A team of researchers in Taiwan has developed software driven by machine learning to accurately identify specimens—both soldiers and workers—of four different termite species. Their goal is to enable smartphone app termite ID for pest management pros and adapt the software's use to additional species.
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.