SEARCH · Engineering Papers
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
The artdaq toolkit is a data-acquisition framework designed for high-energy physics experiments. It provides a flexible, reliable backbone for data transfers and has several locations where users can perform custom analysis tasks using the art framework.
Growing interest in Artificial Intelligence (AI) has resulted in a surge in demand for faster methods of Machine Learning (ML) model training and inference. This demand for speed has prompted the use of high performance computing (HPC) systems that excel in managing distributed workloads. Because data is the main fuel for AI applications, the performance of the storage and I/O subsystem of HPC systems is critical. In the past, HPC applications accessed large portions of data written by simulations or experiments or ingested data for visualizations or analysis tasks. ML workloads perform small reads spread across a large number of random files. This shift of I/O access patterns poses several challenges to modern parallel storage systems. In this paper, we survey I/O in ML applications on HPC systems, and target literature within a 6-year time window from 2019 to 2024. We define the scope of the survey, provide an overview of the common phases of ML, review available profilers and benchmarks, examine the I/O patterns encountered during offline data preparation, training, and inference, and explore I/O optimizations utilized in modern ML frameworks and proposed in recent literature. Lastly, we seek to expose research gaps that could spawn further R&D.
National Energy Technology Laboratory and Covestro LLC. will collaborate on a project titled, “Decarbonizing Solvent Chemistry Through Microwave Processing”, which was selected for funding by DOE’s Office of Energy Efficiency and Renewable Energy (EERE) Industrial Efficiency and Decarbonization Office (IEDO) FOA DE-EE0002997. The project aims to develop a microwave-based approach for low-heat aqueous-based industry-relevant reactions currently conducted using a conventional fossil-energy fueled hydrothermal reactor. The team has combined expertise in the areas of polymer production, microwave assisted reactions and scale-up, and life cycle analysis to perform the tasks proposed.
The objective of the Midwest Regional Carbon Initiative (MRCI) project is to implement a collaborative Regional Initiative (RI) to accelerate the deployment of carbon capture, and storage (CCS) in the Midwest-Northeastern quadrant of the United States. This report is a Technical Summary report describing work performed on Tasks 2.4 (Conducting Regional/Subregional Analysis) and 2.5 (Assessing and Managing Risk) during the MRCI project. In Task 2.4, detailed numerical reservoir simulation models were developed for selected carbon storage (CS) systems identified under Task 2.1 (Battelle, 2021a) in the MRCI study area. The objective of Task 2.4 is to demonstrate a dynamic modeling methodology for evaluating the suitability of the (selected) CS systems in the MRCI region for hosting a commercial-scale storage project. In this study, CO2 injectivity was evaluated for different CS systems with an annual injection rate of 1 million metric tonnes (MMT) of CO2 considered as the minimum requirement for a commercial scale project. The objective of Task 2.5 is to assess key risks associated with storing CO2 in the different CS systems across the MRCI region and to demonstrate a method(s) for assessing these risks that may be used by developers of future CO2 storage projects in the region. The risk analysis was limited to evaluating two types of leakage risks (i.e., wellbore leakage, flow across unfractured caprock) at three modeled sites considered in Task 2.4.
Static analysis is a widely used technique for analyzing various aspects of programs. However, as programs become more complex, static analysis tools require larger resources, such as CPU time and memory, to perform the same tasks. Moreover, the source code of programs may not always be accessible, requiring static analysis to be performed on the binary executable code directly. To overcome these challenges, we propose a lightweight static analysis framework called LSAFE, which constructs control flow graphs (CFGs) and data dependency graphs (DDGs) of target programs with optimized performance in terms of CPU and memory usage. We evaluated the proposed framework using both Spec benchmark programs and real-world industrial applications, and found that it outperformed Angr, an existing state-of-the-art static analysis tool. Additionally, we demonstrate a case study that utilizes the CFG generated by LSAFE to detect memory leaks.
Deep neural networks are known to be resilient to random bit-wise faults in their parameters. However, this resilience has primarily been established through evaluations of classification models. The extent to which this claim holds for large-language models remains underexplored. In this work, we conduct an extensive measurement study on the impact of random bitwise faults in commercial-scale language models. We perform an in-depth analysis of the resulting generation outputs. We first expose that these language models are not truly resilient to random bit-flips. While aggregate metrics such as accuracy may suggest resilience, an in-depth inspection of the generated outputs shows significant degradation in text quality. Our analysis also shows that tasks requiring more complex reasoning suffer more from performance and quality degradation. Moreover, we extend our analysis to models with augmented reasoning capabilities, such as Chain-of-Thought or Mixture of Experts architectures, and characterize their failure scenarios under random bit-flips.
This repo contains software used to clean and assemble high-throughput sequencing data containing viruses. The input is raw illumina sequencing reads and the output is a database of high-quality viral genomes. The specific application is to wastewater viral concentrates but it is not restricted to that sample type. The software is composed of Nextflow workflows and a set of custom Python and bash scripts that call publicly available bioinformatics tools to accomplish obvious tasks in data analysis in a high performance computing environment. For detailed information, please see the repo's README file.
This file provides the documentation for several Python scripts that were developed by Sandia National Laboratories to enhance the automation and customization capabilities for performing various distribution system planning and analysis tasks in CYME. Specifically, these scripts (.py files detailed in Figure 1) enable the user to evaluate different distribution system configurations and the resulting impacts on hosting capacity results and other metrics. In general, these scripts—and the accompanying documentation—provide the foundation upon which future customized tools can be created. For example, the scripts show how to extract and modify parameters of various circuit components, set up and run analyses using built-in CYME tools (iteratively), and export reports for further evaluations and comparisons. Thus, the capabilities and syntaxes used in the scripts can be adapted and leveraged for countless other objectives.
Large language models have revolutionized artificial intelligence by enabling large, generalizable models trained through self-supervision. This paradigm has inspired the development of scientific foundation models (FMs). However, applying this capability to experimental particle physics is challenging due to the sparse, spatially distributed nature of detector data, which differs dramatically from natural language. This work addresses if an FM for particle physics can scale and generalize across diverse tasks. We introduce a new dataset with more than 11 million particle collision events and a suite of downstream tasks and labeled data for evaluation. We propose a novel self-supervised training method for detector data and demonstrate its neural scalability with models that feature up to 188 million parameters. With frozen weights and task-specific adapters, this FM consistently outperforms baseline models across all downstream tasks. The performance also exhibits robust data-efficient adaptation. Further analysis reveals that the representations extracted by the FM are task-agnostic but can be specialized via a single linear mapping for different downstream tasks.
Rapid progress in aberration corrected electron microscopy necessitates development of robust methods for the identification of phases, ferroic variants, and other pertinent aspects of materials structure from imaging data. While unsupervised methods for clustering and classification are widely used for these tasks, their performance can be sensitive to hyperparameter selection in the analysis workflow. In this study, the effects of descriptors and hyperparameters are explored on the capability of unsupervised ML methods to distill local structural information, exemplified by the discovery of polarization and lattice distortion in Sm − dopped BiFeO 3 (BFO) thin films. It is demonstrated that a reward-driven approach can be used to optimize these key hyperparameters across the full workflow, where rewards are designed to reflect domain wall continuity and straightness, ensuring that the analysis aligns with the material's physical behavior. This approach allows the discovery of local descriptors that are best aligned with the specific physical behavior, providing insight into the fundamental physics of materials. The reward driven workflow is further extended to disentangle structural factors of variation via an optimized variational autoencoder (VAE). Lastly, the importance of well-defined rewards is explored as a quantifiable measure of the success of the workflow.
Polynomial chaos expansions (PCEs) are widely used for uncertainty quantification (UQ) tasks, particularly in the applied mathematics community. However, PCE has received comparatively less attention in the statistics literature, and fully Bayesian formulations remain rare—especially with implementations in R. Motivated by the success of adaptive Bayesian machine learning models such as BART, BASS and BPPR, we develop a new fully Bayesian adaptive PCE method with an efficient and accessible R implementation: khaos. Our approach includes a novel proposal distribution that enables data-driven interaction selection and supports a modified g-prior tailored to PCE structure. Through simulation studies and real-world UQ applications, we demonstrate that the Bayesian adaptive PCE provides competitive performance for surrogate modeling, global sensitivity analysis and ordinal regression tasks.
One Modeling Framework for Integrated Tasks (OMFIT) is a widely used software tool in the magnetic fusion research community. OMFIT provides magnetic fusion energy researchers with a framework for the development of special-purpose physics modules. This paper describes an OMFIT physics module pertaining to the Doppler Backscattering (DBS) fusion plasma diagnostic. DBS measures density fluctuations and flow velocity through plasma scattering of electromagnetic waves. The OMFIT DBS module was developed to analyze experimental DBS data and facilitate modeling of DBS systems installed on multiple tokamak devices. The OMFIT DBS module is designed to support several analysis workflows: detailed analysis of experimental data, experimental planning, and theory-based synthetic diagnostic modeling. The DBS module uses integrated modeling by leveraging other OMFIT physics modules to perform tasks related to DBS, e.g. ray/beam–tracing simulations, edge-localized mode–synchronized data analysis, magnetic equilibrium reconstruction, and fitting kinetic profile data. Furthermore, this paper describes several supported workflows and serves a reference for the OMFIT DBS module.
In physical networks trained using supervised learning, physical parameters are adjusted to produce desired responses to inputs. An example is an electrical contrastive local learning network of nodes connected by edges that adjust their conductances during training. When an edge conductance changes, it upsets the current balance of every node. In response, physics adjusts the node voltages to minimize the dissipated power. Learning in these systems is therefore a coupled double-optimization process, in which the network descends both a cost landscape in the high-dimensional space of edge conductances and a physical landscape—the power dissipation—in the high-dimensional space of node voltages. Because of this coupling, the physical landscape of a trained network contains information about the learned task. Here, we derive a structure-function relation for trained tunable networks and demonstrate that all the physical information relevant to the trained input-output relation can be captured by a tuning susceptibility, an experimentally measurable quantity. We supplement our theoretical results with simulations to show that the tuning susceptibility is correlated with functional importance and that we can extract physical insight into how the system performs the task from the conductances of highly susceptible edges. Our analysis is general and can be applied directly to mechanical networks, such as networks trained for protein-inspired function such as allostery.
We present Data-Driven Invertible Neural Surrogates of Atmospheric transmission, or DINSAT. DINSAT is a novel framework for inferring an atmospheric transmission profile from a spectral scene. This framework leverages a lightweight, physics-based simulator that is automatically tuned -- by virtue of autodifferentiation and differentiable programming -- to construct a surrogate atmospheric profile to model the observed data. The framework has utility in (i) performing atmospheric correction, (ii) recasting spectral data between various modalities (e.g. radiance and reflectance at the surface and at the sensor), and (iii) inferring atmospheric transmission profiles, such as absorbing bands and their relative magnitudes. We demonstrate the utility of these methods by performing a canonical atmospheric correction task for the purposes of further analysis - in this case, target detection within a scene.
The scientific computing paradigm has transitioned from compute-intensive to I/O-intensive and memory-intensive in the past decade, especially when data-driven science has become common practice. Numerous empirical I/O-aware scheduling optimizations have been developed by incorporating I/O capacity and bandwidth as constraints into scheduling. Unfortunately, there is a lack of data flow (I/O) characterization tool and an understanding of trade-offs between concurrency, locality, and I/O bandwidth. To bridge the gap, this work 1) presents a set of descriptors to characterize, organize, and visualize I/O profiles, including flow size, I/O bandwidth, and operation count, which group data flows by I/O types, tasks, and files; 2) proposes an I/O Roofline model-based trade-off analysis to find the optimal trade-off between flow operational intensity, concurrency, and flow performance. The I/O descriptors generate useful insights into complicated I/O behaviors, suggesting distinct concurrency, storage, and scheduling to be used by types, tasks, and files. The proposed trade-off analysis guides scheduling decisions that generate resource assignment with the best flow parallelism. We evaluate our I/O-aware scheduling methodology on a highly I/O-intensive workflow–1000 Genomes. The experimental results demonstrate speedups of up to 2.4× compared to the state-of-the- art methods.
Scientific discovery increasingly requires executing heterogeneous scientific workflows on high-performance computing (HPC) platforms. Heterogeneous workflows contain different types of tasks (e.g., simulation, analysis, and learning) that need to be mapped, scheduled, and launched on different computing. That requires a software stack that enables users to code their workflows and automate resource management and workflow execution. Currently, there are many workflow technologies with diverse levels of robustness and capabilities, and users face difficult choices of software that can effectively and efficiently support their use cases on HPC machines, especially when considering the latest exascale platforms. We contributed to addressing this issue by developing the ExaWorks Software Development Kit (SDK). The SDK is a curated collection of workflow technologies engineered following current best practices and specifically designed to work on HPC platforms. We present our experience with (1) curating those technologies, (2) integrating them to provide users with new capabilities, (3) developing a continuous integration platform to test the SDK on DOE HPC platforms, (4) designing a dashboard to publish the results of those tests, and (5) devising an innovative documentation platform to help users to use those technologies. Our experience details the requirements and the best practices needed to curate workflow technologies, and it also serves as a blueprint for the capabilities and services that DOE will have to offer to support a variety of scientific heterogeneous workflows on the newly available exascale HPC platforms.
Manual labeling for machine learning tasks such as image classification is tedious and labor-intensive; as a result, scientific datasets suitable for deep learning applications are scarce and limited. While data augmentation techniques have shown promise for extending image datasets, very little work has been done to understand the impact of combining multiple augmentation methods sequentially or the limits of their effectiveness when combined. Our work addresses this gap by examining how standard and combinatorial data augmentation affects the performance of machine learning models when trained on small datasets for label classification tasks. For our analysis, we generate single, double and quadruple-augmented datasets for a microscopy image classification task using six standard augmentation methods, and compare the resultant improvements observed in binary classification accuracy with three standard image classification models (DenseNet169, MobileNetV2, ResNet101V2). Our experiments show a non-monotonic relationship between the number of simultaneous augmentation methods and classification accuracy, indicating that there is a trade-off between the degree of augmentation and the model performance. These findings suggest that the optimal number of augmentation methods will vary by domain and use case. We also find that the order in which augmentation methods are applied to a limited dataset matters when combining augmentation schemes, with our use case showing performance differences up to 2.6% when the augmentation order is reversed for double-augmented datasets. Our work offers insights to the limits of data augmentation when working on image classification tasks with limited datasets.
This joint initiative is aimed at extending our understanding of real DAC testing conditions at the NETL DAC testbed facility. Of particular focus will be: • Small Scale testing of powdered and formulated materials (supplied by ExxonMobil) to evaluate various performance metrics under DAC process cycles • Pilot scale testing of formulated materials at larger scales ExxonMobil will work with NETL to shake down equipment, validate testing methods, and define best practices for data analysis. Three tasks are proposed: 1. Validation of multi-cycle test data on powdered and formulated materials to benchmark various performance metrics of these materials. 2. Steam regeneration of powdered samples at small scale to define baseline performance under commercially relevant conditions. 3. Pilot scale testing of larger formulated materials to test commercially relevant samples under actual process cycles.