It’s on us to be better caretakers for this beautiful, warming planet that we (and a few million other species) call home. Thankfully, a computer vision algorithm learned how to do a job that once required the help of tens of thousands of citizen wildlife scientists in a fraction of the time.
The A.I. successfully labeled roughly three million images taken by Snapshot Serengeti, a project whose goal is to preserve biodiversity and seek out new phenomena by more carefully monitoring endangered species by filling the Serengeti with unobtrusive cameras.
This is all thanks to team of computer scientists, led by Mohammad Sadegh Norouzzadeh at the University of Wyoming, who together developed an algorithm to analyze the images. 30,000 volunteers had to manually label them. Now, this animal-identifying A.I. published in the journal Proceedings of the National Acamedy of Science allows these citizen scientists to devote their time to conservation endeavors instead of spending hours sorting through photos.
One of the many animals this algorithms might spot in the wild.
“We can save them time and provide them with information quickly and accurately,” Norouzzadeh told Inverse. “The current process they’re using is very slow so it can give them outdated information. Machine learning can supply up-to-date information so they can plan for conservation efforts. That’s why we think this is such a critical advancement for ecology.”
Getting data to ecologists quickly will allow them to take immediate action to deal with ongoing issues. Norouzzadeh is also confident that his algorithm also won’t take over the need for citizen scientists. Roughly 0.7 percent of the images still need a human’s touch to label because the A.I. can’t tell exactly what’s happening.
That makes the Norouzzadeh’s algorithm the perfect lab assistant for overburdened ecologist and citizen scientists.
