MAY 2024

Swatch #11 Artificial Intelligence (AI)

This month, we highlight the potential impact of Artificial Intelligence (AI) on material science and how, if harnessed correctly, it can accelerate progress, leading to innovative, life-changing discoveries. 💡

Moving from serendipity to intelligent design, tech giants have shown us how AI can unleash automated material discoveries which enhance both simulation methods and predictions of material properties. But whilst AI allows for much faster and more cost-effective testing, it often takes time for industries to adopt such discoveries on a commercial scale.

Google DeepMind hopes to turn the tide, with a new tool which implements deep learning to radically speed up the process of discovering new materials. Named ‘graphical networks for material exploration’ (GNoME), the technology has already predicted the structures of 2.2 million new materials, of which more than 700 have gone on to be created in the lab and are now being tested.

By using machine-learning algorithms, researchers can predict and simulate how materials will behave under certain conditions, optimising their properties accordingly. This can result in identifying materials which are stronger, more lightweight or more environmentally friendly.

One of the most recent discoveries made by Microsoft and the Pacific Northwest National Laboratory (PNNL) using AI and supercomputing, led to the identification of a new substance which could potentially reduce lithium-use in batteries by up to 70%. Lithium is inherently scarce and consequently expensive, with its mining presenting significant environmental, social and geopolitical challenges. This newly discovered material named ‘N2116’, is a solid-state electrolyte which holds promise for sustainable energy storage solutions. Using AI and supercomputing, researchers swiftly narrowed down 32 million inorganic materials to 18 promising candidates in under a week. After which, they developed a successful prototype within 9 months – a process which typically takes over two decades.

This video is a visual interpretation of what the N2116 material structure might resemble, designed by our digital creative team and built upon an initial visual created by AlphaFold.

The end image is Tom Hegen's Lithium Series 1 photograph documenting Chile's lithium extraction and its threat to local communities and wildlife habitats.

Previous Swatches