New machine learning program to speed up clean energy generation

New machine learning program to speed up clean energy generation

Researchers have created a new type of machine learning model that could accelerate the process of designing next-generation organic solar cells.

From The Terminator and Blade Runner to The Matrix, Hollywood has taught us to be wary of artificial intelligence. But rather than sealing our doom on the big screen, algorithms could be the solution to at least one issue presented by the climate crisis.

Researchers have created a new type of machine learning model that could help significantly speed up the process of designing more efficient solar cells.

The model predicts the power-conversion efficiency (PCE) of materials for use in next-generation organic solar cells, including ‘virtual’ compounds that don’t exist yet.

Unlike some time-consuming and complicated models, the latest approach is quick, easy to use and the code is freely available for all scientists and engineers.

The method has been detailed in a study led by RMIT University researchers in the ARC Centre of Excellence in Exciton Science published in the Nature journal Computational Materials.

The work was led by RMIT’s Dr Nastaran Meftahi and Professor Salvy Russo, in conjunction with Professor Udo Bach’s team at Monash University.

“The majority of the other models use electronic descriptors, which are complicated, computationally expensive and not chemically interpretable,” Nastaran said.

“It means an experimental chemist or scientist can’t get ideas from those models to design and synthesise materials in the lab.

“If they look at my models, because I used simple and chemically interpretable descriptors, they can see the important fragments.”

A flexible solar cell The model could help significantly speed up the process of designing next-gen solar cells.

Next-gen renewable energy

Attention is increasingly turning to organic photovoltaic (OPV) solar cells after decades of relying on silicon, which is relatively expensive and lacks flexibility.

OPV solar cells will be cheaper to make by using printing technologies, as well as being more versatile and easier to dispose of.

But a major challenge is sorting through the huge volume of potentially suitable chemical compounds that can be synthesised (tailor-made by scientists) for use in OPVs.

Researchers have tried using machine learning before to address this issue but many of those models were time consuming, required significant computer processing power and were difficult to replicate.

Crucially, they did not provide enough guidance for the experimental scientists seeking to build new solar devices.

The key to developing a more efficient and user-friendly model was to replace complex parameters that require quantum mechanical calculations with simpler signature descriptors of the molecules being analysed.

They provide important data about the most significant chemical fragments in materials that affect PCE, generating information that can be used to design improved materials.

By using it, the researchers have been able produce results that are robust and predictive, and generate, among other data, quantitative relationships between the molecular signatures under examination and the efficiency of future OPV devices.

Nastaran and her colleagues now intend to extend the scope of their work to include bigger and more accurate computed and experimental datasets.

Her work was strongly supported by co-author Professor Dave Winkler of CSIRO’s Data 61, Monash University, La Trobe University, and the University of Nottingham, who co-created the BioModeller program which provided the basis for the new, open source model.

‘Machine Learning Property Prediction for Organic Photovoltaic Devices’ is published in the journal Computational Materials (DOI: 10.1038/s41524-020-00429-w).

Dr Nastaran Meftahi. Dr Nastaran Meftahi.

Story: Iain Strachan and Gosia Kaszubska

09 November 2020

Share

09 November 2020

Share

  • Research
  • Sustainability
  • Science and technology
  • Environment
Engage

Related News

Dr Biplob Pramanik shows the difference between a concrete block coated with his team’s anti-fatberg invention (left) compared to a block without any coating after undergoing an experiment that mimicked a sewer environment under extreme conditions to speed up the fatberg formation process. The white coloured blobs on the uncoated block are a mixture of fat, oil and grease (FOG) that have been deposited on the block. Credit: Will Wright, RMIT University

Anti-fatberg invention could help unclog city sewers

Engineers from RMIT University have invented a protective coating for concrete pipes that could help drastically reduce the formation of fatbergs in sewers.

news-carpet-concrete-1220px.jpg

Carpet fibres stop concrete cracking

Engineers in Australia have found a way to make stronger and crack-resistant concrete with scrap carpet fibres, rolling out the red carpet for sustainability in the construction sector.

BComm_1220x732.jpg

Brand-new BCom launches for tech-minded business leaders of the future

RMIT is partnering with Accenture, ANZ, L’Oréal and Salesforce to deliver a new undergraduate degree designed for students with a keen eye on leadership.

Thumb-BeachPlastics-7.jpg

Scientists say plastic rubbish on beaches can now be seen from space

Aussie researchers have developed a new method for spotting plastic rubbish on our beaches and successfully field tested it on a remote stretch of coastline.

Show more
aboriginal flag
torres strait flag

Acknowledgement of Country

RMIT University acknowledges the people of the Woi wurrung and Boon wurrung language groups of the eastern Kulin Nation on whose unceded lands we conduct the business of the University. RMIT University respectfully acknowledges their Ancestors and Elders, past and present. RMIT also acknowledges the Traditional Custodians and their Ancestors of the lands and waters across Australia where we conduct our business - Artwork 'Sentient' by Hollie Johnson, Gunaikurnai and Monero Ngarigo.

More information