Scientists at the Argonne National Laboratory in Chicago, USA, have used machine learning techniques to identify optimal materials for dye sensitized solar cells. Beginning with a list of more than 10,000 candidates, the technique identified five materials for synthesis and testing that best fit the research team’s parameters.
“This study is particularly exciting because we were able to demonstrate the full cycle of data-driven materials discovery,” said Jacqueline Cole, head of the molecular engineering group at the Cavendish Laboratory at the U.K.’s University of Cambridge, which collaborated on the project. “The advantage of this process is that it takes away the old manual curation of databases, which involves many years’ worth of work, and reduces it to matter of a few months, and ultimately, a few days.”
The team used the Argonne lab’s Theta Supercomputer and worked with computational scientists to create an automated analysis that employed simulation, data mining and machine learning techniques to collect chemical data from scientific journals relating to thousands of organic dye candidates. The shortlisting technique is described in the paper Dye‐Sensitized Solar Cells: Design‐to‐Device Approach Affords Panchromatic Co‐Sensitized Solar Cells, published in Advanced Energy Materials.
Process of – rapid – elimination
The initial list ran to 9,431 materials. In an operation that would have made Criminal Minds’ Penelope Garcia proud, the researchers eliminated organometallic compounds and organic molecules too small to absorb visible light, cutting the list down to around 3,000 materials.
The next step was to search for dyes containing components that could be used as ‘chemical glue’ to anchor the dyes to titanium oxide supports, and use the supercomputer to carry out electronic structure calculations on the remaining dye materials.
That left around 300 candidates on a list which was further narrowed, to 30, through computer examination of absorption spectra, and then to five candidates by using Theta to carry out density functional theory calculations, determining likely performance in experiments.
The final stage involved acquiring samples from global laboratories which had synthesized the five materials, to begin testing. While the team has not published details of the materials tested or their performance, it has stated one combination has demonstrated similar conversion efficiencies to a leading organometallic dye material.
“It was really a tremendous bit of teamwork to get so many people from around the world to contribute to this research,” said Cole. “This was a particularly encouraging result because we had made our lives harder by restricting ourselves to organic molecules, for environmental reasons, and yet we found that these organic dyes performed as well as some of the best known organometallics.”
This content is protected by copyright and may not be reused. If you want to cooperate with us and would like to reuse some of our content, please contact: firstname.lastname@example.org.
By submitting this form you agree to pv magazine using your data for the purposes of publishing your comment.
Your personal data will only be disclosed or otherwise transmitted to third parties for the purposes of spam filtering or if this is necessary for technical maintenance of the website. Any other transfer to third parties will not take place unless this is justified on the basis of applicable data protection regulations or if pv magazine is legally obliged to do so.
You may revoke this consent at any time with effect for the future, in which case your personal data will be deleted immediately. Otherwise, your data will be deleted if pv magazine has processed your request or the purpose of data storage is fulfilled.
Further information on data privacy can be found in our Data Protection Policy.