. Decreased traffic could create less artificial light to confuse the hatchlings about which direction to go, Shanon Gann, the program manager at Brevard Zoo Sea Turtle Healing Center in Florida, tells weather.com.

A mixed bag for animals that depend on humans

In urban areas where wildlife is, for better or worse, dependent on human activity, the lockdown brings new challenges. The New York Times describes scenes in Thailand, where macaques have come to rely on humans for food. Their populations have become so dense in these areas because of that food supply that people staying home has quickly created a scarcity of resources, leading to aggressive behavior.

The same goes for duck ponds, ecologist Becky Thomas of Royal Holloway in London writes for The Conversation. Although feeding bread to ducks is harmful to their health and the water around them, there will be an adjustment as they compete for healthier resources.

Thomas notes that decreased traffic will lead to less hedgehog roadkill as well as reduced noise pollution that negatively affects the ability of bats, birds, and other animals to communicate.

The lack of human presence hasn’t benefited all animals, as the Times reports, particularly animals in African nature preserves. With fewer tourists around, poachers are killing rhinos with an increased frequency in Botswana and South Africa.

“We’re in a situation of zero income, and our expenses are actually going up all the time just trying to fight off the poachers and protect the reserve,” Lynne MacTavish, operations manager at Mankwe Wildlife Reserve in South Africa, tells the Times. “To say it’s desperate is an understatement. We’re really in crisis here.”

Some of the earliest widely shared reports of wildlife emerging in populated areas turned out to be false, according to National Geographic’s debunking of some of the more common untruths. One such tale says baby elephants in China got drunk on corn wine and passed out in a tea field, which might be very relatable during these times, but never happened. The absence of boats in the canals of Venice brought claims of dolphins appearing for the first time in decades, but the images were from the island of Sardinia, nearly 500 miles away.

There may not be dolphins in Venice, but the waters have gotten astonishingly clear, as the lack of gondolas and other boats on the water haven’t been stirring up sediment, CNBC reports.

Right now, it isn’t clear what the long-term effects of this lockdown will be on nature, primarily because this is occurring when many species in the Northern Hemisphere are mating, giving birth, or coming out of hibernation. Air pollution in some areas has been cut in half since the lockdowns began, Forbes reports, due to the lack of emissions from vehicles and factories. Some cities notorious for smoggy skies, including Los Angeles and Beijing, are enjoying some of the cleanest air they’ve experienced in decades. While the tolls of air pollution on human health are widely known, animals are also at risk, according to the National Wildlife Refuge System.

As many are still sheltering-in-places as we approach the 50th annual Earth Day, this resurgence of wildlife is giving some cause for hope that this evidence will ultimately lead to better policies to protect the environment and create a new normal.

“I am hopeful,” anthropologist Jane Goodall tells the Post. “I am. I lived through World War II. By the time you get to 86, you realize that we can overcome these things. One day we will be better people, more responsible in our attitudes toward nature.”

https://www.the-scientist.com/news-opinion/with-humans-indoors-animals-go-wild-67434?utm_campaign=TS_DAILY%20NEWSLETTER_2020&utm_source=hs_email&utm_medium=email&utm_content=86538478&_hsenc=p2ANqtz-92e5YchE_c5eEZJOR2VWChyXs-TUYFALDBiX0cEwNWRvtMhsuRr4MWSGBf0DCvU1hKkYi4eEAJ3QErLAitWrBijvumwg&_hsmi=86538478

Researchers Use Artificial Intelligence to Identify, Count, Describe Wild Animals


Motion sensor “camera traps” unobtrusively take pictures of animals in their natural environment, oftentimes yielding images not otherwise observable. The artificial intelligence system automatically processes such images, here correctly reporting this as a picture of two impala standing.

A new paper in the Proceedings of the National Academy of Sciences (PNAS) reports how a cutting-edge artificial intelligence technique called deep learning can automatically identify, count and describe animals in their natural habitats.

Photographs that are automatically collected by motion-sensor cameras can then be automatically described by deep neural networks. The result is a system that can automate animal identification for up to 99.3 percent of images while still performing at the same 96.6 percent accuracy rate of crowdsourced teams of human volunteers.

“This technology lets us accurately, unobtrusively and inexpensively collect wildlife data, which could help catalyze the transformation of many fields of ecology, wildlife biology, zoology, conservation biology and animal behavior into ‘big data’ sciences. This will dramatically improve our ability to both study and conserve wildlife and precious ecosystems,” says Jeff Clune, the senior author of the paper. He is the Harris Associate Professor at the University of Wyoming and a senior research manager at Uber’s Artificial Intelligence Labs.

The paper was written by Clune; his Ph.D. student Mohammad Sadegh Norouzzadeh; his former Ph.D. student Anh Nguyen (now at Auburn University); Margaret Kosmala (Harvard University); Ali Swanson (University of Oxford); and Meredith Palmer and Craig Packer (both from the University of Minnesota).

Deep neural networks are a form of computational intelligence loosely inspired by how animal brains see and understand the world. They require vast amounts of training data to work well, and the data must be accurately labeled (e.g., each image being correctly tagged with which species of animal is present, how many there are, etc.).

This study obtained the necessary data from Snapshot Serengeti, a citizen science project on the http://www.zooniverse.org platform. Snapshot Serengeti has deployed a large number of “camera traps” (motion-sensor cameras) in Tanzania that collect millions of images of animals in their natural habitat, such as lions, leopards, cheetahs and elephants. The information in these photographs is only useful once it has been converted into text and numbers. For years, the best method for extracting such information was to ask crowdsourced teams of human volunteers to label each image manually. The study published today harnessed 3.2 million labeled images produced in this manner by more than 50,000 human volunteers over several years.

“When I told Jeff Clune we had 3.2 million labeled images, he stopped in his tracks,” says Packer, who heads the Snapshot Serengeti project. “We wanted to test whether we could use machine learning to automate the work of human volunteers. Our citizen scientists have done phenomenal work, but we needed to speed up the process to handle ever greater amounts of data. The deep learning algorithm is amazing and far surpassed my expectations. This is a game changer for wildlife ecology.”

Swanson, who founded Snapshot Serengeti, adds: “There are hundreds of camera-trap projects in the world, and very few of them are able to recruit large armies of human volunteers to extract their data. That means that much of the knowledge in these important data sets remains untapped. Although projects are increasingly turning to citizen science for image classification, we’re starting to see it take longer and longer to label each batch of images as the demand for volunteers grows. We believe deep learning will be key in alleviating the bottleneck for camera-trap projects: the effort of converting images into usable data.”

“Not only does the artificial intelligence system tell you which of 48 different species of animal is present, but it also tells you how many there are and what they are doing. It will tell you if they are eating, sleeping, if babies are present, etc.,” adds Kosmala, another Snapshot Serengeti leader. “We estimate that the deep learning technology pipeline we describe would save more than eight years of human labeling effort for each additional 3 million images. That is a lot of valuable volunteer time that can be redeployed to help other projects.”

First-author Sadegh Norouzzadeh points out that “Deep learning is still improving rapidly, and we expect that its performance will only get better in the coming years. Here, we wanted to demonstrate the value of the technology to the wildlife ecology community, but we expect that as more people research how to improve deep learning for this application and publish their datasets, the sky’s the limit. It is exciting to think of all the different ways this technology can help with our important scientific and conservation missions.”

The paper that in PNAS is titled, “Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning.”

http://www.uwyo.edu/uw/news/2018/06/researchers-use-artificial-intelligence-to-identify,-count,-describe-wild-animals.html