Credit: Google News
MORGANTOWN — A new machine-learning model developed by a West Virginia University student has potential applications in the energy, environmental and health-care fields.
The model, which can be used to predict adsorption energies — i.e., adhesive capabilities in gold nanoparticles — was developed by Gihan Panapitiya, a doctoral physics student from Sri Lanka.
Gold nanoparticles have historically been used by artists to bring out vibrant colors via their interaction with light. Now they are increasingly used in high-technology applications such as electronic conductors and others.
“Machine learning recently came into the spotlight, and we wanted to do something linking machine learning with gold nanoparticles as catalysts,” Panapitiya said.
“When I was thinking about a research area, I found that predicting adsorption energies of this particle property is very hard, and the knowledge on adsorption energies is important for catalytic applications in energy, environmental and even biomedical applications,” Panapitiya said.
“I thought if I could use machine learning to predict these adsorption energies without much difficulty, that would enable researchers to easily find nanoparticles with desired properties for a given application,” he said.
Testing the model, Panapitiya and his co-authors used the geometric properties of gold, including the number of bonds and atoms. They ended up with an 80 percent accuracy prediction rate. That is the highest rate possible for a machine-learning model that calculates adsorption energies of nanoparticles based solely on geometric properties.
“We give the machine-learning algorithm completely unseen data so that if it is trained, it can recognize and find the adsorption energy only based on the features it has not seen,” Panapitiya said. “By using just geometric properties, you don’t have to do any calculations. That makes the prediction process very fast and easy to replicate.”
The algorithm was also tested with different nanoparticle types and sizes to demonstrate that it has the same prediction accuracy for any nanoparticle regardless of size or shape.
Panapitiya, whose research was funded by the National Science Foundation and the U.S. Department of Energy, went on to publish these findings in a December issue of the Journal of the American Chemical Society.
His research adviser, WVU professor of physics James P. Lewis, commended the findings.
“Gihan’s significant research efforts have paid off in terms of truly amazing results, and deservedly so,” Lewis said. “Gold-based bimetallic nanocatalysts provide greater tunability in nanostructures and chemical compositions that enable improvements in their reactivity, selectivity and stability to achieve the desired catalytic efficiencies. Correctly predicting their properties will drive technological advances.”
When used as catalysts, gold nanoparticles can have applications in medicine such as bioimaging and biolabeling.
Panapitiya noted that gold nanoparticles can be used as fluorescent labels for biological imaging, which is crucial to understanding the spread of diseases such as cancer.
“When the human cancer cells are allowed to interact with gold nanoparticles, the nanoparticles get attached to cancer cells, which is called biolabeling,” he said. “After some time of attachment, the cancer cells emit luminescence, which can be collected to image these cancer cells.”
Various aspects of machine learning and artificial intelligence have been researched at WVU campuses for years to find ways to improve health and to increase energy production.
Credit: Google News
