Sign In

Communications of the ACM

ACM Careers

Student Develops Machine-Learning Model for Energy and Environmental Applications


West Virginia University doctoral student Gihan Panapitiya

West Virginia University doctoral student Gihan Panapitiya's work linked machine learning with using gold nanoparticles as catalysts.

A West Virginia University physics student helped create a machine-learning model that has the potential to make searching for energy and environmental materials more efficient. 

Gihan Panapitiya, a doctoral student from Sri Lanka, and others used the model to predict the adsorption energies, or adhesive capabilities, in gold nanoparticles. He describes the work in "Machine-Learning Prediction of CO Adsorption in Thiolated, Ag-Alloyed Au Nanoclusters," published in the Journal of the American Chemical Society.

"Machine learning recently came into the spotlight, and we wanted to do something linking machine learning with gold nanoparticles as catalysts," Panapitiya says. "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. 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."

Panapitiya and co-authors of the Journal of the American Chemical Society (JACS) study used the geometric properties of gold, including the number of bonds and atoms, to test the model. They obtained an 80 percent accuracy prediction rate, the highest rate possible for machine-learning models calculating adsorption energies nanoparticles based only 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 says. "By using just geometric properties, you don't have to do any calculations. That makes the prediction process very fast and easy to replicate." 

They also tested the algorithm with different nanoparticle types and sizes to demonstrate that the model has the same prediction accuracy for any nanoparticle of any size and any shape. 

"Gihan's significant research efforts have paid off in terms of truly amazing results, and deservedly so," says Professor of Physics James P. Lewis, Panapitiya's research adviser and a co-author of the JACS work. "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."

Gold nanoparticles are commonly used as catalysts for energy and environmental applications and in biomedical applications like bioimaging and biolabeling. 

"For example, gold nanoparticles can be used as fluorescent labels for biological imaging applications. Bioimaging is essential to understand the nature and the spread of a disease like cancer. When the human cancer cells are allowed to interact with gold nanoparticles, the nanoparticles get attached to cancer cells, which is called biolabeling," Panapitiya says. "After some time of attachment, the cancer cells emit luminescence, which can be collected to image these cancer cells."

Additional co-authors of the JACS article are Guillermo Avendaño-Franco of West Virginia University, plus Pengju Ren, Xiaodong Wen, and Yongwang Li of the Chinese Academy of Sciences, Taiyuan, China.

This research was funded by the U.S. National Science Foundation, award DMREF CHE-1434378 and the U.S. Department of Energy, award DOE SC-0004747.


 

No entries found