Please enjoy the talks below from our 2022 session!
SAND Numbers will be listed for all SNL talks. Speakers were employed at Sandia at the time of the Workshop unless otherwise noted.
Day 1 – 7/25/2022
| Title | Speaker | Time | Media |
|---|---|---|---|
| DAY 1, SESSION 1 | |||
| Keynote: Moving the Needle in MLDL Research for National Security | Kevin Dixon | 1:05 PM | VIDEO, SAND2022-9955 V |
| What is the Best Model? A Statistical Approach to Compression Analytics | Alex Foss | 1:35 PM | PPTX,SAND2022-9696 C VIDEO,SAND2022-9696 C |
| Machine Learning Applications for Defeaturing and Model Preparation | Steven Owen | 1:50 PM | PPTX,SAND2021-8928 C VIDEO,SAND2022-9915 V |
| gLaSDI: Parametric physics-informed greedy latent space dynamics identification | Youngsoo Choi(Lawrence Livermore National Laboratory) | 2:05 PM | PPTX VIDEO |
| Boosting Deep learning Performance using Combinatorial Fusion | Suman Sirimulla(Roivant Sciences) | 2:20 PM | VIDEO |
| Machine Learning Classification for Rapid CAD-to-Simulation | Steven Owen | 2:35 PM | PPTX,SAND2022-2014C VIDEO,SAND2022-9914 V |
| Identifying and Explaining Anomalous Activity in Surveillance Video with Compression Algorithms | Renee Gooding | 2:50 PM | PPTX,SAND2022-8652C VIDEO,SAND2022-9552V |
| A novel approach to determine manufacturing processing parameters that are correlated to end-of-manufacturing test performance using multivariate analysis and iterative predictive modeling | Rosalie Multari | 3:05 PM | PPTX,SAND2022-9063 C VIDEO,SAND2022-9479 C |
Day 2 – 7/26/2022
| Title | Speaker | Time | Media |
|---|---|---|---|
| DAY 2, SESSION 1 | |||
| Keynote: Spatial Statistics & Machine Learning: Why and how should you consider spatial autocorrelation? | Lyndsay Shand | 1:05 PM | PPTX,SAND2022-9708 C VIDEO,SAND2022-9830V |
| Bi-fidelity Training of Neural Networks | Subhayan De(University of Colorado Boulder) | 1:30 PM | PPTX VIDEO |
| Widget Feature Analysis: A Tale of Two Features | Sarah Ackerman | 1:45 PM | PPTX,SAND2022-10076 PE VIDEO,SAND2022-10075 V |
| Differentiable constrained optimization as lingua franca for scientific machine learning | Jan Drgona(Pacific Northwest National Laboratory) | 2:00 PM | PPTX VIDEO |
| Decision Science for Machine Learning (DeSciML) | Rich Field | 2:15 PM | PPTX,SAND2022-9199 C VIDEO,SAND2022-9739 O |
| Safety for Learning-based Differentiable Predictive Control | Wenceslao Shaw-Cortez (Pacific Northwest National Laboratory) | 2:30 PM | PPTX VIDEO |
| Training and Generalization of Residual Neural Networks as Discrete Analogues of Neural ODEs | Khachik Sargsyan | 2:45 PM | PPTX,SAND2022-9064 C VIDEO,SAND2022-9536 C |
| ChemNODE: A neural ordinary differential equations approach for accelerating detailed chemistry calculations in reacting flow CFD | Tadbhagya Kumar(Argonne National Laboratory) | 3:00 PM | VIDEO |
| DAY 2, SESSION 2 | |||
| Embedded uncertainty estimation for data-driven surrogates to enable trustworthy ML for UQ | Tim Wildey and Gianluca Geraci | 3:40 PM | PPTX,SAND2022-9156 C VIDEO,SAND2022-9840 O |
| Testing the Impact of Specificity on Human Interpretations of State Uncertainty | Laura Matzen | 3:55 PM | PPTX,SAND2022-9130 O VIDEO,SAND2022-9746 V |
| Learning from Multi-fidelity Sources Under Uncertainty | Ramin Bostanabad(University of California, Irvine) | 4:05 PM | PPTX VIDEO |
| A Bayesian Network Pipeline for Detection of Cyberattacks | Nathanael Brown | 4:20 PM | TBD |
| Data-Driven Model-Form Uncertainty with Bayesian Statistics and Neural Differential Equations | Erin C.S. Acquesta | 4:45 PM | PPTX VIDEO,SAND2022-9958 PE |
| Error-in-variables modelling for operator learning | Ravi Patel | 5:00 PM | PPTX,SAND2022-5307 C VIDEO,SAND2022-9432 C |
Day 3 – 7/27/2022
| Title | Speaker | Time | Media |
|---|---|---|---|
| DAY 3, SESSION 1 | |||
| Keynote: Predicting Shallow Marine Gas Occurrence using Geospatial Machine Learning Combined with Mechanistic Subsurface Simulation | Michael Nole | 1:05 PM | PPTX,SAND2022-9529 C Video,SAND2022-9529 C |
| Python Data-Driven Model Integration for the Xyce Circuit Simulator | Paul Kuberry | 1:35 PM | PPTX,SAND2022-9031 C Video,SAND2022-9356 V |
| A Generalized Workflow for Creating Machine Leaning-Powered Compact Models of Multi-state Devices | Ahmedullah Aziz(University of Tennessee Knoxville) | 1:50 PM | PPTX Video |
| Automated knowledge sharing with NLP ensemble recommendations to enhance laboratory operations | Matthew T. Dearing(Argonne National Laboratory) | 2:00 PM | PPTX Video |
| Use of Machine Learning for Signature Development in a Multi-Sensor Environment for Safeguard Applications of Solvent Extraction Processes | Dr. Cody Walker(Idaho National Laboratory) | 2:15 PM | PPTX Video |
| Implementation of a Gaussian Process to Autonomously Control and Calibrate the GlueX Central Drift Chamber | Diana McSpadden(Thomas Jefferson National Accelerator Facility) | 2:25 PM | PPTX Video |
| POMDP Modeling for Cyber-Defense of Industrial Control Systems | Robert G. Cole | 2:35 PM | PPTX,SAND2022-9058C Video,SAND2022-9273V |
| Predicting the success rates of quantum circuits with artificial neural networks | Daniel Hothem | 2:50 PM | PPTX,SAND2022-9425 C Video,SAND2022-9485 V |
| DAY 3, SESSION 2 | |||
| Asynchronous Traveling Wave-based Distribution System Protection with Graph Neural Networks | Miguel Jimenez Aparicio | 3:30 PM | Video,SAND2022-9658 V |
| Graph convolutional neural network modeling of vacancy formation for materials discovery in solar thermochemical water splitting | Matthew Witman | 3:45 PM | Video,SAND2022-8352 C |
| Enhanced Physics-constrained Deep Neural Networks for the Redox Flow Battery Modeling | Yucheng Fu(Pacific Northwest National Laboratory) | 4:00 PM | PPTX Video |
| Probabilistic Approaches to Transfer Learning for Sparse and Noisy Data Environments | Wyatt Bridgman | 4:10 PM | PPTX,SAND2022-9310 C Video,SAND2022-9683 V |
| Multifidelity Deep Operator Networks | Amanda Howard(Pacific Northwest National Laboratory) | 4:25 PM | PPTX Video |
| Transfer Learning with Auto-Generated Labels for Cloud Segmentation | Ben Pierce | 4:35 PM | PPTX,SAND2022-9044 PE Video,SAND2022-9372 C |
| Utilization of the critic subnetwork of a generative adversarial network as detector of morphological material change in image data | Ariana Beste | 4:50 PM | PPTX,SAND2022-9134 C Video,SAND2022-9625 V |
Day 4 – 7/28/2022
| Title | Speaker | Time | Media |
|---|---|---|---|
| DAY 4, SESSION 1 | |||
| Keynote: Applications of machine learning in plasma physics | Brad Shadwick(University of Nebraska – Lincoln) | 1:05 PM | PPTX Video |
| Dynamic Role-Based Access Control Policy for Smart Grid Applications: An Offline Deep Reinforcement Learning Approach | Georgios Fragkos(University of New Mexico) | 1:35 PM | Video |
| Shortest Path Navigation using Reinforcement Learning | Tyson Bailey | 1:50 PM | PPTX,SAND2022-9852 C Video,SAND2022-9967 V |
| Using reinforcement learning to control grid operation from near-blackout to high stability while continuing to serve load | Stephen J. Verzi | 2:00 PM | PPTX,SAND2022-9013 PE Video,SAND2022-9541 V |
| Hybrid Deep Reinforcement Learning For Online Distribution Power System Optimization and Control | Nicholas Corrado | 2:15 PM | PPTX,SAND2022-9851 C Video,SAND2022-9968 V |
| Building a new generation of multiscale materials models with machine-learned interatomic potentials | Megan McCarthy | 2:30 PM | PPTX,SAND2022-8952 C Video,SAND2022-9752 V |
| Applying Random Forest Models to Quantify Wildfire Smoke Impacts on Solar Photovoltaic Production | Samuel Gilletly | 2:45 PM | PPTX,SAND2022-9091 C Video,SAND2022-9440 C |
| Discovering governing equations using noisy measurements through projection-based denoising and second order cone programming | Jacqueline Wentz(University of Colorado at Boulder) | 3:00 PM | PPTX Video |
| DAY 4, SESSION 2 | |||
| Simulated X-ray Diffraction and Machine Learning for Interpretation of Dynamic Compression Experiments | David Montes de Oca Zapiain | 3:35 PM | PPTX,SAND2022-8913 C Video,SAND2022-9540 C |
| Neural networks for efficient evaluation of the multi-species Boltzmann collision operator | Stephen Bond | 4:05 PM | TBD |
| S-OPT: A Points Selection Algorithm for Data-Driven Hyper-Reduction in Reduced Order Models | Siu Wun Cheung(Lawrence Livermore National Laboratory) | 4:15 PM | PPTX Video |
| Accelerating Physical Simulations with Reduced Order Models | Dylan Copeland(Lawrence Livermore National Laboratory) | 4:30 PM | PPTX Video |