AI tool GNoME discovers 2.2 million new crystals containing 380,000 stable materials that could power future technologies
Modern technology, from computer chips and batteries to solar panels, relies on inorganic crystals. In order to realize new technology, crystals must be stable or they will decompose. Creating new, stable crystals can require months of painstaking experimentation.
Today, in a paper published in Nature, we share the discovery of 2.2 million new crystals. This is almost 800 years of knowledge. We introduce Graph Networks for Materials Exploration (GNoME), a new deep learning tool that dramatically increases the speed and efficiency of discovery by predicting the stability of new materials.
Using GNoME, we have doubled the number of technically viable materials known to humanity. Of the 2.2 million predictions, 380,000 are the most stable, making them promising candidates for experimental synthesis. These candidates include materials that have the potential to develop future transformative technologies, from superconductors to powering supercomputers to next-generation batteries that will make electric cars more efficient.
GNoME shows the potential of using AI to discover and develop new materials at scale. External researchers in labs around the world independently created 736 of these new structures experimentally in parallel work. A team of researchers at Lawrence Berkeley National Laboratory, in partnership with Google DeepMind, also published a second paper in Nature showing how AI predictions can be leveraged for autonomous materials synthesis.
We have made GNoME predictions available to the research community. We plan to deliver 380,000 materials to materials projects that are expected to be stable. The Materials Project is currently processing the compounds and adding them to the online database. We hope these resources will advance research in inorganic crystals and unlock the potential of machine learning tools to guide experiments.
