Autonomous MultiScale: Embedded Machine Learning for Smart Simulations

Executive Summary

The goal of the project is to enable a new class of multiscale simulations by developing an autonomous framework to efficiently and effectively couple different computing scales through advanced machine learning models. If successful, it has the potential to transform many computational science applications and enable coupled simulations at unprecedented scale and fidelity.

Publications, Presentations, and Patents

S. Fridovich-Keil, B. R. Bartoldson, J. Diffenderfer, B. Kailkhura, and P.-T. Bremer, 2022, “Models Out of Line: A Fourier Lens on Distribution Shift Robustness” (Presentation, ICML 2022 workshop on Principles of Distribution Shift, ICML 2022 PODS Workshop, Hololulu, HI, 2022). https://icml.cc/Conferences/2022/ScheduleMultitrack?event=20543) 

S. Fridovich-Keil, B. R. Bartoldson, J. Diffenderfer, B. Kailkhura, and P.-T. Bremer, 2022, “Models Out of Line: A Fourier Lens on Distribution Shift Robustness” NeurIPS 2022, https://paperswithcode.com/paper/models-out-of-line-a-fourier-lens-on 

Jayaraman J. Thiagarajan, Rushil Anirudh, Vivek Narayanaswamy, Peer-Timo Bremer. "Single Model Uncertainty Estimation via Stochastic Data Centering," Neurips 2022 (spotlight).

V. Narayanaswamy, R. Anirudh, I. Kim, Y. Mubarka, A. Spanias, J. J. Thiagarajan, "Predicting the Generalization Gap in Deep Models Using Anchoring"(Presentation, ICASSP Singapore, May 2022).

Jayaraman J. Thiagarajan, Vivek Narayanaswamy, Puja Trivedi, Jayaraman J. Thiagarajan, "Characterizing Risk Regimes for Safe Deployment of Deep Regression Models" (Presentation, ICML 2023 Workshop on Data-Centric Machine Learning Research, Honolulu, HI, July 2023).

Bhatia, Harsh, Patki, Tapasya A., Brink, Stephanie, Pottier, Loic E., Stitt, Thomas M., Parasyris, Konstantinos, Milroy, Daniel J., Laney, Daniel E., Blake, Robert C., Yeom, Jae-Seung, Bremer, Peer-Timo, and Doutriaux, Charles. "Autonomous MultiScale Library." Computer software. May 01, 2023. https://github.com/LLNL/AMS. https://doi.org/10.11578/dc.20230721.1.

P.T. Bremer, "Multi-Modal Data Representations: Challenges and Opportunities" (Presentation at 1st AI@DOE Workshop, 2021).

P.-T. Bremer,"Cognitive Simulations Connecting Simulations and Experiments" (Presentation, Southern Cal Edison, 2022).

P.-T. Bremer, "Autonomous MultiScale (AMS) Embedded Machine Learning for Smart Simulations" (Presentation, 2022 WPD/WSC CogSim/ML Workshop, LLNL, Livermore, CA, 2022).

J. Gaffney, "Autonomous MultiScale (AMS) Embedded Machine Learning for Smart Simulations" (Poster Presentation, External Review Committee, PLS, Livermore, CA, 2022). 

N. Goldman, L. E. Fried, C. H. Pham, R. K. Lindsey, R. Dettori, "Machine Learning Tools for Long Timescale Simulation of Materials under Reactive Conditions" (Oral Presentation, American Physical Society 2023 March Meeting, Las Vegas, NV, 2023).

P.-T. Bremer, "Autonomous Multiscale Simulations – Turning Synchronous MPI into Asynchronous Workflows" (Presentation, SC22 Workflow BOF, Dallas, TX, November 2022).

P.-T. Bremer, "Autonomous Multiscale Simulations –Embedded Machine Learning for Smart Simulations" (Presentation, BOUT++ Workshop, Livermore, CA, Jan 2023).

P.-T. Bremer, "Autonomous Multiscale Simulations –Embedded Machine Learning for Smart Simulations" (Presentation, COMP ERC, Livermore, CA, April, 2023). 

M. J. Barrow, M. S. Cho, P. E. Grabowski, J. A. Gaffney, R. Anirudh, J. thiagarajan, J. B. Kallman, H. P. Le, H. Scott, P. T. Bremmer, and J. Thathachar, "A Physically Informed Surrogate Approach to Causal System Modeling" (Presentation, AAAI 23 CASD Workshop, Washington, DC, Feb 2023).

J. Gaffney, "Autonomous Multiscale Simulations –Embedded Machine Learning for Smart Simulations" (Presentation, PLS AIML Workshop, Livermore, CA, 2023).