Can machine learning be used for accurate species identification of beetles and other invertebrates? Researchers using carabid beetle data from the National Ecological Observatory Network created an algorithm that reached 85 percent accuracy on unidentified images. Eventually, they hope machine learning could one day be used to classify unidentified species in NEON bycatch and answer new questions about invertebrate diversity and abundance across North America.
With multiple species of termites responsible for structural damage in the U.S., rapid identification is a critical part of management efforts. A team of researchers has developed a faster ID method that uses a genetic tool called inter-simple sequence repeats.
Researchers at the University of Florida and the USDA-ARS have created a mobile app for bark beetle identification, allowing users to either play a beetle ID game or browse through the bewildering diversity of morphologies in the world of bark beetles.
A study evaluating tick identification via photos submitted to public health labs finds that IDs of the three most medically important tick species were correct more than 98 percent of the time.