Linkage Projects 2020 Round 3 Announcement Banner

Machine learning for solar energy is supercomputer kryptonite

Machine learning for solar energy is supercomputer kryptonite

server cable

Full article issued by The Centre of Excellence in Exciton Science.

Researchers at the ARC Centre of Excellence in Exciton Science, based at RMIT University, have written a program that predicts the results of supercomputers, including for solar energy applications, via freely available and easy-to-use software that can run on a laptop.

The researchers trained a machine learning model using data generated from 250,000 previous supercomputer calculations, on 'band gap' predictions – which involve quantum and atomic-scale chemical calculations and are relevant to the design of solar panels, among other applications. Previously, band gap calculations required hundreds of hours of costly supercomputer processing time, as well as complicated and expensive software.

Their findings raise the exciting prospect of lengthy supercomputer calculations no longer being required for some applications. The artificial neural network that powers the machine learning programs could one day be succeeded by a software program that performs a similar function to density functional theory, albeit with far more simplicity.

'If you want to do simulations but you need to have millions of dollars of supercomputing infrastructure behind you, you can't do it.' says lead researcher and Phd candidate Carl Belle.

The researchers say that if they can determine exactly why their learning model is so powerful, then it could mean that supercomputers are not needed to screen candidate materials, nor for accurate simulations.

The machine learning program isn't limited to band gap. It can be used to predict the properties of many other materials for other contexts, and has been developed by a professional programmer, making it useful not only for scientists and academics but also for businesses and corporate applications.

'It's built to industry standard and it's designed to be collaborative,' Carl says.

'The website has a fully relational database. It's got millions of records. It's all there and freely available to use. We're ready to go.'


Image Credit: Shutterstock

Back to top