End-to-End Phase Field Model Discovery Combining Experimentation, Crowdsourcing, Simulation and Learning

The availability of tera-byte scale experiment data calls for AI driven approaches which automatically discover scientic models from data. Nonetheless, sig-nicant challenges present in AI-driven scientic discovery: (i) The annotation of large scale datasets requires fundamental re-thinking in developing scalable crowdsourcing tools. (ii) The learning of scientic models from data calls for innovations beyond blackbox neural nets. (iii) Novel visualization & diagnosis tools are needed for the collaboration of experimental and theoretical physicists, and computer scientists. We present PHASE-FIELD-LAB platform for end-toend phase eld model discovery, which automatically discovers phase eld physics models from experiment data, integrating experimentation, crowdsourcing, simulation and learning. PHASE-FIELD-LAB combines (i) a streamlined annotation tool which reduces the annotation time (by ≈ 50 -75%), while increasing annotation accuracy compared to baseline; (ii) an endto-end neural model which automatically learns phase eld models from data by embedding phase eld simulation and existing domain knowledge into learning; and (iii) novel interfaces and visualizations to integrate our platform into the scientic discovery cycle of domain scientists. Our platform is deployed in the analysis of nano-structure evolution in materials under extreme conditions (high temperature and irradiation). Our approach reveals new properties of nano-void defects, which otherwise cannot be detected via manual analysis. Figure 1: Scientic discovery workow in material science domain, assisted by our PHASE-FIELD-LAB framework. PHASE-FIELD-LAB provides material scientists an integrated framework for data annotation, physics model learning and simulationvisualization of physics models.