Mixed ionic/electronic conductors have been shown using traditional cumbersome research approaches to have promise for energy storage materials and to possess unexpected synergy between conducting phases. This DMREF program will accelerate the discovery of new promising mixed ionic/electronic conductors by using a dual iterative cycle to study the general phase behavior and transport dynamics of self-assembling polymeric and oligomeric liquid crystal mixed conductors. A machine learning approach will combine a genetic algorithm to propose successive generations of candidate materials, and a neural network scheme to construct a regression model to correlate input (a library of chemical groups and structures) with output variables (conductivity properties). An important aspect of the intellectual merit of this project lies in the development of processes to integrate computation, experiment and data analysis for the design of these functional materials. The proposed research is envisioned to not only shed light on the role of structure on phase behavior and charge transport, and their effect on interface sharpness and conductivity between the solid-like electronically conducting phase and the liquid-like ionically conducting regions but also lead to new applications as energy storage, sensing and robotic materials. Collaborations will provide additional expertise to this program.