TAMIDS 2022 SciML Workshop

Workshop Description

The 2022 edition of the annual TAMIDS SciML workshop will be held in person in Blocker 220, in the morning of Tuesday, Nov 8. The aim of this informal workshop is to showcase work by the Texas A&M community on scientific machine learning and to foster the formation of new collaborations. Areas of interest include:

• Physics-informed deep neural networks
• Physics-informed Gaussian processes
• Data-driven model discovery through large-scale simulation
• ML-guided acceleration of numerical simulations
• Bayesian inference in physical models
• Scientific and Engineering applications
  

Workshop Organization

The workshop is open to all members of Texas A&M. No registration is required to attend. The workshop will comprise short invited talks from Texas A&M speakers, which will consist of a 10-minute presentation plus 5-minute technical discussion. There is a zoom option, and the talks will be recorded and made available later on this webpage. There will be a 30-minute coffee break to foster networking and collaboration.

Schedule

8:35-8:40	Nick Duffield, Professor, Electrical and Computer Engineering, and TAMIDS Director Welcome
8:40-8:45	Ulisses Braga-Neto, Professor, Electrical and Computer Engineering, and TAMIDS SciML Lab Director Introduction
8:45-9:00	Lisa Perez, Associate Director, High Performance Research Computing Accelerating Computing for Emerging Sciences (ACES): An Innovative Composable Hardware Platform for the Development of Transformative Machine Learning Workflows
9:00-9:15	Eduardo Gildin, Professor, Petroleum Engineering Development of a Physics-Informed Machine Learning Method for Pressure Transient Test and Reservoir Characterization
9:15-9:30	Ming Zhong, Assistant Professor, Illinois Institute of Technology, former TAMIDS Research Associate New Training Schemes for Physics Informed Machine Learning
9:30-9:45	Lifan Wang, Professor, Physics and Astronomy Finding Cosmic Defects from Images of James Webb Space Telescopes
9:45-10:00	Arun Srinivasa, Professor, Mechanical Engineering Physics informed machine learning for tire-terrain interaction modeling
10:00-10:30	Coffee Break
10:30-10:45	Ulisses Braga-Neto, Professor, Electrical and Computer Engineering Characteristics-Informed Neural Network for Hyperbolic Problems
10:45-11:00	James Cai, Associate Professor, Veterinary Medicine and Biomedical Sciences scTenifoldXct: a semi-supervised method for predicting cell-cell interactions and mapping cellular communication graphs via manifold alignment of intra- and inter-cellular gene regulatory networks
11:00-11:15	Hieu Le and Jian Tao, Assistant Professor, School of Performance, Visualization & Fine Arts Autoencoder-based Lossy Compression for Large-Scale Scientific Data
11:15-11:30	Quincy Huhn and Jean Ragusa, Professor, Nuclear Engineering, and TAMIDS Assistant Director for Project Development PINN for Neutron Transport