Glass is an extremely useful item as it has a lot of practical applications. In the sphere of technology, glass is used in many devices as displays on tablets, laptops as well as solar cells. Here, glass allows light to pass through. Now, imagine if the same glass that allows light to pass can also repel water, other liquids and dirt, too. 

Researchers have done something like that now. Taking inspiration from the wings of a glasswing butterfly, a team from the University of Pittsburgh’s Swanson School of Engineering has found a new nanostructure glass that offers clean and clear vision across a wide wavelength. It also has anti-fogging properties.

The researchers recently explained their work in a paper in Materials Horizons, and also presented this work during a workshop on how AI can help manage climate change at the ICML conference.

The new type of glass has random nanostructures that are smaller than the wavelength of visible light. What this means is the glass allows a lot of light to pass through. In scientific terms, it has a transparency of 99.5 per cent when random nanostructures are present on either side of the glass. 

Such a high level of transparency can be used to ensure a device’s display requires lesser power than before. It allows for higher battery life. Besides, being anti-reflective in higher angles, the glass can improve viewing angles. Low haze in the glass helps in ensuring the text and image output is clear.

“The glass is superomniphobic, meaning it repels a wide variety of liquids such as orange juice, coffee, water, blood, and milk,” says Sajad Haghanifar, lead author of the paper and a doctoral candidate in industrial engineering at Pitt. “The glass is also anti-fogging, as water condensation tends to easily roll off the surface, and the view through the glass remains unobstructed. Finally, the nanostructured glass is durable from abrasion due to its self-healing properties — abrading the surface with a rough sponge damages the coating, but heating restores it to its original function.”

Scientists were inspired to develop the structure after observing that certain natural objects had omniphobic properties, meaning they can repel liquids without changing their properties. Butterfly wings and moth eyes have this kind of property, besides being able to clean itself and keep free of bacteria. Tapping on these properties, researchers used machine learning to come up with the nanostructured glass. 

“Something significant about the nanostructured glass research, in particular, is that we partnered with SigOpt to use machine learning to reach our final product,” says Paul Leu, PhD, associate professor of industrial engineering, whose lab conducted the research. “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.”

“Bayesian optimisation and active search are the ideal tools to explore the balance between transparency and omniphobicity efficiently, that is, without needing thousands of fabrications and hundreds of days,” says Michael McCourt, PhD, research engineer at SigOpt. Bolong Cheng, PhD, fellow research engineer at SigOpt, adds, “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.”

The project, partly supported by National Science Foundation CAREER Award, was carried out by Sajad Haghanifar and Paul Leu from Pitt’s Swanson School of Engineering; Michael McCourt and Bolong Cheng from SigOpt; and Paul Ohodnicki and Jeffrey Wuenschell from the US Department of Energy’s National Energy Laboratory.