Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning
This addresses a major bottleneck in high-throughput materials discovery for materials scientists by automating a complex task that experts struggle with, though it appears incremental as it builds on existing deep learning and constraint reasoning methods.
The paper tackles the challenge of automating crystal-structure phase mapping in materials science by formulating it as an unsupervised pattern demixing problem and solving it with Deep Reasoning Networks (DRNets), which combine deep learning with constraint reasoning to incorporate scientific prior knowledge and achieve results surpassing previous approaches, such as unraveling the Bi-Cu-V oxide phase diagram and aiding in solar-fuels materials discovery.
Crystal-structure phase mapping is a core, long-standing challenge in materials science that requires identifying crystal structures, or mixtures thereof, in synthesized materials. Materials science experts excel at solving simple systems but cannot solve complex systems, creating a major bottleneck in high-throughput materials discovery. Herein we show how to automate crystal-structure phase mapping. We formulate phase mapping as an unsupervised pattern demixing problem and describe how to solve it using Deep Reasoning Networks (DRNets). DRNets combine deep learning with constraint reasoning for incorporating scientific prior knowledge and consequently require only a modest amount of (unlabeled) data. DRNets compensate for the limited data by exploiting and magnifying the rich prior knowledge about the thermodynamic rules governing the mixtures of crystals with constraint reasoning seamlessly integrated into neural network optimization. DRNets are designed with an interpretable latent space for encoding prior-knowledge domain constraints and seamlessly integrate constraint reasoning into neural network optimization. DRNets surpass previous approaches on crystal-structure phase mapping, unraveling the Bi-Cu-V oxide phase diagram, and aiding the discovery of solar-fuels materials.