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 1,099 records · Page 61
All sourcesNASA NTRSDOE OSTI
NASA NTRS2019

Cognitive Communications for NASA Space Systems

The growing complexity of spacecraft constellations, communication relay offerings, and mission architectures drives the need for the development of autonomous communication systems. NASA has traditionally launched single spacecraft missions that are served by the Space Communication and Navigation (SCaN) program. Operations on SCaN networks are typically scheduled weeks in advance, and often each asset serves a single user spacecraft at a time. Recent movement towards swarm missions could make the current approach unsustainable. Additionally, the integration of commercial communication service providers will substantially increase the data transfer options available to new missions. NASA science missions have found benefit in launching swarms of spacecraft, allowing coordinated simultaneous observations from different perspectives. Inter-spacecraft communication (mesh networking) is an enabler for this architecture, as are CubeSats that allow cost-effective provisioning of distributed mission assets. As more complex swarm missions launch, one challenge is coordinating communication within the swarm and choosing the appropriate mechanism for telemetry, tracking, control, and data services to and from Earth. Cognitive communications research conducted by SCaN aims to mitigate the increasing communication complexity for mission users by increasing the autonomy of links, networks, and service scheduling. By considering automation techniques including recent advances in artificial intelligence and machine learning, cognitive algorithms and related approaches enable increased mission science return, improved resource utilization for service provider networks, and resiliency in unpredictable or unplanned environments. The Cognitive Communications Project at the NASA Glenn Research Center develops applications of data-driven, non-deterministic methods to improve the autonomy of space communication. The project emphasizes development of decentralized space networks with artificial intelligence agents optimizing communication link throughput, data routing, and system-wide asset management. This paper discusses the objectives, approaches, and opportunities of the research to address growing needs of the space communications community.

Chelmins, David↗
DOE OSTI2025

Distributed Acoustic Sensing to Estimate the Permeability

Optical fiber in a borehole can be interrogated with distributed acoustic sensors (DAS) to capture fracture displacements with the potential to map surrounding fracture networks. We designed a laboratory experiment to test the capability of DAS to determine borehole flow characteristics, and we show that for the first time DAS can be used to remotely estimate permeability. Optical fiber was wrapped around a bead filled pipe and the pressure drop and flow velocity were measured to directly calculate permeability. A machine learning model using statistical features from continuous DAS estimated the bulk permeability. Fluid interactions with the permeable material demonstrate insufficient resolution using DAS amplitude-based measurements for estimating pressure drop to infer permeability. Variations in the spectral domain relate DAS measurements to the pressure drop and provide consistent permeability estimates. Resolution with DAS is sufficient to estimate permeability and provides a reliable method to monitor at depth in borehole conditions.

58 GEOSCIENCES↗
DOE OSTI2023

An Analysis of Published DAS Studies for Application to SPE Phase III

Distributed Acoustic Sensing (DAS) is an emerging technology capable of recording the acoustic wavefield at unprecedented spatial resolution. However, this new tool requires significant refinements before it becomes operational for explosion monitoring objectives. Recent studies have shown significant development of array processing with DAS data. In this report we explore three such array processing methods including DAS strain-rate data versus geophone measured ground motion, beamforming for event parameters, and machine learning based denoising. Prior to applying these algorithms to the Source Physics Experiment Phase II and Phase III data, we validate these methods through replication analysis.

47 OTHER INSTRUMENTATION↗
NASA NTRS2006

Robust Coordination for Large Sets of Simple Rovers

The ability to coordinate sets of rovers in an unknown environment is critical to the long-term success of many of NASA;s exploration missions. Such coordination policies must have the ability to adapt in unmodeled or partially modeled domains and must be robust against environmental noise and rover failures. In addition such coordination policies must accommodate a large number of rovers, without excessive and burdensome hand-tuning. In this paper we present a distributed coordination method that addresses these issues in the domain of controlling a set of simple rovers. The application of these methods allows reliable and efficient robotic exploration in dangerous, dynamic, and previously unexplored domains. Most control policies for space missions are directly programmed by engineers or created through the use of planning tools, and are appropriate for single rover missions or missions requiring the coordination of a small number of rovers. Such methods typically require significant amounts of domain knowledge, and are difficult to scale to large numbers of rovers. The method described in this article aims to address cases where a large number of rovers need to coordinate to solve a complex time dependent problem in a noisy environment. In this approach, each rover decomposes a global utility, representing the overall goal of the system, into rover-specific utilities that properly assign credit to the rover s actions. Each rover then has the responsibility to create a control policy that maximizes its own rover-specific utility. We show a method of creating rover-utilities that are "aligned" with the global utility, such that when the rovers maximize their own utility, they also maximize the global utility. In addition we show that our method creates rover-utilities that allow the rovers to create their control policies quickly and reliably. Our distributed learning method allows large sets rovers be used unmodeled domains, while providing robustness against rover failures and changing environments. In experimental simulations we show that our method scales well with large numbers of rovers in addition to being robust against noisy sensor inputs and noisy servo control. The results show that our method is able to scale to large numbers of rovers and achieves up to 400% performance improvement over standard machine learning methods.

Tumer, Kagan↗
DOE OSTI2024

Automating the Analysis of Large Language Models Responses through Zero-Shot Question Answering

Recent advancements in Large Language Models (LLMs) have shown significant potential in various applications, yet their evaluation, particularly in zero-shot question answering scenarios, remains a challenging task. In this study, our objective was to explore precision metrics for Large Language Models (LLM) and design and implement a software pipeline to automatically evaluate LLMs' outputs under zero-shot question answering. Zero-shot question answering involves a model providing answers to questions about topics it hasn't seen during training. It leverages the principles of zero-shot learning by relying on semantic understanding and generalization from related knowledge. The data used was metadata from medical databases on congenital heart disease. We explored eleven LLM metrics and selected three for our evaluation: BLEU, BERTScore, and MoverScore. BLEU calculates a score based on the overlap of n-grams (contiguous sequences of n items, typically words) between the machine-generated translation and the reference translations. Higher BLEU scores indicate better correspondence between the machine-generated and human-generated translations. BERTScore is a metric used to evaluate the quality of machine-generated text by measuring the similarity of token embeddings produced by BERT (Bidirectional Encoder Representations from Transformers) between the generated text and reference text. MoverScore is a metric that quantifies the dissimilarity between the distributions of word embeddings from machine-generated text and reference text, emphasizing semantic similarity over exact token overlap. We also introduced HBKI, a composite metric summarizing these approaches. We tested five models —GPT-3, Llama-2, Gemini 1.5 Pro, Solar 10.7B, and Mixtral-8x7b. Our software pipeline, designed and implemented using Object-Oriented Programming principles, allows users to customize the selection and extraction of features for topics of interest in their own research. Our results show that MoverScore delivered the most precise evaluation of the LLM's outputs, while Mixtral-8x7b achieved the best overall performance in extracting metadata from the databases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A derecho climatology (2004–2021) in the United States based on machine learning identification of bow echoes

Due to their persistent widespread severe winds, derechos pose significant threats to human safety and property, with impacts comparable to many tornadoes and hurricanes. Yet, automated detection of derechos remains challenging due to the absence of spatiotemporally continuous observations and the complex criteria employed to define the phenomenon. This study presents an objective derecho detection approach capable of automatically identifying derechos through both observations and model results. The approach is grounded in a physically based definition of derechos and integrates three algorithms: (1) the Python Flexible Object Tracker (PyFLEXTRKR) algorithm to track mesoscale convective systems (MCSs), (2) a semantic segmentation convolutional neural network to identify bow echoes, and (3) a comprehensive classification algorithm to detect derechos within MCS life cycles and distinguish derecho-producing from non-derecho-producing MCSs. Using this approach, we developed a novel high-resolution (4 km and hourly) observational dataset of derechos and accompanying derecho-producing MCSs over the United States east of the Rocky Mountains from 2004 to 2021. The dataset consists of two subsets based on different gust speed data sources and is analyzed to document the climatology of derechos in the United States. On average, 12–15 derechos are identified per year, aligning with previous estimations (∼6–21 events annually). The spatial distribution and seasonal variation patterns are consistent with prior studies, showing peak occurrences in the Great Plains and the Midwest during the warm season. Additionally, during the study period, derechos account for approximately 3.1 % of measured damaging gusts (≥25.93 m s−1) over the eastern United States. The dataset is publicly available at https://doi.org/10.5281/zenodo.14835362 (Li et al., 2025).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Physics-coupled data-driven design of high-temperature alloys

We present a materials design loop, which streamlines physics-coupled machine learning (ML) surrogate models to discover new alloy chemistries with improved properties. The efficacy is demonstrated by discovering a high-temperature alumina-forming austenitic (AFA) stainless steel with enhanced creep, followed by experimental validation. The ML models have been trained using a well-curated, highly consistent experimental dataset augmented with synthetic microstructural features from a computational thermodynamic approach. We have populated a large number of hypothetical AFA alloys to explore the high-dimensional composition space and have predicted their creep properties by providing the same synthetic input features obtained from the trained ML models. Uncertainties from the ML training were taken as thresholds for truncating predicted results to identify alloys with improved or deteriorated creep. Individual elemental compositions have been determined via probability density distribution analysis from the group of alloys at the top and bottom of the predicted creep values for further virtual and experimental validations. In conclusion, we anticipate that this workflow can be applied to screen desired conditions, such as chemistry and processing parameters, in high-dimensional space through physics-guided data analytics.

Alloy design↗
NASA NTRS2022

Simultaneous Retrieval of Selected Optical Water Quality Indicators From Landsat-8, Sentinel-2, and Sentinel-3

Constructing multi-source satellite-derived water quality (WQ) products in inland and nearshore coastal waters from the past, present, and future missions is a long-standing challenge. Despite inherent differences in sensors’ spectral capability, spatial sampling, and radiometric performance, research efforts focused on formulating, implementing, and validating universal WQ algorithms continue to evolve. This research extends a recently developed machine-learning (ML) model, i.e., Mixture Density Networks (MDNs) (Pahlevan et al., 2020; Smith et al., 2021), to the inverse problem of simultaneously retrieving WQ indicators, including chlorophyll-a (Chla), Total Suspended Solids (TSS), and the absorption by Colored Dissolved Organic Matter at 440 nm (a cdom (440)), across a wide array of aquatic ecosystems. We use a database of in situ measurements to train and optimize MDN models developed for the relevant spectral measurements (400–800 nm) of the Operational Land Imager (OLI), MultiSpectral Instrument (MSI), and Ocean and Land Color Instrument (OLCI) aboard the Landsat-8, Sentinel-2, and Sentinel-3 missions, respectively. Our two performance assessment approaches, namely hold-out and leave-one-out, suggest significant, albeit varying degrees of improvements with respect to second-best algorithms, depending on the sensor and WQ indicator (e.g., 68%, 75%, 117% improvements based on the hold-out method for Chla, TSS, and a cdom (440), respectively from MSI-like spectra). Using these two assessment methods, we provide theoretical upper and lower bounds on model performance when evaluating similar and/or out-of-sample datasets. To evaluate multi-mission product consistency across broad spatial scales, map products are demonstrated for three near-concurrent OLI, MSI, and OLCI acquisitions. Overall, estimated TSS and a cdom (440) from these three missions are consistent within the uncertainty of the model, but Chla maps from MSI and OLCI achieve greater accuracy than those from OLI. By applying two different atmospheric correction processors to OLI and MSI images, we also conduct matchup analyses to quantify the sensitivity of the MDN model and best-practice algorithms to uncertainties in reflectance products. Our model is less or equally sensitive to these uncertainties compared to other algorithms. Recognizing their uncertainties, MDN models can be applied as a global algorithm to enable harmonized retrievals of Chla, TSS, and a cdom (440) in various aquatic ecosystems from multi-source satellite imagery. Local and/or regional ML models tuned with an apt data distribution (e.g., a subset of our dataset) should nevertheless be expected to outperform our global model.

Machine learning↗
DOE OSTI2022

Predicting solid state material platforms for quantum technologies

Semiconductor materials provide a compelling platform for quantum technologies (QT). However, identifying promising material hosts among the plethora of candidates is a major challenge. Therefore, we have developed a framework for the automated discovery of semiconductor platforms for QT using material informatics and machine learning methods. Different approaches were implemented to label data for training the supervised machine learning (ML) algorithms logistic regression, decision trees, random forests and gradient boosting. We find that an empirical approach relying exclusively on findings from the literature yields a clear separation between predicted suitable and unsuitable candidates. In contrast to expectations from the literature focusing on band gap and ionic character as important properties for QT compatibility, the ML methods highlight features related to symmetry and crystal structure, including bond length, orientation and radial distribution, as influential when predicting a material as suitable for QT.

36 MATERIALS SCIENCE↗
DOE OSTI2024

An Active Learning-Based Streaming Pipeline for Reduced Data Training of Structure Finding Models in Neutron Diffractometry

Structure determination workloads in neutron diffractometry are computationally expensive and routinely require several hours to many days to determine the structure of a material from its neutron diffraction patterns. The potential for machine learning models trained on simulated neutron scattering patterns to significantly speed up these tasks have been reported recently. However, the amount of simulated data needed to train these models grows exponentially with the number of structural parameters to be predicted and poses a significant computational challenge. To overcome this challenge, we introduce a novel batch-mode active learning (AL) policy that uses uncertainty sampling to simulate training data drawn from a probability distribution that prefers labelled examples about which the model is least certain. We confirm its efficacy in training the same models with ∼ 75% less training data while improving the accuracy. We then discuss the design of an efficient stream-based training workflow that uses this AL policy and present a performance study on two heterogeneous platforms to demonstrate that, compared with a conventional training workflow, the streaming workflow delivers ∼ 20% shorter training time without any loss of accuracy.

Wang, Tianle [Brookhaven National Laboratory (BNL)↗
DOE OSTI2022

Deep Electric Field Predictions by Drift-Reduced Braginskii Theory with Plasma-Neutral Interactions Based on Experimental Images of Boundary Turbulence

We present 2-dimensional turbulent electric field calculations via physics-informed deep learning consistent with (i) drift-reduced Braginskii theory under the framework of an axisymmetric fusion plasma with purely toroidal field and (ii) experimental estimates of the fluctuating electron density and temperature on open field lines obtained from analysis of gas puff imaging of a discharge on the Alcator C-Mod tokamak. The inclusion of effects from the locally puffed atomic helium on particle and energy sources within the reduced plasma turbulence model are found to strengthen correlations between the electric field and electron pressure. The neutrals are also directly associated with broadening the distribution of turbulent field amplitudes and increasing ${\bf E \times B}$ shearing rates. As a result, this demonstrates a novel approach in plasma experiments by solving for nonlinear dynamics consistent with partial differential equations and data without encoding explicit boundary nor initial conditions.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Modeling Spatial Distribution of Snow Water Equivalent by Combining Meteorological and Satellite Data with Lidar Maps

Abstract An accurate characterization of the water content of snowpack, or snow water equivalent (SWE), is necessary to quantify water availability and constrain hydrologic and land surface models. Recently, airborne observations (e.g., lidar) have emerged as a promising method to accurately quantify SWE at high resolutions (scales of ∼100 m and finer). However, the frequency of these observations is very low, typically once or twice per season in the Rocky Mountains of Colorado. Here, we present a machine learning framework that is based on random forests to model temporally sparse lidar-derived SWE, enabling estimation of SWE at unmapped time points. We approximated the physical processes governing snow accumulation and melt as well as snow characteristics by obtaining 15 different variables from gridded estimates of precipitation, temperature, surface reflectance, elevation, and canopy. Results showed that, in the Rocky Mountains of Colorado, our framework is capable of modeling SWE with a higher accuracy when compared with estimates generated by the Snow Data Assimilation System (SNODAS). The mean value of the coefficient of determination R 2 using our approach was 0.57, and the root-mean-square error (RMSE) was 13 cm, which was a significant improvement over SNODAS (mean R 2 = 0.13; RMSE = 20 cm). We explored the relative importance of the input variables and observed that, at the spatial resolution of 800 m, meteorological variables are more important drivers of predictive accuracy than surface variables that characterize the properties of snow on the ground. This research provides a framework to expand the applicability of lidar-derived SWE to unmapped time points. Significance Statement Snowpack is the main source of freshwater for close to 2 billion people globally and needs to be estimated accurately. Mountainous snowpack is highly variable and is challenging to quantify. Recently, lidar technology has been employed to observe snow in great detail, but it is costly and can only be used sparingly. To counter that, we use machine learning to estimate snowpack when lidar data are not available. We approximate the processes that govern snowpack by incorporating meteorological and satellite data. We found that variables associated with precipitation and temperature have more predictive power than variables that characterize snowpack properties. Our work helps to improve snowpack estimation, which is critical for sustainable management of water resources.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

DLHub: Simplifying publication, discovery, and use of machine learning models in science

Machine Learning (ML) has become a critical tool enabling new methods of analysis and driving deeper understanding of phenomena across scientific disciplines. There is a growing need for "learning systems" to support various phases in the ML lifecycle. While others have focused on supporting model development, training, and inference, few have focused on the unique challenges inherent in science, such as the need to publish and share models and to serve them on a range of available computing resources. In this paper, we present the Data and Learning Hub for science (DLHub), a learning system designed to support these use cases. Specifically, DLHub enables publication of models, with descriptive metadata, persistent identifiers, and flexible access control. It packages arbitrary models into portable servable containers, and enables low-latency, distributed serving of these models on heterogeneous compute resources. In this work, we show that DLHub supports low-latency model inference comparable to other model serving systems including TensorFlow Serving, SageMaker, and Clipper, and improved performance, by up to 95%, with batching and memoization enabled. We also show that DLHub can scale to concurrently serve models on 500 containers. Finally, we describe five case studies that highlight the use of DLHub for scientific applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Converting sWeights to probabilities with density ratios

The use of machine learning approaches continues to have many benefits in experimental nuclear and particle physics. One common issue is generating training data which is sufficiently realistic to give reliable results. Here we advocate using real experimental data as the source of training data and demonstrate how one might subtract background contributions through the use of probabilistic weights which can be readily applied to training data. The sPlot formalism is a common tool used to isolate distributions from different sources. However, the negative sWeights produced by the sPlot technique can cause training problems and poor predictive power. This article demonstrates how density ratio estimation can be applied to convert sWeights to event probabilities, which we call drWeights. The drWeights can then be applied to produce the distributions of interest and are consistent with direct use of the sWeights. This article will also show how decision trees are particularly well suited to convert sWeights, with the benefit of fast prediction rates and adaptability to aspects of experimental data such as the data sample size and proportions of different event sources. We also show that a density ratio product approach in which the initial drWeights are reweighted by an additional converter gives substantially better results.

Glazier, Derek I. [Univ. of Glasgow, Scotland (Uni↗
DOE OSTI2021

Streamflow simulation in data-scarce basins using Bayesian and physics-informed machine learning models

Hydrologic predictions at rural watersheds are important but also challenging due to data shortage. Long short-term memory (LSTM) networks are a promising machine learning approach and have demonstrated good performance in streamflow predictions. However, due to its data-hungry nature, most LSTM applications focus on well-monitored catchments with abundant and high-quality observations. In this work, we investigate predictive capabilities of LSTM in poorly monitored watersheds with short observation records. To address three main challenges of LSTM applications in data-scarce locations, i.e., overfitting, uncertainty quantification (UQ), and out-of-distribution prediction, we evaluate different regularization techniques to prevent overfitting, apply a Bayesian LSTM for UQ, and introduce a physics-informed hybrid LSTM to enhance out-of-distribution prediction. Through case studies in two diverse sets of catchments with and without snow influence, we demonstrate that 1) when hydrologic variability in the prediction period is similar to the calibration period, LSTM models can reasonably predict daily streamflow with Nash–Sutcliffe efficiency above 0.8, even with only 2 years of calibration data; 2) when the hydrologic variability in the prediction and calibration periods is dramatically different, LSTM alone does not predict well, but the hybrid model can improve the out-of-distribution prediction with acceptable generalization accuracy; 3) L2 norm penalty and dropout can mitigate overfitting, and Bayesian and hybrid LSTM have no overfitting; and 4) Bayesian LSTM provides useful uncertainty information to improve prediction understanding and credibility. In conclusion, these insights have vital implications for streamflow simulation in watersheds where data quality and availability are a critical issue.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Physics vs structure: A systematic benchmark of learning strategies for multi-zone building thermal dynamics

Recent advances in physics-informed and data-driven machine learning promise improved thermal models for advanced building control, yet there is limited quantitative evidence on when added physics structure and architectural complexity are beneficial. Here, this work presents a systematic benchmark of five representative system identification methods for modeling multi-zone building thermal dynamics: linear state-space models, multi-layer perceptrons, neural state-space models, neural ordinary differential equations, and physically-consistent neural networks. The methods are evaluated across multiple data regimes and zone coupling strategies. Using a high-fidelity multi-zone commercial building emulator, we examine short-term and long-term prediction accuracy, computational efficiency, and ease of development. Our results reveal critical trade-offs between prediction performance, model complexity, and physical consistency. We demonstrate that decoupled, nonlinear black-box models consistently outperform coupled physics-constrained architectures in both predictive accuracy and out-of-distribution robustness in majority of the test cases for the building type considered in the study. Our findings quantify the cost of complexity in building thermal modeling and provide concrete, actionable, scenario-based guidelines for selecting model classes for control-oriented applications.

Building thermal modeling↗
DOE OSTI2024

MassiveGNN: Efficient Training via Prefetching for Massively Connected Distributed Graphs

Graph Neural Networks (GNN) are indispensable in learning from graph-structured data, yet their rising computational costs, especially on massively connected graphs, pose significant challenges in terms of execution performance. To tackle this, distributed-memory solutions such as partitioning the graph to concurrently train multiple replicas of GNNs are in practice. However, approaches requiring a partitioned graph usually suffer from communication overhead and load imbalance, even under optimal partitioning and communication strategies due to irregularities in the neighborhood minibatch sampling. This paper proposes practical trade-offs for improving the sampling and communication overheads for representation learn- ing on distributed graphs (using popular GraphSAGE architecture) by developing a parameterized prefetch and eviction scheme on top of the state-of-the-art Amazon DistDGL distributed GNN framework, demonstrating about 15–40% improvement in end-to-end training performance on the NERSC Perlmutter supercomputer for various OGB datasets.

Machine Leanring, high performance comptuing, grap↗
DOE OSTI2022

Enhanced analysis of experimental x-ray spectra through deep learning

X-ray spectroscopic data from high-energy-density laser-produced plasmas has long required thorough, time-consuming analysis to extract meaningful source conditions. There are often confounding factors due to rapidly evolving states and finite spatial gradients (e.g., the existence of multi-temperature, multi-density, multi-ionization states, etc.) that make spectral measurements and analysis difficult. Here, in this paper, we demonstrate how deep learning can be applied to enhance x-ray spectral data analysis in both speed and intricacy. Neural networks (NNs) are trained on ensemble atomic physics simulations so that they can subsequently construct a model capable of extracting plasma parameters directly from experimental spectra. Through deep learning, the models can extract temperature distributions as opposed to single or dual temperature/density fits from standard trial-and-error atomic modeling at a significantly reduced computational cost compared to traditional trial-and-error methods. These NNs are envisioned to be deployed with high repetition rate x-ray spectrometers in order to provide detailed real-time analysis of experimental spectra.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗