How Artificial Intelligence Could Revolutionize Archival Museum Research

A new study shows off a computer program’s specimen-sorting prowess

 The herbarium of Washington, D.C.’s Natural History Museum teems with pressed specimens of thousands of distinct plants.

(National Museum of Natural History)

 By Ryan P. Smith

When you think of artificial intelligence, the field of botany probably isn’t uppermost in your mind. When you picture settings for cutting-edge computational research, century-old museums may not top the list. And yet, a just-published article in the Biodiversity Data Journal shows that some of the most exciting and portentous innovation in machine learning is taking place at none other than the National Herbarium of the National Museum of Natural History in Washington, D.C.

The paper, which demonstrates that digital neural networks are capable of distinguishing between two similar families of plants with rates of accuracy well over 90 percent, implies all sorts of mouth-watering possibilities for scientists and academics going forward. The study relies on software grounded in “deep learning” algorithms, which allow computer programs to accrue experience in much the same way human experts do, upping their game each time they run. Soon, this tech could enable comparative analyses of millions of distinct specimens from all corners of the globe—a proposition which would previously have demanded an untenable amount of human labor…