3-D imaging, AI reveal stories hidden in shells

A clam shell may be a familiar find on the beach, but its intricate curves and markings tell a rich tale. For centuries, biologists have collected, drawn, measured and compared the shells of bivalve species, pursuing knowledge about how the environment and behavior shape biodiversity. Now, University of Chicago scientists are combining high-resolution 3-D imaging with new geometric deep learning approaches to reveal a fuller version of the story hidden in shells. Prof. David Jablonski has pioneered the study of the evolution and extinction dynamics in marine life for nearly four decades. But over the last two years, his research group has moved into the third dimension, using a campus micro-CT scanner to create 3-D images of more than 3,000 shells from clams, oysters, mussels, and other members of the bivalve class collected by scientists and museums around the world.