4 citations · 5 across the 12 of their papers we have counts for
14 papers
Diff-NekRS: A Scalable Differentiable Framework for Multi-Timestep Solver-in-the-Loop Training
Junoh Jung, Riccardo Balin, Bethany Lusch +1
Hybrid physics-machine-learning solvers improve under-resolved simulations by embedding trainable corrections into the time integration. During autoregressive inference, repeated s…
Super-Resolution Initialization of High-Fidelity CFD Simulations for Pebble-Bed Reactors
Guilherme Gottems, Vasil Ivakimov, Luiz Aldeia Machado +13
High-order CFD simulations provide detailed resolution of the heterogeneous interstitial flow in pebble-bed reactors, but their computational cost is high, especially during the in…
Application Failures and Machine Computational Efficiency
Carlo Graziani, Bethany Lusch, O. E. Bronson Messer
We present a framework for evaluating uptime efficiency of Exascale-class scientific computers when application failure rates are appreciable. This is the situation that confronts…
A Scalable Pattern Mining Workflow for Interpretable Machine Log Analysis in High-Performance Computing Environments
Shilpika Shilpika, Bethany Lusch, Eric Pershey +3
Modern supercomputers housed in High Performance Computing (HPC) environments generate massive volumes of log data daily, revealing intricate information and performance metrics ab…
Probabilistic Attribution For Large Language Models
Shilpika Shilpika, Carlo Graziani, Bethany Lusch +2
The generative nature of Large Language Models (LLMs) is reflected in the conditional probabilities they compute to sample each response token given the previous tokens. These prob…
An Incremental Multi-Level, Multi-Scale Approach to Assessment of Multifidelity HPC Systems
Shilpika Shilpika, Bethany Lusch, Venkatram Vishwanath +1
With the growing complexity in architecture and the size of large-scale computing systems, monitoring and analyzing system behavior and events has become daunting. Monitoring data…
Scalable and Consistent Graph Neural Networks for Distributed Mesh-based Data-driven Modeling
Shivam Barwey, Riccardo Balin, Bethany Lusch +5
This work develops a distributed graph neural network (GNN) methodology for mesh-based modeling applications using a consistent neural message passing layer. As the name implies, t…
Mesh-based Super-Resolution of Fluid Flows with Multiscale Graph Neural Networks
Shivam Barwey, Pinaki Pal, Saumil Patel +5
A graph neural network (GNN) approach is introduced in this work which enables mesh-based three-dimensional super-resolution of fluid flows. In this framework, the GNN is designed…
A Multi-Level, Multi-Scale Visual Analytics Approach to Assessment of Multifidelity HPC Systems
Shilpika, Bethany Lusch, Murali Emani +4
The ability to monitor and interpret of hardware system events and behaviors are crucial to improving the robustness and reliability of these systems, especially in a supercomputin…
Efficient high-dimensional variational data assimilation with machine-learned reduced-order models
Romit Maulik, Vishwas Rao, Jiali Wang +6
Data assimilation (DA) in the geophysical sciences remains the cornerstone of robust forecasts from numerical models. Indeed, DA plays a crucial role in the quality of numerical we…
AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification
Romain Egele, Romit Maulik, Krishnan Raghavan +3
Deep neural networks are powerful predictors for a variety of tasks. However, they do not capture uncertainty directly. Using neural network ensembles to quantify uncertainty is co…
PythonFOAM: In-situ data analyses with OpenFOAM and Python
Romit Maulik, Dimitrios Fytanidis, Bethany Lusch +2
We outline the development of a general-purpose Python-based data analysis tool for OpenFOAM. Our implementation relies on the construction of OpenFOAM applications that have bindi…
Deploying deep learning in OpenFOAM with TensorFlow
Romit Maulik, Himanshu Sharma, Saumil Patel +2
We outline the development of a data science module within OpenFOAM which allows for the in-situ deployment of trained deep learning architectures for general-purpose predictive ta…
Recurrent Neural Network Architecture Search for Geophysical Emulation
Romit Maulik, Romain Egele, Bethany Lusch +1
Developing surrogate geophysical models from data is a key research topic in atmospheric and oceanic modeling because of the large computational costs associated with numerical sim…