Simultaneous Causes of Charge Transfer Properties of Diamond Nanoparticles from Bayesian Inference

While the field of nanomaterials design has benefited from the application of conventional machine learning methods by leveraging the correlations between structure and property variables, the outcomes from purely correlational studies lack actionability due to missing mechanistic insights. Statistical learning, particularly causal inference, can potentially provide access to more actionable insights by allowing the discovery and verification of deeply obscured causal relationships between variables, using strong correlations as starting points. In this presentation interpretable multi-target machine learning will be used to identify simultaneous correlations between the charge transfer properties of diamond nanoparticles, as a basis for statistical learning. Using Bayesian inference, directed graph models will be developed to predict causal pathways characteristic of the mechanisms responsible for the ionization potential the electron affinity, the electron band gap and the thermodynamic probability, and compare the likelihood that tuning a property via one causal path will impact another.