What is it about?

The signing of the Paris Agreement signified multiple nations’ commitment to mitigating global warming. Achieving this goal requires efforts and scientific development in renewable energy technologies. Whileresearchers are actively working towards developing such technologies and materials, new research concepts and strategies are needed to accelerate the progress. Fortunately, machine learning can come to our aid. A 2019 review study focuses on how this approach has equipped the engineering community with a framework for predicting material properties and then rapidly screening them for desirable characteristics. The study highlights the use of machine learning to screen developments in technologies such as catalysis, carbon dioxide capture, batteries, solar cells, and crystal discovery. The study also discusses applications leading to real discoveries. Additionally, it emphasizes the scope for further accelerating material discovery and the gaps that need to be addressed in doing so.

Featured Image

Why is it important?

Many industries still rely on fossil fuels for their operations. The discovery, testing, development, and market deployment of new and alternative materials need 10-20 years. At this rate, meeting the goal of limiting global warming set in the 2016 Paris agreement is unlikely unless the material discovery process speeds up. This is where machine learning could change the game. KEY TAKEAWAY: Machine learning has tremendous potential in the field of material engineering for renewable energy technologies. It could accelerate their development, opening doors to a carbon-neutral society. This research relates to the following Sustainable Development Goals: • SDG 7: Affordable and Clean Energy • SDG 13: Climate Action • SDG 9: Industry, Innovation, and Infrastructure

Read the Original

This page is a summary of: Machine learning for renewable energy materials, Journal of Materials Chemistry A, January 2019, Royal Society of Chemistry,
DOI: 10.1039/c9ta02356a.
You can read the full text:




Be the first to contribute to this page