Researchers at UC Davis have devised an early detection system for sick wildlife.

Wildlife rehabilitation centers on the California coast often receive ailing marine birds suffering from domoic acid poisoning, which is caused by harmful algal blooms. The neurological disease afflicts California brown pelicans, red-throated loons, and other species, but the problem remains – how to warn other rehab centers on the coastline of the emergence of the disease? Researchers at UC Davis have now devised an AI system for real-time detection. (WIRED)

How it works

The UC Davis researchers trained an AI system on five years of data and more than 200,000 records to establish patterns of wildlife sicknesses.

Now their system scans the admission reports for sick animals at 30 California wildlife centers – these reports contain the animal’s species, age, reason for admission, and diagnosis.

The AI uses natural language processing (NLP) to classify the reports and match emerging data with the patterns it was trained on.

When there is a sudden spike or other anomaly in cases, the system issues an alert to wildlife experts, agencies, and researchers through the dashboard.

These alerts serve as early warnings for these people to take action to protect wildlife.

The bigger picture

“We wanted to use the data in an aggregate form to better help rehabbers to see the bigger picture, other than what they see at their individual centers,” says Devin Dombrowski, president of the Wild Neighbors Database Project and one of the authors of a paper that described the system and was published in the journal Proceedings of the Royal Society.

Early warnings for animals could also be useful to protect human beings.

“Wild animals can serve as an early indicator of diseases like West Nile virus,” said Study coauthor Terra Kelly, a veterinarian and epidemiologist at UC Davis. That disease is often first observed in sick birds before being detected in domestic animals and humans.

Related Story:   AI Protects Endangered Sea Turtles From Feral Pigs