It’s difficult for humans to identify phase transitions, or exotic states of matter that come about through unusual transitions (say, a material becoming a superconductor). They might not have to do all the hard work going forward, however. Two sets of researchers have shown that you can teach neural networks to recognize those states and the nature of the transitions themselves. Similar to what you see with other AI-based recognition systems, the networks were trained on images — in this case, particle collections — to the point where they could detect phase transitions on their own. They’re both very accurate (within 0.3 percent for the temperature of one transition) and only need to see a few hundred atoms to identify what they’re looking at.
A machine learning system is particularly advantageous in a field like this, as you don’t have to outline exactly what you’re looking for. You can identify the exact conditions that prompt a transition without knowing what they are, and theoretically spot previously undiscovered transitions.
There’s a lot of work to be done. It’s easy to detect known transitions in a lab, where you can limit the number of particles, but it’s much harder when you’re looking at the overwhelming volume of particles in real life. If researchers can achieve that feat, though, they could discover reproducible behavior that might be useful in products, such as superconductors with more forgiving properties.