Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “distributed machine learning”

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.

At least 559 records · Page 31
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Abstract for CRADA between NETL and Louisiana State University

The National Energy Technology Laboratory (NETL) and Louisiana State University (PARTICIPANT) will collaborate in developing and testing distributed optical fiber CO 2 sensors for CO 2 storage site monitoring. Safe and reliable monitoring of CO 2 storage sites and transport infrastructure is critical for ensuring the long-term effectiveness and integrity of carbon capture and storage (CCS). In this project, the objective is to develop a novel optical fiber-based distributed CO 2 sensor for long-term monitoring of CCS sites and CO 2 pipelines and also implement machine learning to automate leak and structural anomaly detection. This effort aligns with NETL’s mission in reliable and sustainable energy and decarbonization.

47 OTHER INSTRUMENTATION↗
NASA NTRS2018

The Zwicky Transient Facility: Data Processing, Products, and Archive

The Zwicky Transient Facility (ZTF) is a new robotic time-domain survey currently in progress using the Palomar 48-inch Schmidt Telescope. ZTF uses a 47 square degree field with a 600 megapixel camera to scan the entire northern visible sky at rates of ∼3760 square degrees/hour to median depths of g ~ 20.8 and r ~ 20.6 mag (AB, 5σ in 30 sec). We describe the Science Data System that is housed at IPAC, Caltech. This comprises the data-processing pipelines, alert production system, data archive, and user interfaces for accessing and analyzing the products. The real-time pipeline employs a novel image-differencing algorithm, optimized for the detection of point-source transient events. These events are vetted for reliability using a machine-learned classifier and combined with contextual information to generate data-rich alert packets. The packets become available for distribution typically within 13 minutes (95th percentile) of observation. Detected events are also linked to generate candidate moving-object tracks using a novel algorithm. Objects that move fast enough to streak in the individual exposures are also extracted and vetted. We present some preliminary results of the calibration performance delivered by the real-time pipeline. The reconstructed astrometric accuracy per science image with respect to Gaia DR1 is typically 45 to 85 milliarcsec. This is the RMS per-axis on the sky for sources extracted with photometric S/N ≥10 and hence corresponds to the typical astrometric uncertainty down to this limit. The derived photometric precision (repeatability) at bright unsaturated fluxes varies between 8 and 25 millimag. The high end of these ranges corresponds to an airmass approaching ∼2—the limit of the public survey. Photometric calibration accuracy with respect to Pan-STARRS1 is generally better than 2%. The products support a broad range of scientific applications: fast and young supernovae; rare flux transients; variable stars; eclipsing binaries; variability from active galactic nuclei; counterparts to gravitational wave sources; a more complete census of Type Ia supernovae; and solar-system objects.

Frank J. Masci↗
DOE OSTI2026

torch-einshard v1.0

torch-einshard is a Python library for describing local and distributed PyTorch tensor computations with compact, einsum-like notation. Its expressions name logical axes, specify how they are sharded across a PyTorch DeviceMesh, and represent partial reductions. The library automatically performs contractions, permutations, reshaping, splitting, gathering, reduction, reduce-scatter, and repartitioning while preserving autograd. Additional features include sharding-aware FFTs, tensor rolls, halo exchange, sliding windows, 1D–3D convolutions, uneven-shard handling, parameter initialization and gradient management, and cost-based execution planning. It is designed for scientific machine learning and large-model workloads, including tensor-, sequence-, and spatial-parallel MLPs, attention, convolutions, and spectral operations. Compared with manually combining torch.einsum and distributed collectives, torch-einshard expresses both the mathematical operation and data placement in one readable formula. This reduces boilerplate and synchronization errors, keeps forward and backward communication consistent, and allows the library to select optimized collective strategies without changing model code.

Morozov, Dmitriy [Lawrence Berkeley National Labor↗
DOE OSTI2023

The miniJPAS survey quasar selection – II. Machine learning classification with photometric measurements and uncertainties

Astrophysical surveys rely heavily on the classification of sources as stars, galaxies, or quasars from multiband photometry. Surveys in narrow-band filters allow for greater discriminatory power, but the variety of different types and redshifts of the objects present a challenge to standard template-based methods. In this work, which is part of a larger effort that aims at building a catalogue of quasars from the miniJPAS survey, we present a machine learning-based method that employs convolutional neural networks (CNNs) to classify point-like sources including the information in the measurement errors. We validate our methods using data from the miniJPAS survey, a proof-of-concept project of the Javalambre Physics of the Accelerating Universe Astrophysical Survey (J-PAS) collaboration covering ∼1 deg 2 of the northern sky using the 56 narrow-band filters of the J-PAS survey. Due to the scarcity of real data, we trained our algorithms using mocks that were purpose-built to reproduce the distributions of different types of objects that we expect to find in the miniJPAS survey, as well as the properties of the real observations in terms of signal and noise. We compare the performance of the CNNs with other well-established machine learning classification methods based on decision trees, finding that the CNNs improve the classification when the measurement errors are provided as inputs. The predicted distribution of objects in miniJPAS is consistent with the putative luminosity functions of stars, quasars, and unresolved galaxies. Our results are a proof of concept for the idea that the J-PAS survey will be able to detect unprecedented numbers of quasars with high confidence.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

DGaaS: GPU as a Service on Distributed Computing System

In the rapidly evolving landscape of scientific computing, Graphics Processing Units (GPUs) have become indispensable for their unparalleled ability to handle parallel tasks in complex calculations, simulations, and data analysis. Their utility is further magnified in machine learning and AI applications, where they significantly accelerate model training and predictive analytics. Within this context, the Triton Inference Server emerges as a pivotal open-source tool, specializing in AI inferencing and optimizing GPU utilization across various platforms and frameworks. This paper presents an in-depth study on distributed High Throughput Computing (HTC), specifically focusing on the HTCondor framework and its resource provisioning tools, GlideinWMS and HEPCloud. These systems enable large-scale scientific experiments like CMS and DUNE to efficiently access and utilize vast computational resources. The paper explores the core architectural components of GlideinWMS, including jobs, user pools, and worker nodes, and discusses their integration with GPUs and the Triton server. The primary aim of this research is to develop a solution that optimizes GPU utilization by leveraging Glideins and containers. This approach allows computational jobs, particularly those involving AI models, to use GPUs only when essential, thereby facilitating efficient sharing of limited GPU resources. To validate this architecture, the study conducted three key tests involving custom scripts, container-based servers, and Triton server deployments. However, the study faces challenges, notably in locating the Triton server and ensuring secure remote access. To address these issues, future work will focus on developing a proxy mechanism and enhancing security protocols. In conclusion, this study offers a comprehensive roadmap for effective and efficient GPU utilization in distributed High Throughput Computing. It aims to contribute significantly to the scientific community by solving pressing problems and implementing robust solutions in collaboration with the GlideinWMS and HEPCloud teams. The research sets the stage for a more efficient, scalable, and cost-effective paradigm in scientific computing.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Recent Advances in Machine Learning for Fiber Optic Sensor Applications

Over the last three decades, fiber optic sensors (FOS) have gained a lot of attention for their wide range of monitoring applications across many industries, including aerospace, defense, security, civil engineering, and energy. FOS technologies hold great promise to form the backbone for next‐generation intelligent sensing platforms that offer long‐distance, high‐accuracy, distributed measurement capabilities and multiparametric monitoring with resilience to harsh environmental conditions. The major limitations posed by FOS are 1) cross‐sensitivity, 2) enormous volume and large data generation, 3) low data processing speed, 4) degradation of signal‐to‐noise ratio over the fiber length, and 5) overall cost of sensor and interrogator systems. These challenges can be overcome by building advanced data analytics engines enabled by recent breakthroughs in machine learning (ML) and artificial intelligence (AI). This article presents a comprehensive review of recent studies that integrate ML and AI algorithms with FOS technologies. This review also highlights several FOS technology development directions that promise a significant impact on widespread use for several industrial applications, with an emphasis on energy systems monitoring. A perspective on future directions for further research development is also provided.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Data augmentation for disruption prediction via robust surrogate models

The goal of this work is to generate large statistically representative data sets to train machine learning models for disruption prediction provided by data from few existing discharges. Such a comprehensive training database is important to achieve satisfying and reliable prediction results in artificial neural network classifiers. Here, we aim for a robust augmentation of the training database for multivariate time series data using Student t process regression. We apply Student t process regression in a state space formulation via Bayesian filtering to tackle challenges imposed by outliers and noise in the training data set and to reduce the computational complexity. Thus, the method can also be used if the time resolution is high. We use an uncorrelated model for each dimension and impose correlations afterwards via colouring transformations. We demonstrate the efficacy of our approach on plasma diagnostics data of three different disruption classes from the DIII-D tokamak. To evaluate if the distribution of the generated data is similar to the training data, we additionally perform statistical analyses using methods from time series analysis, descriptive statistics and classic machine learning clustering algorithms.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

LDMS-GPU: Lightweight Distributed Metric Service (LDMS) for NVIDIA GPGPUs

GPUs are now a fundamental accelerator for many high-performance computing applications. They are viewed by many as a technology facilitator for the surge in fields like machine learning and Convolutional Neural Networks. To deliver the best performance on a GPU, we need to create monitoring tools to ensure that we optimize the code to get the most performance and efficiency out of a GPU. Since NVIDIA GPUs are currently the most commonly implemented in HPC applications and systems, NVIDIA tools are the solution for performance monitoring. The Light-Weight Distributed Metric System (LDMS) at Sandia is an infrastructure widely adopted for large-scale systems and application monitoring. Sandia has developed CPU application monitoring capability within LDMS. Therefore, we chose to develop a GPU monitoring capability within the same framework. In this report, we discuss the current limitations in the NVIDIA monitoring tools, how we overcame such limitations, and present an overview of the tool we built to monitor GPU performance in LDMS and its capabilities. Also, we discuss our current validation results. Most of the performance counter results are the same in both vendor tools and our tool when using LDMS to collect these results. Furthermore, our tool provides these statistics during the entire runtime of the tool as a time series and not just aggregate statistics at the end of the application run. This allows the user to see the progress of the behavior of the applications during their lifetime.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Data augmentation for disruption prediction via robust surrogate models

The goal of this work is to generate large statistically representative datasets to train machine learning models for disruption prediction provided by data from few existing discharges. Such a comprehensive training database is important to achieve satisfying and reliable prediction results in artificial neural network classifiers. Here, we aim for a robust augmentation of the training database for multivariate time series data using Student-t process regression. We apply Student-t process regression in a state space formulation via Bayesian filtering to tackle challenges imposed by outliers and noise in the training data set and to reduce the computational complexity. Thus, the method can also be used if the time resolution is high. We use an uncorrelated model for each dimension and impose correlations afterwards via coloring transformations. We demonstrate the efficacy of our approach on plasma diagnostics data of three different disruption classes from the DIII-D tokamak. To evaluate if the distribution of the generated data is similar to the training data, we additionally perform statistical analyses using methods from time series analysis, descriptive statistics, and classic machine learning clustering algorithms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Spatiotemporal Learning in Power Modules: Wavelet-Enhanced Forecasting of Thermomechanical Degradation

Detecting internal defects in power electronics packages is critical for their performance and reliability, especially under extreme operating conditions, as these defects can lead to catastrophic failure if not properly addressed. Confocal scanning acoustic microscopy (C-SAM) plays a key role in the nondestructive evaluation of bond layer degradation within a power electronics package by detecting defects such as delamination, voids, and cracks. However, accurately quantifying and predicting these defects from C-SAM images remains a significant challenge due to the low noise-to-signal ratio, which typically arises from both imaging process and bond patterns itself. In this paper, we explore machine learning strategies for processing C-SAM images and providing predictive models of defect growth. We use C-SAM images of sintered copper and sintered silver samples, which are obtained under accelerated thermal experiments, as the representative dataset for our study. We investigate the effect of Fourier transforms and wavelet transforms on these datasets to remove high-frequency noise and address noise across multiple scales with histogram equalization to enhance the contrast and improve the visibility of defects. As a result, defect boundaries can be clearly distinguished, enabling more accurate tracking of their growth over time. We then employ different time-series forecasting algorithms on the denoised images to formulate an image-based lifetime prediction model. Statistical models and deep-learning techniques are trained on images obtained in the early stages of thermal shock, and defect growth in the later stages is predicted. Our work serves as a preliminary attempt to improve the accuracy of lifetime prediction models of power electronics packages, which is critical under extreme operating environments.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Time-drift Aware RF Optimization with Machine Learning Techniques

The Fermilab Linac delivers 400 MeV H- beam to the rest of the accelerator chain. Providing stable intensity, energy, and emittance is key since it directly affects downstream machines. To operate high current beam, accelerators must minimize uncontrolled particle loss; this can be accomplished by minimizing beam longitudinal emittance via RF parameter optimization. However, RF tuning is required daily since the resonance frequency of the accelerating cavities is affected by ambient temperature and humidity variations and thus drifts with time. In addition, the energy and phase space distribution of particles emerging from the ion source are subject to fluctuations. Such drift is not unique to Fermilab, but rather affects most laboratories. We are exploring machine learning (ML) algorithms for automated RF tuning for 2 objectives: optimization of Linac output energy and phase oscillation correction, with an emphasis on time-drift aware modeling that can account for conditions changing over time.

43 PARTICLE ACCELERATORS↗
DOE OSTI2022

A differentiable approach to the maximum independent set problem using dataless neural networks

The success of machine learning solutions for reasoning about discrete structures has brought attention to its adoption within combinatorial optimization algorithms. Such approaches generally rely on supervised learning by leveraging datasets of the combinatorial structures of interest drawn from some distribution of problem instances. Reinforcement learning has also been employed to find such structures. Here, in this paper, we propose a different approach in that no data is required for training the neural networks that produce the solution. In this sense, what we present is not a machine learning solution, but rather one that is dependent on neural networks and where backpropagation is applied to a loss function defined by the structure of the neural network architecture as opposed to a training dataset. In particular, we reduce the popular combinatorial optimization problem of finding a maximum independent set to a neural network and employ a dataless training scheme to refine the parameters of the network such that those parameters yield the structure of interest. Additionally, we propose a universal graph reduction procedure to handle large-scale graphs. The reduction exploits community detection for graph partitioning and is applicable to any graph type and/or density. Experimental results on both real and synthetic graphs demonstrate that our proposed method performs on par or outperforms state-of-the-art learning-based methods in terms of the size of the found set without requiring any training data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Thermal Hysteresis and Ordering Behavior of Magnetic Skyrmion Lattices

The physics of phase transitions in two-dimensional (2D) systems underpins research in diverse fields including statistical mechanics, nanomagnetism, and soft condensed matter. However, many aspects of 2D phase transitions are still not well understood, including the effects of interparticle potential, polydispersity, and particle shape. Magnetic skyrmions are chiral spin-structure quasi-particles that form two-dimensional lattices. Here, in this study, we show, by real-space imaging using in situ cryo-Lorentz transmission electron microscopy coupled with machine learning image analysis, the ordering behavior of Néel skyrmion lattices in van der Waals Fe 3 GeTe 2 . We demonstrate a distinct change in the skyrmion size distribution during field-cooling, which leads to a loss of lattice order and an evolution of the skyrmion liquid phase. Remarkably, the lattice order is restored during field heating and demonstrates a thermal hysteresis. This behavior is explained by the skyrmion energy landscape and demonstrates the potential to control the lattice order in 2D phase transitions.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2022

A multi-scale time-series dataset with benchmark for machine learning in decarbonized energy grids

The electric grid is a key enabling infrastructure for the ambitious transition towards carbon neutrality as we grapple with climate change. With deepening penetration of renewable resources, the reliable operation of the electric grid becomes increasingly challenging. In this paper, we present PSML, a first-of-its-kind open-access multi-scale time-series dataset, to aid in the development of data-driven machine learning (ML)-based approaches towards reliable operation of future electric grids. The dataset is synthesized from a joint transmission and distribution electric grid to capture the increasingly important interactions and uncertainties of the grid dynamics, containing power, voltage and current measurements over multiple spatio-temporal scales. Using PSML, we provide state-of-the-art ML benchmarks on three challenging use cases of critical importance to achieve: (i) early detection, accurate classification and localization of dynamic disturbances; (ii) robust hierarchical forecasting of load and renewable energy; and (iii) realistic synthetic generation of physical-law-constrained measurements. We envision that this dataset will provide use-inspired ML research in safety-critical systems, while simultaneously enabling ML researchers to contribute towards decarbonization of energy sectors.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

A high-dimensional neural network potential for molecular dynamics simulations of condensed phase nickel and phase transitions

A high-dimensional neural network interatomic potential was developed and used in molecular dynamics simulations of condensed phase Ni and Ni systems with liquid–solid phase coexistence. The reference data set was generated by sampling the potential energy surface over a broad temperature-pressure domain using ab initio MD simulations to train a unified potential. Excellent agreement was achieved between bulk face-centered cubic nickel thermal expansion simulations and relevant experimental data. The same potential also yields accurate structures and diffusivities in the liquid state. The phase transition between liquid and solid phases was simulated using the two-phase interface method. The predicted melting point temperature is within a few kelvins of the literature value. Here, the general methodology could be applied to describe crystals with much more complex phase behaviors.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2022

AutoEnRichness: A hybrid empirical and analytical approach for estimating the richness of galaxy clusters

ABSTRACT We introduce AutoEnRichness, a hybrid approach that combines empirical and analytical strategies to determine the richness of galaxy clusters (in the redshift range of 0.1 ≤ z ≤ 0.35) using photometry data from the Sloan Digital Sky Survey Data Release 16, where cluster richness can be used as a proxy for cluster mass. In order to reliably estimate cluster richness, it is vital that the background subtraction is as accurate as possible when distinguishing cluster and field galaxies to mitigate severe contamination. AutoEnRichness is comprised of a multistage machine learning algorithm that performs background subtraction of interloping field galaxies along the cluster line of sight and a conventional luminosity distribution fitting approach that estimates cluster richness based only on the number of galaxies within a magnitude range and search area. In this proof-of-concept study, we obtain a balanced accuracy of 83.20 per cent when distinguishing between cluster and field galaxies as well as a median absolute percentage error of 33.50 per cent between our estimated cluster richnesses and known cluster richnesses within r200. In the future, we aim for AutoEnRichness to be applied on upcoming large-scale optical surveys, such as the Legacy Survey of Space and Time and Euclid, to estimate the richness of a large sample of galaxy groups and clusters from across the halo mass function. This would advance our overall understanding of galaxy evolution within overdense environments as well as enable cosmological parameters to be further constrained.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Energy transfer in random-matrix ensembles of Floquet Hamiltonians

Here, we explore the statistical properties of energy transfer in ensembles of doubly driven random-matrix Floquet Hamiltonians based on universal symmetry arguments. The energy-pumping efficiency distribution P⁡($\overline{E}$) is associated with the Hamiltonian parameter ensemble and the eigenvalue statistics of the Floquet operator. For specific Hamiltonian ensembles, P⁡($\overline{E}$) undergoes a transition which cannot be associated with a symmetry breaking of the instantaneous Hamiltonian. The Floquet eigenvalue spacing distribution indicates the considered ensembles constitute generic nonintegrable Hamiltonian families. As a step towards Hamiltonian engineering, we develop a machine-learning classifier to understand the relative parameter importance in resulting high-conversion efficiency. We propose random Floquet Hamiltonians as a general framework to investigate frequency conversion effects in a class of generic dynamical processes beyond adiabatic pumps.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗