A team of researchers at the University of Central Florida say their new AI’s work on a special liquid called “perovskite” could one day be used to create spray-on solar cells.
The so-called “perovskite solar cells” (PSCs) can turn sunlight into energy, just like regular silicon-based solar panels. Scientists came up with the idea over a decade ago — but until now, they’ve struggled to come up with a cost- and energy-efficient recipe.
By feeding a machine learning algorithm hundreds of data points from peer-reviewed publications about perovskite, the system was able to predict which recipes would work best.
The team is hoping their machine learning technique will give the futuristic material the flexibility and efficiency it needs without breaking the bank. Their research was detailed in a paper published in the journal Advanced Energy Materials last week.
At present, more research is still needed.
“Our results demonstrate that machine learning tools can be used for crafting perovskite materials and investigating the physics behind developing highly efficient PSCs,” lead author Jayan Thomas said in a statement.
READ MORE: Artificial intelligence may help scientists make spray-on solar cells [University of Central Florida]
More on solar cell: This Solar Panel-Like Device Can Generate Electricity in the Dark