Download CV and Seminar

Materials Discovery in the Era of Watson:
Challenges and Opportunities in “Big Data” Science
Venkat Venkatasubramanian
Department of Chemical Engineering
Institute for Data Science and Engineering
Columbia University
New York, NY 10027
Abstract
“Who is Bram Stoker?” – With this $1 million prize winning final question in the game
show Jeopardy, IBM’s Watson supercomputer using DeepQA technology ushered in a new era in
artificial intelligence, cyberinfrastructure and informatics. This has far reaching implications for
knowledge management in a number of fields including materials design and discovery.
Designing new materials and formulations with desired properties is an important and
difficult problem, encompassing a wide variety of products in the specialty chemicals and
pharmaceuticals industries. Traditional trial-and-error design approaches are laborious and
expensive, and cause delays time-to-market as well as miss some potential solutions.
Furthermore, the growing avalanche of high throughput experimentation data has created both an
opportunity, and a major modeling and informatics challenge, for material design and discovery.
Such a data deluge is coming from smart sensors in process plants, ab initio quantum
calculations, molecular dynamics simulations, and so on. We are moving from an era of limited
data obtained through time consuming experiments and simulations to one of a tsunami enabled
by high throughput experiments and TeraGrid computing environments— it’s a dramatic
transition from a “data poor” to a “data rich” era. A systematic way to convert raw data into
information and first-principles knowledge that can be used for real-time decision making is very
much lacking. A new paradigm is needed that increases the idea flow, broadens the search
horizon, and archives the knowledge from today’s successes to accelerate those of tomorrow.
Data science, loosely defined as a body of knowledge comprising of machine learning,
natural language processing, databases and informatics, will play a crucial role in materials
design and discovery, process development and commercial scale manufacturing by streamlining
information gathering, data integration, model development, and managing all these for easy and
timely access and reuse. In this talk, I will discuss a novel cyberinfrastructure framework called
Ontological Discovery Informatics. The foundation of such an infrastructure is the explicitly and
formally modeled information, called an ontology. This framework enables the management of
information complexity, accumulation of knowledge, systematic model development, and
efficient search for new materials with desired performance characteristics. I will discuss the
application of this paradigm for industrial molecular products design problems in the specialty
chemical and pharmaceutical industries.
Professor Venkat Venkatasubramanian is
Samuel Ruben-Peter G. Viele Professor
of Engineering in the Department of
Chemical Engineering, Professor of
Computer Science (Affiliate),
and
Professor of Industrial Engineering and
Operations Research (Affiliate) at
Columbia University in the City of New
York. He earned his Ph. D. in Chemical
Engineering at Cornell, M.S. in Physics at
Vanderbilt, and B. Tech. in Chemical
Engineering at the University of Madras,
India. Venkat worked as a Research
Associate in Artificial Intelligence in the
School of Computer Science at CarnegieMellon University. He taught at Purdue University for 23 years, before returning to Columbia in 2011. At
Columbia, Venkat directs the research efforts of several graduate students and co-workers in the Complex
Resilient Intelligent Systems Laboratory. He is also the founding Co-Director of the Center for the
Management of Systemic Risk, a transdisciplinary center focused on understanding how complex systems
fail in order to prevent or mitigate such failures in the future, with faculty from a number of departments at
Columbia University. Venkat’s research contributions have been in the areas of process fault diagnosis and
risk management in complex systems, materials discovery through design and informatics, and
pharmaceutical engineering using knowledge-based systems, neural networks, genetic algorithms,
mathematical programming and statistical approaches.
Prof. Venkatasubramanian received the Norris Shreve Award for Outstanding Teaching in
Chemical Engineering three times at Purdue University. He won the Computing in Chemical Engineering
Award from AIChE in 2009 and was elected a Fellow of AIChE in 2011. Also in 2011, the College of
Engineering at Purdue University recognized his outstanding contributions with the Research Excellence
Award. He is a past-President of the Computer Aids for Chemical Engineering (CACHE) Corporation, a
non-profit organization for the promotion of computers in chemical engineering education. He currently
serves as an Editor for Computers and Chemical Engineering for the topical area of cyberinfrastructure,
informatics and intelligent systems. Venkat’s other interests include comparative theology, classical music,
and cricket.