Publications

A Two-Level Scheme for Training Partition of Unity Networks

27th International Domain Decomposition Conference

Eric Christopher Cyr, Nathaniel Albert Trask, Amelia Henriksen, Carianne Martinez

Accurate Compression of Tabulated Chemistry Models with Partition of Unity Networks

Combustion Science and Technology

Elizabeth Armstrong, Michael Alan Hansen, Robert C. Knaus, Nathaniel Albert Trask, John C. Hewson, James Sutherland

Continuum semiconductor physics model compression via Data-driven Discrete Exterior Calculus

8th European Congress on Computational Methods in Applied Sciences and Engineering

Andy Huang, Nathaniel Albert Trask, Xujiao Gao, Shahed Reza, Ravi Ghanshyam Patel, Christopher Brissette, Xiaozhe Hu

Scalable algorithms for physics-informed neural and graph networks

Data Centric Engineering

Khemraj Shukla, Mengjia Xu, Nathaniel Albert Trask, George Karniadakis

https://www.osti.gov/search/identifier:1872036

Reinforcement learning for material calibration via kalman filter estimation

USACM Thematic Conference on Uncertainty Quantification for Machine Learning Integrated Physics Modeling

Ruben Villarreal, Thomas Anthony Catanach, Reese E. Jones, Nathaniel Albert Trask, Sharlotte LorraineBolyard Kramer, Nikolaos Vlassis N., WaiChing Sun

Improving chemistry tabulation with partition of unity networks

18th International Conference on Numerical Combustion

Elizabeth Armstrong, Michael Alan Hansen, Robert C. Knaus, Nathaniel Albert Trask, John C. Hewson, James Sutherland

Structure preserving machine learning for data-driven multiscale/multiphysics modeling

Stanford engineering seminar

Nathaniel Albert Trask

Improving Chemistry Tabulation with Partition of Unity Networks

18th International Conference on Numerical Combustion

Elizabeth Armstrong, Michael Alan Hansen, Robert C. Knaus, Nathaniel Albert Trask, John C. Hewson, James Sutherland

Physics-informed Multimodal Autoencoders (PIMA) High-throughput science through modal fusion

crunch webinar

Nathaniel Albert Trask

Accurate Compression of Tabulated Chemistry Models with Partition of Unity Networks

39th International Symposium on Combustion

Elizabeth Armstrong, Michael Alan Hansen, Robert C. Knaus, Nathaniel Albert Trask, John C. Hewson, James Sutherland

Remapping native fields for climate applications

15th World Congress on Computational Mechanics (WCCM-XV)

Paul Allen Kuberry, Mauro Perego, Nathaniel Albert Trask, Pavel B. Bochev

Sandia / IBM Discussion on Machine Learning for Materials Applications

David John Littlewood, Mitchell Wood, David Montes de Oca Zapiain, Sivasankaran Rajamanickam, Nathaniel Albert Trask

https://www.osti.gov/search/identifier:1828106

Structure preserving machine learning for data-driven multiscale/multiphysics modeling

UPenn Engineering department colloquium

Nathaniel Albert Trask

Machine learning of Physics-Informed Graph Neural Networks from TCAD models

Mechanistic Machine Learning and Digital Twins for Computational Science, Engineering & Technology (IACM conference) 2021

Andy Huang, Nathaniel Albert Trask, Xujiao Gao, Shahed Reza, Ravi Ghanshyam Patel, Christopher Brissette, Xiaozhe Hu

Discovery of structure-preserving finite element spaces for multiscale

Mechanistic Machine Learning and Digital Twins for Computational Science, Engineering & Technology

Nathaniel Albert Trask

ASCEND: Asymptotically compatible strong form foundations for nonlocal discretization

Nathaniel Albert Trask, Marta D'Elia, David John Littlewood, Stewart A. Silling, Jeremy Trageser, Michael R. Tupek

https://www.osti.gov/search/identifier:1820006

Machine learning surrogates of high-fidelity electrical models

REHEDS External Review

Andy Huang, Xujiao Gao, Shahed Reza, Nathaniel Albert Trask, Ian Zachary Wilcox, Candace Pauline Diaz, Ravi Ghanshyam Patel

A data-driven exterior calculus for model discovery

Usacm

Nathaniel Albert Trask

Modal Operator Regression for Extracting Nonlocal Continuum Models

Usnccm16

Ravi Ghanshyam Patel, Nathaniel Albert Trask, Mitchell Wood, Eric Christopher Cyr

An Adaptive Basis Perspective to Improve Initialization and Accelerate Training of DNNs

Fomics-dadsi Seminars On Scientific Learning

Eric Christopher Cyr, Mamikon Gulian, Kookjin Lee (ASU), Ravi Ghanshyam Patel, Mauro Perego, Nathaniel Albert Trask

https://www.osti.gov/search/identifier:1872708

Structure preserving architectures for SciML

Philms webinar

Nathaniel Albert Trask

https://www.osti.gov/search/identifier:1872183

ASCeND: ASymptotically Compatible Strong Form Foundations for Nonlocal Discretization

Sandia Academic Alliance Spring 2021 UT Austin LDRD Virtual Poster Session

Barun Das, Masoud Behzadinasab, Nathaniel Albert Trask, John Foster

https://www.osti.gov/search/identifier:1862184

Multiscale training for Physics-informed Neural Networks

Copper Mountain Conference On Multigrid Methods

Ravi Ghanshyam Patel, Nathaniel Albert Trask, Eric Christopher Cyr

https://www.osti.gov/search/identifier:1861255

Greedy Fiedler Spectral Partitioning for Data-driven Discrete Exterior Calculus

Association for the Advancement of Artificial Intelligence - Machine Learning for the Physical Sciences (AAAI-MLPS) 2021

Andy Huang, Nathaniel Albert Trask, Christopher Brissette, Xiaozhe Hu

https://www.osti.gov/search/identifier:1859685

Making physics-informed ML work

Informal presentation for ML reading group at LANL

Nathaniel Albert Trask

https://www.osti.gov/search/identifier:1856302