Search NASA⌕ Search

SEARCH · Search NASA

Results for “Data Pipeline”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

HARMONY: Large-Scale Architecture Search for Efficient Hybrid Language Models

As large language models scale to trillions of parameters, their computational and memory requirements present critical challenges for efficient training and deployment. While Mixture of Experts (MoE) architectures enable efficient scaling through sparse parameter activation, and state-space models like Mamba offer linear-time complexity, principled methods for combining these paradigms remain undeveloped. We introduce HARMONY (Hybrid Architecture Research for Mamba, Optimized with Neural efficiencY), a multi-objective evolutionary neural architecture search framework for discovering efficient hybrid language models that integrate Transformer attention mechanisms, Mixture-of-Experts routing, and Mamba state-space components. Through large-scale distributed search using 16,384 MI250X GPUs on the Frontier supercomputer, HARMONY explores a comprehensive design space encompassing six attention variants (MHA, MQA, GQA, MLA, SWA, and Mamba-2), variable MoE configurations with both routed and shared experts, and extensive Mamba hyperparameters. Our framework discovers heterogeneous architectures that balance training performance with computational efficiency through multi-objective optimization incorporating latency penalties and fitness-based selection. Analysis of discovered architectures reveals that optimal hybrid designs favor heterogeneous component mixing rather than homogeneous patterns, with Mamba-2 and Multi-Head Latent Attention (MLA) emerging as preferred mechanisms. Discovered architectures demonstrate superior training efficiency: our best configuration achieves a final perplexity of 1.0874 with 2.38B parameters while processing 4,320 tokens/second, outperforming significantly larger manually designed models. Full-scale evaluation shows HARMONY's top architectures achieve better loss trajectories than equivalently-sized models using state-of-the-art configurations including Mixtral, Jamba, and Samba. Additionally, we demonstrate 91% weak scaling efficiency when training discovered 36B-parameter models across 1,024 GPUs. HARMONY is released as an open framework with comprehensive tools for building and training hybrid models using expert-data-pipeline parallelism, democratizing access to automated architecture design for next-generation language models.

Herron, Emily [ORNL] (ORCID:0000000273008172)↗
DOE OSTI2025

Summary of Carbon Dioxide Pipeline Systems and Incident Data in North America

Pipelines are historically seen as the primary transportation mode for carbon dioxide (CO 2 ) streams in the context of carbon capture and storage (CCS) and oil and gas industries. Pipeline transmission of CO 2 over longer distances is regarded as most efficient and economical when the CO 2 is in the dense phase, i.e., in liquid or supercritical regime, due to transporting CO 2 in dense phase that allows for a smaller-diameter pipeline to move a given flow, which optimizes project cost.

42 ENGINEERING↗
DOE OSTI2024

Hydropower Capacity Factor Trends & Analytics for the United States

This data repository contains all code, input data, and data generated for Turner et al. (2024)—“Hydropower capacity factors trending down in the United States”. File descriptions: – hydro-cf-trends-inputs.zip: Full set of input data used in this study, organized for direct entry into “/data” directory of hydro-cf-trends data processing pipeline. – hydro-cf-trends.zip: Full data processing pipeline, coded using the R {targets} framework. This is a snapshot release (v1.0) of the code repository stored at https://code.ornl.gov/turnersw/hydro-cf-trends/. – hydro-cf-trends-results.zip: Provides all dam level results required to reproduce results and graphics in Turner et al. (2024). Dams are identified by the “complxID” (root of the hydropower plant ID in the Existing Hydropower Assets Database, inherited from HILARRI). Results include: • dam_CF_trends.csv: Table of long-term trends in annualized capacity factors for 610 dams and modeled annualized capacity factors for 362 modeled dams (naturalized and assimilated flows). • dam_annualized_CF_gen.csv: Annualized time series of the following variables for each of 610 hydropower dams with nameplate > 5MW – Reported nameplate capacity (MW) – Implied maximum annual generation (MWh) – Reported net generation (MWh) – Computed annual capacity factor – Modeled annual capacity factor (362 modeled plants only)

13 HYDRO ENERGY↗
DOE OSTI2022

Reviews and syntheses: The promise of big diverse soil data, moving current practices towards future potential

Abstract. In the age of big data, soil data are more available and richer than ever, but – outside of a few large soil survey resources – they remain largely unusable for informing soil management and understanding Earth system processes beyond the original study. Data science has promised a fully reusable research pipeline where data from past studies are used to contextualize new findings and reanalyzed for new insight. Yet synthesis projects encounter challenges at all steps of the data reuse pipeline, including unavailable data, labor-intensive transcription of datasets, incomplete metadata, and a lack of communication between collaborators. Here, using insights from a diversity of soil, data, and climate scientists, we summarize current practices in soil data synthesis across all stages of database creation: availability, input, harmonization, curation, and publication. We then suggest new soil-focused semantic tools to improve existing data pipelines, such as ontologies, vocabulary lists, and community practices. Our goal is to provide the soil data community with an overview of current practices in soil data and where we need to go to fully leverage big data to solve soil problems in the next century.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

A path to intelligent watersheds: coordinating the data to decision pipeline

Operations of multi-reservoir systems are challenged in-part by the interplay of complex physical processes functioning within the watershed. The employment of intelligent systems can be of aid by linking environmental sensing, information technology, data analytics, simulation and decision support to achieve a data-to-decision flow of information. A further challenge is that watershed resources are managed for multiple purposes requiring some level of coordination among numerous resource managers, asset operators and users. System intelligence in this context relies on shared community platforms (data portals, community models), and coordinated communication between decision makers. Opportunities to enrich watershed intelligence has been the subject of a roadmapping exercise for the Department of Energy’s Water Power Technologies Office which has relied on broad stakeholder engagement. Initial phases of engagement involved personal interviews and a series of virtual group meetings, which focused on identifying opportunities to improve the intelligence of the physical infrastructure within our watersheds—examples of feedback include improved sensing of snowpack and runoff, data standards for facilitated data sharing, and better forecasting tools. The latter phase of engagement involved the conduct of a case study in the Upper Colorado River basin where key stakeholders were interviewed to map how their decisions are informed by intelligence from other basin stakeholders. Our presentation will highlight the interdisciplinary flow of information in complex watershed systems and identify physical and institutional opportunities toward the strategic operation of water infrastructure.

Colorado River↗
DOE OSTI2020

Distributed fiber sensor and machine learning data analytics for pipeline protection against extrinsic intrusions and intrinsic corrosions

This paper presents an integrated technical framework to protect pipelines against both malicious intrusions and piping degradation using a distributed fiber sensing technology and artificial intelligence. A distributed acoustic sensing (DAS) system based on phase-sensitive optical time-domain reflectometry (φ-OTDR) was used to detect acoustic wave propagation and scattering along pipeline structures consisting of straight piping and sharp bend elbow. Signal to noise ratio of the DAS system was enhanced by femtosecond induced artificial Rayleigh scattering centers. Data harnessed by the DAS system were analyzed by neural network-based machine learning algorithms. The system identified with over 85% accuracy in various external impact events, and over 94% accuracy for defect identification through supervised learning and 71% accuracy through unsupervised learning.

Peng, Zhaoqiang↗
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 OSTI2024

Artificial Intelligence Transforming Post-Translational Modification Research

Post-Translational Modifications (PTMs) are covalent changes to amino acids that occur after protein synthesis, including covalent modifications on side chains and peptide backbones. Many PTMs profoundly impact cellular and molecular functions and structures, and their significance extends to evolutionary studies as well. In light of these implications, we have explored how artificial intelligence (AI) can be utilized in researching PTMs. Initially, rationales for adopting AI and its advantages in understanding the functions of PTMs are discussed. Then, various deep learning architectures and programs, including recent applications of language models, for predicting PTM sites on proteins and the regulatory functions of these PTMs are compared. Finally, our high-throughput PTM-data-generation pipeline, which formats data suitably for AI training and predictions is described. We hope this review illuminates areas where future AI models on PTMs can be improved, thereby contributing to the field of PTM bioengineering.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

A Hydro-particle-mesh Code for Efficient and Rapid Simulations of the Intracluster Medium

We introduce the cosmological HYPER code based on an innovative hydro-particle-mesh (HPM) algorithm for efficient and rapid simulations of gas and dark matter. For the HPM algorithm, we update the approach of Gnedin & Hui to expand the scope of its application from the lower-density intergalactic medium (IGM) to the higher-density intracluster medium (ICM). While the original algorithm tracks only one effective particle species, the updated version separately tracks the gas and dark matter particles, as they do not exactly trace each other on small scales. For the approximate hydrodynamics solver, the pressure term in the gas equations of motion is calculated using robust physical models. In particular, we use a dark matter halo model, ICM pressure profile, and IGM temperature–density relation, all of which can be systematically varied for parameter-space studies. We show that the HYPER simulation results are in good agreement with the halo model expectations for the density, temperature, and pressure radial profiles. Simulated galaxy cluster scaling relations for Sunyaev–Zel’dovich (SZ) and X-ray observables are also in good agreement with mean predictions, with scatter comparable to that found in hydrodynamic simulations. HYPER also produces lightcone catalogs of dark matter halos and full-sky tomographic maps of the lensing convergence, SZ effect, and X-ray emission. These simulation products are useful for testing data analysis pipelines, generating training data for machine learning, understanding selection and systematic effects, and for interpreting astrophysical and cosmological constraints.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

archi : pipeline for light curve extraction of CHEOPS background stars

ABSTRACT High precision time-series photometry from space is being used for a number of scientific cases. In this context, the recently launched CHaracterizing ExOPlanet Satellite (CHEOPS) (ESA) mission promises to bring 20 ppm precision over an exposure time of 6 h, when targeting nearby bright stars, having in mind the detailed characterization of exoplanetary systems through transit measurements. However, the official CHEOPS (ESA) mission pipeline only provides photometry for the main target (the central star in the field). In order to explore the potential of CHEOPS photometry for all stars in the field, in this paper, we present archi, an additional open-source pipeline module1 to analyse the background stars present in the image. As archi uses the official data reduction pipeline data as input, it is not meant to be used as an independent tool to process raw CHEOPS data but, instead, to be used as an add-on to the official pipeline. We test archi using CHEOPS simulated images, and show that photometry of background stars in CHEOPS images is only slightly degraded (by a factor of 2–3) with respect to the main target. This opens a potential for the use of CHEOPS to produce photometric time-series of several close-by targets at once, as well as to use different stars in the image to calibrate systematic errors. We also show one clear scientific application where the study of the companion light curve can be important for the understanding of the contamination on the main target.

Silva, André M.↗
DOE OSTI2024

Evolving Multi-hazard Machine Learning Modeling for Advanced Risk-Informed Infrastructure Resilience Assessment

The socioeconomic impacts of pipeline incidents have escalated over the past three decades, revealing the limitation of traditional risk modeling methods when applied to extensive pipeline networks. This research aims to develop machine learning (ML) models that effectively identify, rank, and predict the diverse hazards and socioeconomic consequences associated with pipeline incidents. Utilizing historical data on pipeline incidents alongside weather and oceanographic data from the 1980s onward, the Houston metropolitan area serves as a testbed for the proposed methodologies. The research segments the combined datasets into three consecutive periods, demonstrating the efficacy of the updated model in predicting future events, particularly concerning precipitation rate data. Despite the challenges posed by a relatively limited dataset, local-level ML modeling offers valuable insights into the spatial and temporal dynamics of multiple hazards that contribute to pipeline incidents. These findings hold significant implications for future research, particularly in understanding and mitigating risks in various locations across the Gulf Coast and other coastal regions.

42 ENGINEERING↗
DOE OSTI2024

RectifHyd Version 2.0: Historical and counterfactual-climatological hydropower monthly generation totals for CONUS plants, 1980 – 2019

This dataset will contain the following files: - RectifHydV2.zip – the RectifHydV2 dataset, split into two files: o RectifHydV2_Actual_MWh.csv: Estimated actual monthly net generation from 590 Hydropower Plants (>10MW nameplate) in CONUS, 1980 – 2019 o RectifHydV2_Counterfactual_MWh.csv: Counterfactual (climate-only) monthly net generation from 590 Hydropower Plants (>10MW nameplate) in CONUS, 1980 – 2019 - RectifHydV2_code.zip: Full data processing pipeline, coded using R {targets} framework. This is a snapshot release (v1.0) of the code repository stored at https://code.ornl.gov/turnersw/rectifhydv2 - RectifHydV2_inputs.zip: Complete set of input data used to create RectifHydV2, organized for direct entry into “/data/” directory of the RectifHydV2 reproducible data pipeline - RectifHydV2_misc.zip: - RectifHydV2_dailyRelease.csv

13 HYDRO ENERGY↗
DOE OSTI2023

In-depth analysis on parallel processing patterns for high-performance Dataframes

The Data Science domain has expanded monumentally in both research and industry communities during the past decade, predominantly owing to the Big Data revolution. Artificial Intelligence (AI) and Machine Learning (ML) are bringing more complexities to data engineering applications, which are now integrated into data processing pipelines to process terabytes of data. Typically, a significant amount of time is spent on data preprocessing in these pipelines, and hence improving its efficiency directly impacts the overall pipeline performance. The community has recently embraced the concept of Dataframes as the de-facto data structure for data representation and manipulation. However, the most widely used serial Dataframes today (R, pandas) experience performance limitations while working on even moderately large data sets. We believe that there is plenty of room for improvement by taking a look at this problem from a high-performance computing point of view. In a prior publication, we presented a set of parallel processing patterns for distributed dataframe operators and the reference runtime implementation, Cylon. In this paper, we are expanding on the initial concept by introducing a cost model for evaluating the said patterns. Furthermore, we evaluate the performance of Cylon on the ORNL Summit supercomputer.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Data-driven selection and spectral classification of white dwarf stars

The next generation of spectroscopic surveys is expected to provide spectra for hundreds of thousands of white dwarf (WD) candidates in the upcoming years. Currently, spectroscopic classification of white dwarfs is mostly done by visual inspection, requiring substantial amounts of expert attention. We propose a data-driven pipeline for fast, automatic selection, and spectroscopic classification of WD candidates, trained using spectroscopically confirmed objects with available Gaia astrometry, photometry, and Sloan Digital Sky Survey (SDSS) spectra with signal-to-noise ratios ≥9. The pipeline selects WD candidates with improved accuracy and completeness over existing algorithms, classifies their primary spectroscopic type with ≥ 90 % accuracy, and spectroscopically detects main sequence companions with similar performance. We apply our pipeline to the Gaia Data Release 3 cross-matched with the SDSS Data Release 17 (DR17), identifying 424 096 high-confidence WD candidates and providing the first catalogue of automated and quantifiable classification for 36 523 WD spectra. Both the catalogue and pipeline are made available online. Such a tool will prove particularly useful for the undergoing SDSS-V survey, allowing for rapid classification of thousands of spectra at every data release.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Data Curation for Machine Learning Applied to Geothermal Power Plant Operational Data for GOOML: Geothermal Operational Optimization with Machine Learning: Preprint

Geothermal Operational Optimization with Machine Learning (GOOML) is a transferable and extensible component-based geothermal asset modeling framework that considers complex steamfield relationships and identifies optimization prospects using a data-driven approach to physics-guided, data-centric machine learning. This framework has been used to develop digital twins that provide steamfield operators with operational environments to analyze and understand historical and forecasted power production, explore new steamfield configuration possibilities, and seek optimal asset management in real world applications. To create, test, and apply the GOOML framework, diverse time-series datasets spanning multiple years were sourced from various geothermal power plant components within several complex real-world geothermal operations. These operations are based in the United States and New Zealand and include a variety of technologies, end-uses and configurations, collectively covering nearly all relevant operating conditions for modern geothermal fields. Datasets were acquired from multiple sources to ensure that machine learning experiments generalized properly to various operating conditions. It was found that the data varied in quality, format, and completeness. To ensure consistency between the various datasets, a standardized data curation process was developed to reliably streamline data preparation. This paper will discuss best practices as learned from the GOOML data curation process which takes the following steps: 1) acquisition of large quantities of data from power plant operators, 2) digestion of data to gain an initial understanding of what is included, 3) data transformation, which includes converting the data into a standardized machine-readable format so that they can be visualized, quality checked, and cleaned, 4) quality assurance and quality control, involving identification of significant data gaps and apparent anomalies through mapping of data features to real world componentry via the GOOML historical model, followed by discussion with modelers and power plant operators to identify additional data needs and to resolve issues, 5) use in machine learning algorithms, and 6) repetition of steps one through five until all data needs are met and data are deemed suitable for producing trustworthy modeling results which may be disseminated, ideally along with the curated dataset. This iterative process is focused on improving the quality of the data rather than tuning machine learning model parameters and supports a shift towards data-centric AI as a means to improving real-world applicability of geothermal machine learning projects.

access↗