GNoME (Graph Networks for Materials Exploration ) is AI model developed by Google's DeepMind team and it's task is to predict inorganic crystal structures ...
which are repeating arrangements of atoms that provide materials with particular properties – for example, the six-fold symmetry of a snowflake is a result of the crystal structure of ice.
.
There are 48,000 possible inorganic crystals so far and GNoME has predicted over 2 Millions new ones. Several hundreds of these predictions has been already made in the lab of University of California, Berkeley, led by Dr. Yan Zeng.
So why this is important?
It will significantly speed up the process of discovery of new materials hence help build new materials science. This can lead to improve new technologies like better batteries, solar panels or never before seen alloys.
Next generation materials with enhanced capabilities and applications will pave the way for future technologies and innovations. Also we can't forget about economic and environmental performance of new materials.
Nanomaterials, nanoparticles, biomaterials, graphene, carbon nanotubes, 2D materials, metamaterials, artificial spider silk, perovskites, etc., are a few among the many wonder materials touted for their innovative properties and potential for advanced applications in the future.
.
Gnome is graph neural network, type of AI that can learn relations between objects. It is trained on existing database of known inorganic crystals. So far its predictions have been tested at 70% accuracy.
image source edited in Canva
resources:
