ESCAPE21
Porto
Carras Resort, Chalkidiki –
“Process Systems Engineering in the Era of Watson:
Challenges and Opportunities in Cyberinfrastructure and Informatics”
Venkat Venkatasubramanian
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 process systems
engineering.
Chemical
engineering, too, has entered an important era. Driven by a convergence of
powerful forces such as the great progress in molecular sciences and
computer/communications technologies, ever increasing automation of globally
integrated operations of our enterprises, tightening regulatory constraints,
and competitive business pressures demanding speed to market for products and
services, our discipline is in an unprecedented transition. One important
common outcome from this convergence is the generation, use, and management of
massive amounts of diverse data, information, and knowledge.
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”
paradigm. Further, the extensive monitoring of equipment, processes, and
products at all scales, from individual units to globally integrated supply
chains, enabled by revolutionary progress in sensing and wireless communication
technologies is another source of such data overload.
But it
is not raw data that we are after. What we desire are in-depth knowledge and
mechanistic, first-principles based, understanding of the underlying phenomena
that can be modeled to aid us in rational decision making. However, knowledge
extraction and model development from this data deluge pose unprecedented
challenges, as well as offer tremendous opportunities. Past approaches
developed in a “data poor” era do not work well in this new world. The new
environment requires imaginative thinking and innovative approaches to address
these challenges. This is where informatics concepts and cyberinfrastructure breakthroughs
such as Watson will play a crucial role. In this presentation, I will discuss
the challenges, opportunities and emerging trends using case studies drawn from
diverse areas such as molecular products design, pharmaceutical manufacturing
and systemic risks management in complex plants.