Learning material synthesis-process-structure-property relationship by data fusion: Bayesian Coregionalization N-Dimensional Piecewise Function Learning
This addresses the need for accelerating materials optimization and discovery in materials science, though it appears incremental as it builds on existing multimodal coregionalization methods.
The paper tackles the problem of learning material synthesis-process-structure-property relationships from diverse data streams in autonomous materials research, presenting the SAGE algorithm that outputs a probabilistic posterior for these relationships.
Autonomous materials research labs require the ability to combine and learn from diverse data streams. This is especially true for learning material synthesis-process-structure-property relationships, key to accelerating materials optimization and discovery as well as accelerating mechanistic understanding. We present the Synthesis-process-structure-property relAtionship coreGionalized lEarner (SAGE) algorithm. A fully Bayesian algorithm that uses multimodal coregionalization to merge knowledge across data sources to learn synthesis-process-structure-property relationships. SAGE outputs a probabilistic posterior for the relationships including the most likely relationships given the data.