Big Data and Quantum Mechanics
GOALS: Leverage advances in machine learning and data analytics to enable faster and more accurate calculations of chemical properties using quantum-mechanical techniques such as density functional theory (DFT).
METHODS & TECHNOLOGIES: Density functional theory, databases, automation, neural networks, Bayesian statistics, high performance computing, visualization, user interface design.
RESEARCH/DESIGN ISSUES: High-throughput system for submission and management of DFT calculations; Automated data capture and integrated data analysis system; Interactive visualization of high-dimensional electron density descriptor data; Implementation of algorithms for fusion of distinct exchange-correlation approximations; Uncertainty quantification and propagation for exchange-correlation approximations.
MEETING TIME: Wed, 10:10-11:00
ADVISOR: Andrew Medford (CHBE)
PARTNERS & SPONSORS: Citrine Informatics
MAJORS, PREPERATION AND INTERESTS:
ChBE, Chem, MSE, Physics – Background/interest in quantum mechanics, computational materials science, computational chemistry. Curiosity about machine learning, data science, and big data. Programming skills would be helpful but are not required.
CS, Applied Math, Stats, CSE – Background/interest in machine learning, uncertainty quantification, data-driven methods. Interest in the intersection of machine learning and physics. Programming skills encouraged but not required.
CS – Interest in software architecture, database design, schema-free data models, functional programming, interactive visualization. Programming experience and skills are strongly encouraged.
CONTACT: Prof. Andrew J. Medford, email@example.com