Causal Paths Allowing Simultaneous Control of Multiple Nanoparticle Properties Using Multi‐Target Bayesian Inference

Abstract

Machine learning can extract complex structure/property relationships but is often insufficient to explain how to control or tune the properties of materials, particularly when they are multi-functional. This study demonstrates the value of combining multi-target regression and multi-target causal graphs to address the need to simultaneously control multiple properties of nanomaterials, and the need to translate these relationships into actionable insights. Using nanodiamonds as an exemplar, recursive feature elimination is first used to identify nine structural features that allow simultaneous prediction of their electron charge transfer properties and thermochemical stability to high accuracy by an interpretable random forest regressor. A multi-target Bayesian network with domain knowledge incorporated via interactive learning using a hill-climbing algorithm then determines how these important structural features of nanodiamonds relate to their functional properties, proposing causal paths that can be used to inform experimental design.

Data-Driven Design of Classes of Ruthenium Nanoparticles Using Multitarget Bayesian Inference

“…The interactive learning restricts the graphs to edges that are directed from categories 1 to 3, and then to the target classes, and prohibits intercategory relationships, which is equivalent to imposing constraint rules upon the structure learning problem . This approach has previously been demonstrated for defective graphene oxide nanoflakes and diamond nanoparticles . The methodology is illustrated by the workflow in Figure .…”