A collaboration of CNAM members including Ichiro Takeuchi (MSE), Efrain Rodriguez (Chemistry) and Johnpierre Paglione (Physics), together with researchers from NIST and Duke University,have been exploring methods of using artificial intelligence techniques to explore new compounds and search for new, practical superconducting materials by developing machine learning schemes to model the critical temperature (Tc) of over 12,000 known superconductors. Led by postdoctoral research Valentin Stanev, this project involved training a classification model based only on chemical compositions to categorize the known superconductors using a random forest model, and developing regression models to predict the values of Tc for compounds from the database of known materials. Including calculated first principles data from the AFLOW Online Repositories, classification and regression models were combined into a single-integrated pipeline to search the entire Inorganic Crystallographic Structure Database and predict more than 30 new candidate superconductors. This work is now published in NPJ Computational Materials.