Close

Search

Search Menu
Photonics Media Photonics Buyers' Guide Photonics Spectra BioPhotonics EuroPhotonics Vision Spectra Photonics Showcase Photonics ProdSpec Photonics Handbook
More News

Machine Learning Predicts How to Develop High-Performing Solar Cells

Facebook Twitter LinkedIn Email Comments
ORLANDO, Fla., Dec. 17, 2019 — To determine the best way to optimize the materials used to build perovskite solar cells, a research team at the University of Central Florida turned to machine learning techniques. The researchers reviewed more than 2000 peer-reviewed publications about perovskites and collected more than 300 data points and then fed these into an artificial intelligence system developed by the team.

The system analyzed the information and predicted which recipe for spray-on perovskite solar technology would work best. The machine learning approach considered how to optimize material composition and predicted the best design strategies and potential performance of perovskite solar cells. The machine learning predictions corresponded with the Shockley-Queisser limit. Optimum frontier orbital energies between the transport layer and perovskite layer were also predicted.

If the researchers’ model bears out, it could be used to identify a formula that could become the standard recipe used for making perovskites that are flexible, stable, efficient, and low-cost.

UCF’s Jayan Thomas led the team in reviewing more than 2000 peer-reviewed publications about perovskites and collecting more than 300 data points that were fed into the AI system the team created. The system was able to analyze the information and predict which perovskites recipe would work best. Courtesy of UCF/Karen Norum.
UCF’s Jayan Thomas led the team in reviewing more than 2000 peer-reviewed publications about perovskites and collecting more than 300 data points that were fed into the AI system the team created. The system was able to analyze the information and predict which perovskites recipe would work best. Courtesy of UCF/Karen Norum.

“Our results demonstrate that machine learning tools can be used for crafting perovskite materials and investigating the physics behind developing highly efficient PSCs,” professor Jayan Thomas said. “This can be a guide to design new materials as evidenced by our experimental demonstration.”

Spray-on solar cells could be used to spray-paint bridges, buildings, homes, and other structures to capture light, turn it into energy, and feed it into the electrical grid.

“This is a promising finding because we use data from real experiments to predict and obtain a similar trend from the theoretical calculation, which is new for PSCs. We also predicted the best recipe to make PSCs with different bandgap perovskites,” Thomas and graduate student Jinxin Li said. “Perovskites have been a hot research topic for the past 10 years, but we think we really have something here that can move us forward.”

The research was published in Advanced Energy Materials (www.doi.org/10.1002/aenm.201970181).  

Photonics.com
Dec 2019
GLOSSARY
artificial intelligence
The ability of a machine to perform certain complex functions normally associated with human intelligence, such as judgment, pattern recognition, understanding, learning, planning and problem solving.
Research & TechnologyeducationAmericasUniversity of Central Floridacoatingslight sourcesmaterialsmaterials processingopticsphotovoltaicsartificial intelligencemachine learningsolarenergyenvironmentConsumerindustrialperovskitesperovskite solar cells

Comments
back to top
Facebook Twitter Instagram LinkedIn YouTube RSS
©2020 Photonics Media, 100 West St., Pittsfield, MA, 01201 USA, info@photonics.com

Photonics Media, Laurin Publishing
x We deliver – right to your inbox. Subscribe FREE to our newsletters.
We use cookies to improve user experience and analyze our website traffic as stated in our Privacy Policy. By using this website, you agree to the use of cookies unless you have disabled them.