arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.09523cs.LGcond-mat.mtrl-scics.AI
收藏

自动晶体结构相位映射:结合深度学习和约束推理

Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning

Cornell University(康奈尔大学);California Institute of Technology(加州理工学院)

Di Chen, Yiwei Bai, Sebastian Ament, Wenting Zhao, Dan Guevarra, Lan Zhou, Bart Selman, R. Bruce van Dover, John M. Gregoire, Carla P. Gomes

摘要:

晶体结构相位映射是材料科学中的核心、长期挑战,需要在合成材料中识别晶体结构或其混合物。材料科学专家擅长解决简单的系统,但不能解决复杂的系统,这在高通量材料发现中形成了一个主要瓶颈。在这里,我们展示了如何自动晶体结构相位映射。我们将相位映射表示为一个无监督的模式分离问题,并描述了如何使用深度推理网络(DRNets)解决它。DRNet将深度学习与约束推理相结合,以整合科学先验知识,因此只需要少量(未标记)数据。DRNets通过利用和放大有关晶体混合物热力学规则的丰富先验知识,将约束推理无缝集成到神经网络优化中,从而补偿有限的数据。DRNets设计了一个可解释的潜在空间,用于编码先验知识域约束,并将约束推理无缝集成到神经网络优化中。DRNets在晶体结构相位映射、解开Bi-Cu-V氧化物相图和帮助发现太阳能燃料材料方面超越了以前的方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑