This event is part of Uncertainty Quantification and AI for Complex Systems View Details

Uncertainty Quantification and Machine Learning for Complex Physical Systems

May 19 — 23, 2025

Description

Back to top

This workshop explores the intersection of uncertainty quantification (UQ) and machine learning (ML) in modeling and analyzing intricate physical phenomena. Participants will examine the challenges of quantifying uncertainties in complex systems across various scientific and engineering domains. The workshop will cover advanced UQ techniques, including Bayesian inference, sensitivity analysis, and probabilistic modeling, tailored for complex physical systems. Attendees will delve into cutting-edge machine learning approaches, such as physics-informed neural networks, deep learning for differential equations, and transfer learning, applied to physical system modeling. The workshop will emphasize the synergy between UQ and ML, exploring how these fields can complement each other to enhance prediction accuracy and reliability in complex systems. Through interactive lectures and group discussions, participants will gain insights into implementing these methods in their research or industrial applications. This workshop is designed for researchers, engineers, and data scientists working with complex physical systems in fields such as fluid dynamics, climate modeling, aerospace engineering, and beyond. Attendees will leave equipped with state-of-the-art knowledge to tackle uncertainty and complexity in their respective domains.

Funding

All funding has been allocated for this event.

In-Person Attendance

We are at capacity for in-person attendees as of May 11, 2025. Registrations received after May 11, 2025 will be asked to attend online only.

Organizers

Back to top
R G
Robert Gramacy Virginia Tech
X L
Xiao Liu Georgia Tech
S M
Simon Mak Duke University
M P
Matthew Pratola Indiana University
Q Z
Qiong Zhang Clemson University

Speakers

Back to top
A B
Annie Booth Virgina Tech
A B
Amy Braverman Jet Propulsion Laboratory (JPL)
A B
Andrew Brown Clemson University
P C
Po-Wen Chang Lawrence Berkeley National Laboratory (LBNL)
P C
Peter Chien University of Wisconsin, Madison
T C
Tiangang Cui University of Syndey
G E
Gwen Edie University of Toronto
D H
Dave Higdon Virginia Tech
Y H
Ying Hung Rutgers University
Y H
Youngdeok Hwang Baruch College
I J
Irene Ji JMP Statistical Software
E K
Emily Kang University of Cincinnati
M K
Matthias Katzfuss University of Wisconsin, Madison
Y L
Yiping Lu Northwestern University
W X
Wei Xie Northeastern University

Schedule

Monday, May 19, 2025
9:00-9:30 CDT
Welcome & Breakfast
9:30-10:30 CDT
Towards prediction uncertainty for computational physics-based models, agent-based models, and machine learning models

Speaker: Dave Higdon (Virginia Tech)

10:30-11:15 CDT
Coffee Break & Networking
11:15-12:15 CDT
Simulation-based Uncertainty Quantification for Remote Sensing Inverse Problems

Speaker: Amy Braverman (Jet Propulsion Laboratory)

12:15-14:00 CDT
Lunch Break
14:00-15:00 CDT
Accelerating Gaussian Process Emulators for Computer Simulations Using Random Fourier Features

Speaker: Peter Chien (University of Wisconsin, Madison)

15:00-16:30 CDT
Coffee Break & Poster Session 1
Tuesday, May 20, 2025
9:00-9:30 CDT
Sign-in & Breakfast
9:30-10:30 CDT
FAIR Universe: Benchmarks for Systematics-Aware Machine Learning in Particle Physics and Cosmology

Speaker: Po-Wen Chang (Lawrence Berkeley National Laboratory)

10:30-11:15 CDT
Coffee Break & Networking
11:15-12:15 CDT
TBA

Speaker: Emily Kang (University of Cincinnati)

12:15-14:00 CDT
Lunch Break
14:00-15:00 CDT
Deep Gaussian processes for estimation of failure probabilities in complex systems

Speaker: Annie Booth (Virginia Tech)

15:00-16:30 CDT
Coffee Break & Poster Session 2
Wednesday, May 21, 2025
9:00-9:30 CDT
Sign-in & Breakfast
9:30-10:30 CDT
Studying the Universe with Astrostatistics

Speaker: Gwen Eadie (University of Toronto)

10:30-11:15 CDT
Coffee Break & Networking
11:15-12:15 CDT
MaLT: Machine-Learning-Guided Test Case Design and Fault Localization of Complex Software Systems

Speaker: Irene Ji (JMP)

12:15-14:00 CDT
Lunch Break
14:00-15:00 CDT
Generative modeling of conditional spatial distributions via autoregressive Gaussian processes

Speaker: Matthias Katzfuss (University of Wisconsin Madison)

15:00-15:30 CDT
Coffee Break & Networking
15:30-16:30 CDT
From Matrix Interpolation to Tensorized Simulation of High-Dimensional Random Variables: with Applications to Rare Event Estimation

Speaker: Tiangang Cu (University of Sydney)

Thursday, May 22, 2025
9:00-9:30 CDT
Sign-in & Breakfast
9:30-10:30 CDT
Digital Twin Calibration with Model-Based Reinforcement Learning

Speaker: Wei Xie (Northeastern University)

10:30-11:15 CDT
Coffee Break & Networking
11:15-12:15 CDT
A Kernel-Based Approach for Modelling Gaussian Processes with Functional Information

Speaker: Andrew Brown (Clemson University)

12:15-14:00 CDT
Lunch Break
14:00-15:00 CDT
Two Tales, One Resolution: Physics-Informed Inference Time Scaling and Precondition

Speaker: Yiping Lu (Northwestern University)

15:00-15:30 CDT
Coffee Break & Networking
15:30-16:30 CDT
Development of Physics-informed Spatio-temporal Models

Speaker: Youngdeok Hwang (CUNY - Bernard M. Baruch College)

Friday, May 23, 2025
9:00-9:30 CDT
Sign-in & Breakfast
9:30-10:30 CDT
TBA

Speaker: Ying Hung (Rutgers University)

10:30-11:15 CDT
Coffee Break & Networking
11:15-11:45 CDT
Concluding Talk

Registration

Back to top

IMSI is committed to making all of our programs and events inclusive and accessible. Contact [email protected] to request disability-related accommodations.

In order to register for this workshop, you must have an IMSI account and be logged in. Please use one of the buttons below to login or create an account.