393 Data Driven Modeling and Decision Making


Description:
Rapid advances in cloud computing, data management, and machine learning has led to new opportunities to integrate systems, computation and decision-making in real time. Initiatives such as Industrie 4.0 and Smart Manufacturing encourage industry, government and academia to work together to advance theory and application. Papers are solicited that describe all aspects of data-driven modeling and decision making as they relate to the chemical manufacturing industries. Industrial contributions and reviews are encouraged. We are interested in theoretical advances in machine learning, applications of learning and related data analysis methods useful for data-driven modeling and decision making in systems with integrated continuous and discrete transitions.

Sponsor:
Data and Information Systems


Chair:
B. Erik Ydstie
Professor
Carnegie Mellon University
Department of Chemical Engineering
5000 Forbes Avenue
Pittsburgh, PA
15213
Email: ydstie@cmu.edu

Co-Chair:
Bethany Nicholson
Senior Member of Technical Staff
Center for Computing Research, Sandia National Laboratories
Albuquerque, NM
60616
Email: blnicho@sandia.gov


Papers:
A Metaheuristic Approach to Best Subset Selection for the Development of Regression-Based Surrogate Models
Owais Sarwar, Carnegie Mellon University; Nick Sahinidis, Carnegie Mellon University
Data-Driven Stochastic Robust Optimization for Process Operation Under Uncertainty
Chao Ning, Cornell University; Fengqi You, Cornell University
Uncertainty Quantification and Stochastic Programming Strategies for Energy Market Participation
Xian Gao, University of Notre Dame; Steven Atkinson, University of Notre Dame; Alexander W. Dowling, University of Notre Dame
Predicting Future Production for Unconventional Resources: A Data-Driven Approach
Sunit Mathur, University of Houston; Matteo Marongiu-Porcu, Schlumberger; Michael Nikolaou, University of Houston
Distributed Approximate Dynamic Programming (dADP) for Data-Driven Optimal Control of Nonlinear Systems
Wentao Tang, University of Minnesota, Twin Cities; Prodromos Daoutidis, University of Minnesota
Data-Driven Evolution Equation Reconstruction for Parameter-Dependent Nonlinear Dynamical Systems
David Sroczynski, Princeton University; Or Yair, Technion - Israel Institute of Technology; Felix Dietrich, Johns Hopkins University; Ronen Talmon, Technion - Israel Institute of Technology; Ioannis G. Kevrekidis, Johns Hopkins University
Integrated Data-Driven Monitoring & Explicit Fault-Aware Control of Chemical Processes: An Adaptive Approach for Smart Operation
Melis Onel, Texas A&M Energy Institute, Texas A&M University; Baris Burnak, Texas A&M University; Efstratios N. Pistikopoulos, Texas A&M Energy Institute, Texas A&M University
Why Plant Operations Are Unstable after All the Design and How Data Science Can Help
S. Joe Qin, University of Southern California; Yining Dong, University of Southern California
Abstract Submissions Closed
See more of this Group/Topical: Computing and Systems Technology Division