AI could improve the manufacture of perovskite solar cells

Tandem solar cells based on perovskite semiconductors convert sunlight into electricity more efficiently than conventional silicon solar cells. In order to make this technology ready for the market, further improvements are needed to enhance stability and the manufacturing process. Now, researchers from the Karlsruhe Institute of Technology (KIT) have found a way to predict the quality of the perovskite layers and consequently that of the resulting solar cells. Assisted by machine learning and new methods in artificial intelligence, it is possible to assess their quality from variations in light emission in the manufacturing process. The results were published in the journal Advanced Materials.

Perovskite tandem solar cells combine a perovskite solar cell with a conventional solar cell. These cells feature an efficiency of more than 33%, which is higher than that of conventional silicon solar cells. They also use inexpensive raw materials and are easily manufactured. To achieve this level of efficiency, a thin high-grade perovskite layer, whose thickness is a fraction of that of human hair, has to be produced.

Professor Ulrich W. Paetzold said manufacturing these high-grade, multi-crystalline thin layers without any deficiencies or holes using low-cost and scalable methods is a challenge. Even under apparently perfect lab conditions, there may be unknown factors that cause variations in semiconductor layer quality. “This drawback eventually prevents a quick start of industrial-scale production of these highly efficient solar cells, which are needed so badly for the energy turnaround,” Paetzold said.

To find the factors that influence coating, an interdisciplinary team of researchers developed AI methods that train and analyse neural networks using a huge dataset. This dataset includes video recordings that show the photoluminescence of the thin perovskite layers during the manufacturing process. Photoluminescence refers to the radiant emission of the semiconductor layers that have been excited by an external light source.

“Since even experts could not see anything particular on the thin layers, the idea was born to train an AI system for machine learning (deep learning) to detect hidden signs of good or poor coating from the millions of data items on the videos,” Lukas Klein and Sebastian Ziegler from Helmholtz Imaging at the DKFZ said.

To filter and analyse the widely scattered indications output by the deep learning AI system, the researchers used methods of explainable artificial intelligence (XAI) and found out experimentally that the photoluminescence varies during production and that this phenomenon has an influence on the coating quality. “Key to our work was the targeted use of XAI methods to see which factors have to be changed to obtain a high-grade solar cell,” Klein and Ziegler said.

This is not the usual approach, as XAI is generally used as a kind of guardrail to avoid mistakes when building AI models. “This is a change of paradigm: gaining highly relevant insights in materials science in such a systematic way is a totally new experience,” Klein and Ziegler said.

The conclusion drawn from the photoluminescence variation enabled the researchers to take the next step. After the neural networks had been trained accordingly, the AI was able to predict whether each solar cell would achieve a low or a high level of efficiency based on which variation of light emission occurred at what point in the manufacturing process. “Now we are able to conduct our experiments in a more targeted way and are no longer forced to look blindfolded for the needle in a haystack. This is a blueprint for follow-up research that also applies to many other aspects of energy research and materials science,” Paetzold said.

Top image caption: Assisted by AI methods, researchers are striving to improve the manufacturing processes for highly efficient perovskite solar cells. Image credit: Amadeus Bramsiepe, KIT