Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Towards a Robust Adaptive Digital Twin for Fusion Applications

The development of a digital twin system for fusion applications is essential for enhancing the prediction, analysis, and optimization of complex plasma processes. Machine learning (ML), particularly deep learning has demonstrated strong capabilities in modeling such highly nonlinear and intricate systems. However, two critical challenges limit the deployment of deep learning-based digital twins: Uncertainty Quantification (UQ) and data drift. UQ is vital for ensuring trustworthy predictions, especially in decision-support scenarios. Additionally, data-driven models are often sensitive to changes in the underlying data distribution, such as shot-to-shot variations in fusion experiments, which can lead to performance degradation over time. To address these challenges, we are developing an uncertainty-aware, adaptive digital twin framework. Our approach incorporates deep learning models enhanced with Gaussian Process approximations for predictive uncertainty estimation, coupled with an online learning mechanism that enables continuous model adaptation to new experimental data. This adaptive capability allows the data driven models to respond effectively to evolving plasma behaviors and equipment conditions. Specifically, to mitigate the effects of shot-to-shot drift, our system updates itself incrementally as new data becomes available, improving both robustness and fidelity. Our vision is to evolve this data driven model into a self-sustaining digital twin system that leverages UQ based feedback to continuously refine itself and potentially support real-time decision making. This presentation will cover a brief background on uncertainty quantification for ML, our ongoing effort on development of UQ capabilities for ML, our data science pipeline from data collection to model development and analysis and online learning framework for modeling coil deflection at DIII-D. I will also briefly touch upon opportunities and challenges in development of digital twin framework.

Sammuli, Brian [General Atomics]↗
DOE OSTI2026

Data Release 1 of the Dark Energy Spectroscopic Instrument

In 2021 May the Dark Energy Spectroscopic Instrument (DESI) collaboration began a 5 yr spectroscopic redshift survey to produce a detailed map of the evolving three-dimensional structure of the Universe between z = 0 and z ≈ 4. DESI’s principal scientific objectives are to place precise constraints on the equation of state of dark energy, the gravitationally driven growth of large-scale structure, and the sum of the neutrino masses, and to explore the observational signatures of primordial inflation. We present DESI DR1, which consists of all data acquired during the first 13 months of the DESI main survey, as well as a uniform reprocessing of the DESI Survey Validation data, which were previously made public in the DESI Early Data Release. The DR1 main survey includes high-confidence redshifts for 18.7M objects, of which 13.1M are spectroscopically classified as galaxies, 1.6M as quasars, and 4M as stars, making DR1 the largest sample of extragalactic redshifts ever assembled. We summarize the DR1 observations, the spectroscopic data-reduction pipeline and data products, large-scale structure catalogs, value-added catalogs, and describe how to access and interact with the data. In addition to fulfilling its core cosmological objectives with unprecedented precision, we expect DR1 to enable a wide range of transformational astrophysical studies and discoveries.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

sdt (Solar Data Tools) [SWR-25-130]

Solar Data Tools (sdt) is an open-source Python library for analyzing PV power (and irradiance) time-series data. It was developed to enable analysis of unlabeled PV data, i.e. with no model, no meteorological data, and no performance index required, by taking a statistical signal processing approach in the algorithms used in the package’s main data processing pipeline. Solar Data Tools empowers PV system fleet owners or operators to analyze system performance a hundred times faster even when they only have access to the most basic data stream—power output of the system.

Meyers-Im, Bennet [National Laboratory of the Rock↗
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 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 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 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 OSTI2025

Scalable Hybrid Learning Techniques for Scientific Data Compression

Data compression is becoming critical for storing scientific data because many scientific applications need to store large amounts of data and post process this data for scientific discovery. Unlike image and video compression algorithms that limit errors to primary data (PD), scientists require compression techniques that accurately preserve derived quantities of interest (QoIs). Here, this article presents a physics-informed compression technique implemented as an end-to-end, scalable, GPU-based pipeline for data compression that addresses this requirement. Our hybrid compression technique combines machine learning techniques and standard compression methods. Specifically, we combine an autoencoder, an error-bounded lossy compressor to provide guarantees on raw data error, and a constraint satisfaction post-processing step to preserve the QoIs within a minimal error (generally less than floating point error). The effectiveness of the data compression pipeline is demonstrated by compressing nuclear fusion simulation data generated by a large-scale fusion code, XGC, which produces hundreds of terabytes of data in a single day. Our approach works within the ADIOS framework and results in compression by a factor of more than 150 while requiring only a few percent of the computational resources necessary for generating the data, making the overall approach highly effective for practical scenarios.

ITER↗
DOE OSTI2024

Modeling performance of data collection systems for high-energy physics

Exponential increases in scientific experimental data are outpacing silicon technology progress, necessitating heterogeneous computing systems—particularly those utilizing machine learning (ML)—to meet future scientific computing demands. The growing importance and complexity of heterogeneous computing systems require systematic modeling to understand and predict the effective roles for ML. We present a model that addresses this need by framing the key aspects of data collection pipelines and constraints and combining them with the important vectors of technology that shape alternatives, computing metrics that allow complex alternatives to be compared. For instance, a data collection pipeline may be characterized by parameters such as sensor sampling rates and the overall relevancy of retrieved samples. Alternatives to this pipeline are enabled by development vectors including ML, parallelization, advancing CMOS, and neuromorphic computing. By calculating metrics for each alternative such as overall F1 score, power, hardware cost, and energy expended per relevant sample, our model allows alternative data collection systems to be rigorously compared. We apply this model to the Compact Muon Solenoid experiment and its planned high luminosity-large hadron collider upgrade, evaluating novel technologies for the data acquisition system (DAQ), including ML-based filtering and parallelized software. The results demonstrate that improvements to early DAQ stages significantly reduce resources required later, with a power reduction of 60% and increased relevant data retrieval per unit power (from 0.065 to 0.31 samples/kJ). However, we predict that further advances will be required in order to meet overall power and cost constraints for the DAQ.

Olin-Ammentorp, Wilkie (ORCID:0000000224729862)↗
DOE OSTI2025

HydroForecast Long-term: Improving hydropower’s resilience to climate change through accurate climate-scale

With hydrologic patterns and water availability across the globe shifting due to climate change, advancements in hydrologic prediction systems can help significantly reduce the uncertainties that utilities and water supply entities have in their decision making. Understanding and estimating hydrology at the climate scale is critical for managing water resources under changing climate scenarios. This project focuses on integrating state-of-the-art neural network modeling with downscaled climate projections to deliver the reliable water supply projections decades into the future to meet an urgent need from hydropower operators and water utilities. In this Phase 1 DOE SBIR proposal, we developed and validated a theory-guided neural network model, HydroForecast Long-term, for climate-scale hydrology and implemented the model within existing HydroForecast infrastructure. HydroForecast Long-term combines the most accurate streamflow modeling system with a flexible and scalable data architecture to generate water supply projections out to the year 2100. This report illustrates that we have achieved our four objectives: 1) create a prototype of HydroForecast Long-term, building the neural network prediction model, 2) build an automated data input pipeline that processes large amounts of data from the latest global temperature and precipitation climate models; 3) benchmark the accuracy of the hydrologic model over the recent two decades over a large set of diverse basins, and 4) create a set of output visuals and summary metrics informed by customer feedback that connect the data to critical decision points. This work empowers water users to make data-informed decisions supporting a resilient, renewable-powered grid and water system. The results advance the Department of Energy’s mission by addressing critical gaps in water supply planning under climate change.

13 HYDRO ENERGY↗
DOE OSTI2026

Data for An End-to-End Pipeline for Succinic Acid Production at an Industrially Relevant Scale Using Issatchenkia orientalis

Microbial production of succinic acid (SA) at an industrially relevant scale has been hindered by high downstream processing costs arising from neutral pH fermentation for over three decades. Here, we metabolically engineer the acid-tolerant yeast Issatchenkia orientalis for SA production, attaining the highest titers in sugar-based media at low pH (pH 3) in fed-batch fermentations, i.e. 109.5 g/L in minimal medium and 104.6 g/L in sugarcane juice medium. We further perform batch fermentation using sugarcane juice medium in a pilot-scale fermenter (300×) and achieve 63.1 g/L of SA, which can be directly crystallized with a yield of 64.0%. Finally, we simulate an end-to-end low-pH SA production pipeline, and techno-economic analysis and life cycle assessment indicate our process is financially viable and can reduce greenhouse gas emissions by 34–90% relative to fossil-based production processes. We expect I. orientalis can serve as a general industrial platform for production of organic acids.

Metabolomics↗
DOE OSTI2026

Curation and Dissemination of Complex Multi-Modal Datasets for Radiation Detection, Localization, and Tracking

The PANDAWN sensor network in Chicago, IL, is a state-of-the-art testbed for networked, multi-modal sensing. It integrates AI/data science methods into its operation, from data acquisition to automated data labeling and curation workflows. The curation and dissemination of diverse multi-modal datasets will enable the development of new radiological/nuclear (R/N) detection, localization, and tracking algorithms and methods relevant across the nonproliferation mission space. This article first introduces the PANDAWN sensor network and the features that make it stand out from previous multi-modal data acquisition efforts. We then review the various data streams acquired on the PANDAWN nodes and present the implementation of an automated data curation pipeline that includes the labeling of radiation and contextual data streams. Here, we finally provide a short overview of different studies that leveraged the curated datasets.

Data curation↗