AI learns to design better materials by knowing physics first
Researchers have cracked a fundamental barrier in using artificial intelligence to discover new materials: they taught the AI to obey the laws of physics while generating designs. By applying this method to topological insulators—exotic materials with potential applications in quantum computing and electronics—the team produced novel candidates with stronger protective properties than most predicted alternatives.
Originaltitel: Fine tuning generative adversarial networks with universal force fields: application to two-dimensional topological insulators
<p>Despite rapid growth in use cases for generative artificial intelligence, its ability to design purpose built crystalline materials remains in a nascent phase. At the moment inverse design is generally accomplished by either constraining the training data set or producing a vast number of samples from a generator network and constraining the output via post-processing. We show that a general adversarial network trained to produce crystal structures from a latent space can be fine tuned through the introduction of advanced graph neural networks as discriminators, including a universal force field, to intrinsically bias the network towards generation of target materials. This is exemplified utilizing two-dimensional topological insulators as a sample target space. While a number of two-dimensional topological insulators have been predicted, the size of the band-gap, a measure of topological protection, remains a concern in most candidate compounds. The resulting generative network is shown to yield novel topological insulators.</p>