Current research Materials design with machine learning: A case study of high-entropy alloys Methods and algorithms for machine learning assisted materials design Discovery of high-entropy alloys for corrosion protection A machine learning framework to evaluate corrosion performance for given compositions of high-entropy alloys Machine learning enabled multiscale simulations for brittle particle cold spray Atomistic-mesoscale simulation framework to understand size and shape effects of particle feedstock for brittle particle cold spray A data-efficient and interpretable approach to inverse materials design Disentangled representation of compositions/structures and properties in a semi-supervised variational autoencoder Past research Enabling exascale computing of chemical systems Machine learning potentials for large-size nanoparticle catalysts Atomistic models to expedite catalyst design Force-displacement models for strain effect, surface relaxation and lateral interaction Data science Machine learning competitions on Kaggle A list of past kaggle competitions Course projects A collection of data science course projects supported by Brown's open graduate education program
