The researchers took inspiration from the extraordinary transparent wings of the glasswing butterfly and used machine learning to test out different nanostructure design options that would offer similar benefits.
Natural surfaces like lotus leaves, moth eyes and butterfly wings display omniphobic properties which render them self-cleaning, bacteria resistant and water repellant - adaptations for survival that evolved over millions of years. Researchers have long sought inspiration from nature to replicate these properties in a synthetic material, and even to improve upon them. While the team could not rely on evolution to achieve these results, they instead used machine learning for the final product.
“When you create something like this, you don’t start with a lot of data, and each trial takes a great deal of time. We used machine learning to suggest variables to change, and it took us fewer tries to create this material as a result,” explains Paul Leu, associate professor of industrial engineering at the Swanson School, whose lab conducted the research.
“Machine learning and AI strategies are only relevant when they solve real problems; we are excited to be able to collaborate with the University of Pittsburgh to bring the power of Bayesian active learning to a new application,” said Bolong Cheng, PhD, research engineer at SigOpt.