TAMIDS SciML Lab 2021 Workshop

Workshop Aims

This informal workshop is intended to showcase some of the current work being done by members of the Texas A&M community on cutting-edge scientific and engineering problems using physics-informed machine learning. Through the exchange of ideas and results, the workshop also aims to foster coherent research efforts that can lead to new scientific advances and enhance competitiveness for external funding. 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; ML-guided automation of data acquisition and decision-support for complex systems; incorporating approaches such as multi-fidelity surrogate modeling, uncertainty quantification, Bayesian inference; and computational frameworks, systems, and methods for SciML. While recent advances in SciML have been driven primarily by applications in engineering, physical sciences, and systems biology, the workshop encourages discussion of potential applications in other fields that may integrate domain knowledge and models with machine learning.

Workshop Organization

The workshop is open to all members of Texas A&M virtually via Zoom (TAMU authentication required). No registration is required to attend. The workshop will comprise short invited talks from Texas A&M speakers with plenty of time for technical discussion, and a round table discussion to identify challenges and opportunities for collaborative work in SciML at Texas A&M.

Schedule

8:30-8:35	Nick Duffield, Professor, ECE and TAMIDS Director, Welcome
8:35-8:45	Ulisses Braga-Neto, Professor, ECE and TAMIDS SciML Lab Director, Introduction
8:45-9:10	Byung-Jun Yoon, Associate Professor, ECE and Brookhaven National Lab “Optimal experimental design for complex uncertain systems based on coupled ordinary differential equations”
9:10-9:35	Lisa Perez, Associate Director, High Performance Research Computing (HPRC) “Accelerating Computing for Emerging Sciences (ACES): An Innovative Composable Hardware Platform”
9:35-10:00	Ming Zhong, Post-Doctoral Researcher, TAMIDS “Solving nonlinear PDEs with Gaussian Processes and Deep Neural Networks”
10:00-10:25	Dehao Liu,Post-Doctoral Researcher, TAMIDS & MSEN “Physics-Constrained Neural Networks with Minimax Architecture for Predicting Microstructure Evolution”
10:25-10:50	Xingzhuo Chen, Graduate Student, Physics and Astronomy “Using Physics-Informed Neural Network to Calculate Radiative Transfer Problems”
10:50-11:00	Break
11:00-11:25	Giri Arthrey, Associate Professor, Poultry Science “Potential Applications of SciML for Understanding Vertebrate Microbiota Assembly”
11:25-11:50	Emílio Coutinho, Graduate Student, Petroleum Engineering “Stabilized Hyperbolic PDE Solver by Adding Adaptive Localized Artificial Viscosity to Physics-Informed Neural Networks”
11:50-12:15	Jean Ragusa, Professor, Nuclear Engineering “Models with multiple levels of fidelity for radiation effects: a scientific machine learning perspective”
12:15-12:40	Round table discussion. Technical challenges/opportunities for collaboration/Steps for growing SciML at TAMU

TAMU Scientific Machine Learning Mailing List

https://groups.google.com/a/lists.tamu.edu/g/sciml (select “Join Group”; requires login with TAMU NetID)