University of Cambridge > Talks.cam > CEDSG-AI4ER > Harvesting the Sun: using AI to design better materials for energy

Harvesting the Sun: using AI to design better materials for energy

Add to your list(s) Download to your calendar using vCal

  • UserXiaolei Feng, University of Cambridge, Department of Earth Sciences
  • ClockTuesday 18 February 2020, 12:00-13:15
  • HouseBullard Lab, Seminar Room.

If you have a question about this talk, please contact Jonathan Rosser.

Chair: Alex Archibald Abstract: Our Sun provides almost all the energy that society depends upon. The first industrial revolution, driven by the discovery that steam made by burning coal provides the energy to drive machines, has led to the warming planet that we must adapt to today. But even that first fuel, that fossil fuel, was itself generated from the Sun, by photosynthesis in plants hundreds of millions of years ago. Plants continue to use photosynthesis to make the energy that we all rely on for food, directly or indirectly via other animals, for our daily survival. But the fourth industrial of machine learning and artificial intelligence is now providing a route to designing and discovering new materials that harvest the Sun’s energy directly. We are familiar with silicon photovoltaics (PV) in solar cells, for generating electricity from sunlight. Now, new materials offer more convenient, cheaper, and more efficient routes to harvesting the light that shines upon us daily. Computing power opens new ways to search for new materials, and to predict which will work best. I will discuss how computer predictions of new materials provide a route to designing better routes to harvest energy from the Sun, in sustainable and effective devices. Maybe silicon, in the shape of computer processors and banks of memory, will be the means by which we can build a sustainable future from materials that first emerge, in silico, rather than in the test tube or crucible. That is our aim.

This talk is part of the CEDSG-AI4ER series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity