Artificial Intelligence (AI) has revolutionized industries, redefining how we work, learn and interact. AI has revolutionized healthcare by diagnosing diseases, personalizing treatments and speeding up drug discovery. It has transformed transportation with self-driving cars, optimized routes and enhanced safety. In the world of finance, AI powers fraud detection, trading algorithms and customer services with unprecedented efficiency and innovation.

It is also reshaping other industries and an innovation has emerged in material sciences. What is about? Let's find out!

Well, Google’s DeepMind scientists published a paper this week claiming that the system has already predicted 2.2 million potential new materials. Out of these 380,000 are stable enough to be promising candidates for actually being created in a lab. Researchers say the discovery is the equivalent of “nearly 800 years’ worth of knowledge” and multiplies the number of stable materials known to humanity.


Let’s see what’s worth noting down about this innovation:
 

• It’s the latest big scientific breakthrough from Google’s DeepMind, which is dedicated to putting neural networks to work on some of the world’s biggest problems. 

• The division has previously similarly used deep learning to predict millions of protein structures in a database that scientists hope will fuel drug discovery. More recently, DeepMind’s scientists used AI to more accurately predict weather than leading forecasting systems.

• DeepMind said the goal of its new system, called Graph Networks for Materials Exploration, or GNoME, is to revamp the way scientists discover new crystal structures that might make for more efficient batteries or better superconductors.

So, how does GNoME work?
 

• “GNoME can be described as AlphaFold for materials discovery”, according to Ju Li, a materials science and engineering professor at the Massachusetts Institute of Technology. AlphaFold, a DeepMind AI system announced in 2020, predicts the structures of proteins with high accuracy and has since advanced biological research and drug discovery. Thanks to GNoME, the number of known stable materials has grown almost tenfold, to 421,000. 

• Historically, that’s been a painstaking experimentation process of altering known materials or combining different elements and it’s yielded limited results, the researchers wrote in a blog post. Various existing computational approaches have helped researchers expand the list of known materials by 28,000. GNoME can now supercharge that progress, the researchers said.

• The system works through two pipelines of neural networks: one tweaks the compositions of known stable crystal structures, while the other takes a more randomized approach. Results from both are then evaluated for stability by a series of calculations and the results are added to the database in a feedback loop that then informs the next round of learning.

Additionally, Google DeepMind also collaborated with scientists at UC Berkeley and Lawrence Berkeley National Laboratory, who published their paper on how an autonomous lab could use DeepMind’s findings to help create new compounds.

Google DeepMind will now share GNoME’s extensive results with the scientific community through an open-access database of known materials founded by Lawrence Berkeley called The Materials Project, which was also used to train GNoME.

Do you think Google DeepMind has started a new revolution in the world of material science? Which business areas can DeepMind’s AI contribute to with this latest innovation?

Feel free to pitch your thoughts in the comments below!