Data-Driven Model Reduction, Scientific Frontiers, and Applications (2024)

November 7, 2024
Texas A&M University
College Station, TX
Joe C. Richardson Petroleum Engineering Building (RICH) 910

Description

Data-driven modeling is a cornerstone for many applications. Finding appropriate scale-level models conditioned to the data requires some type of reduced-order modeling. This workshop brings together experts working on mathematical, statistical, computational, and engineering aspects of model reduction to share their research experience.

The workshop will be hosted by Texas A&M University in College Station, Texas, and is supported by the Institute for Scientific Computation.

We will provide and update information for this workshop online at http://isc.tamu.edu/events/Fall2024/.

Registration

There is no registration required to participate in this workshop. Participants may come and go as they please.

Organizing Committee

Yalchin Efendiev, Institute for Scientific Computation & Department of Mathematics
Eduardo Gildin, Harold Vance Department of Petroleum Engineering
Joseph Kwon, Artie McFerrin Department of Chemical Engineering
Jean Ragusa, Institute for Scientific Computation & Department of Nuclear Engineering

Speakers

Anirban Bhattacharya, Department of Statistics: On the Convergence of Coordinate Ascent Variational Inference
Suparno Bhattacharyya, Institute of Data Science: Uncertainty Quantification with Hyper-Reduced Order Models
Suman Chakravorty, Department of Aerospace Engineering: Information State Based Reinforcement Learning for the Control of Partially Observed Nonlinear Systems
Yalchin Efendiev, Institute for Scientific Computation & Department of Mathematics: Multicontinuum Homogenization and Applications
Eduardo Gildin, Harold Vance Department of Petroleum Engineering: Nonintrusive Reduced-Order Modeling for Reservoir Simulation Using Operator Inference
David Huckleberry Gutman, Industrial and Systems Engineering
Joseph Kwon, Artie McFerrin Department of Chemical Engineering: Creating Universal Chemical Language: Leveraging Generative AI to Enhance Molecular Fingerprinting for Quantitative Structure-Property-Performance Relationship
Matthias Maier, Department of Mathematics: Modeling and Optimization of Optical Layered Heterostructures
Daniele Mortari, Department of Aerospace Engineering: New Applications of the Theory of Functional Connections
Jonathan Siegel, Department of Mathematics: Convergence and Error Control of Consistent PINNs for Elliptic PDEs
Timo Sprekeler, Department of Mathematics: Effective Diffusion Matrices via Fokker—Planck—Kolmogorov Equations and Beyond
Freddie Witherden, Department of Ocean Engineering: Online Compression of High-Order CFD Solutions Using Machine Learning
Rami Younis, Harold Vance Department of Petroleum Engineering: Amortizing the Costs of Scientific Machine Learning at Scale: Timely Challenges and Opportunities

Schedule

All workshop presentations will take place in Joe C. Richardson Petroleum Engineering Building (RICH) 910. Please note that the schedule is tentative and subject to change. All times listed are local time.

Thursday, November 7, 2024

9–9:05 a.m.: Welcome
9:05–9:30 a.m.: Daniele Mortari, Department of Aerospace Engineering; New Applications of the Theory of Functional Connections
9:30–9:55 a.m.: Timo Sprekeler, Department of Mathematics; Effective Diffusion Matrices via Fokker—Planck—Kolmogorov Equations and Beyond
9:55–10:20 a.m.: Suman Chakravorty, Department of Aerospace Engineering; Information State Based Reinforcement Learning for the Control of Partially Observed Nonlinear Systems
10:20–10:35 a.m.: Morning Break
10:35–11 a.m.: Matthias Maier, Department of Mathematics; Modeling and Optimization of Optical Layered Heterostructures
11–11:25 a.m.: Anirban Bhattacharya, Department of Statistics; On the Convergence of Coordinate Ascent Variational Inference
11:25–11:50 a.m.: David Huckleberry Gutman, Industrial and Systems Engineering
11:50 a.m.–12:15 p.m.: Joseph Kwon, Artie McFerrin Department of Chemical Engineering; Creating Universal Chemical Language: Leveraging Generative AI to Enhance Molecular Fingerprinting for Quantitative Structure-Property-Performance Relationship
12:15–1:15 p.m.: Lunch Break
1:15–1:40 p.m.: Jonathan Siegel, Department of Mathematics; Convergence and Error Control of Consistent PINNs for Elliptic PDEs
1:40–2:05 p.m.: Rami Younis, Harold Vance Department of Petroleum Engineering; Amortizing the Costs of Scientific Machine Learning at Scale: Timely Challenges and Opportunities
2:05–2:30 p.m.: Freddie Witherden, Department of Ocean Engineering; Online Compression of High-Order CFD Solutions Using Machine Learning
2:30–2:45 p.m.: Afternoon Break
2:45–3:10 p.m.: Yalchin Efendiev, Institute for Scientific Computation & Department of Mathematics; Multicontinuum Homogenization and Applications
3:10–3:35 p.m.: Suparno Bhattacharyya, Institute of Data Science; Uncertainty Quantification with Hyper-Reduced Order Models
3:35–4 p.m.: Eduardo Gildin, Harold Vance Department of Petroleum Engineering; Nonintrusive Reduced-Order Modeling for Reservoir Simulation Using Operator Inference
4–4:05 p.m.: Closing Remarks

Contact Information

If you have any questions concerning this workshop, email Brad Shumbera at shumbera@tamu.edu.

Return to the Quick Links Selection Button.