SEARCH · Engineering Papers

Results for “combined data integration”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Software Defined Architectures for Portability and Performance

The Software Defined Architectures for Portability and Performance (SODAPOP) project developed a co-design framework to partition and map converged applications on specialized heterogeneous architectures. We started from key domain applications that combine scientific simulation with data analytics and machine learning as drivers to integrate our framework. The framework includes high-level compilers that interfaces with high-level programming frameworks, domain-specific optimization passes, and hardware-oriented optimizations. The framework leverages hardware generators to enable specialization and facilitate exploration of custom system designs.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Multi-Sourced Collaboration for the Production and Refining of Rare Elements and Critical Metals (Final Technical Report)

The project objective was to develop a feasible and cost-effective method for recovering rare earth elements (REEs) and critical materials (CMs) from coal and coal byproducts, resulting in high-purity individually separated REEs and CMs. The targeted REEs included Y, Pr, Nd, Gd, Dy, and Sm, with a purity of over 99.5%, while the CMs included Co, Mn, Ga, Sr, Li, Ni, Zn, and Ge, with a purity of over 90%. The project aimed to design a prototype facility capable of producing 1-3 tonnes/day of high-purity REO mixes. The work was divided into four designated circuits: 1) REE extraction and concentration, 2) REE separation and purification, 3) RE metal production, and 4) CM production. To achieve these goals, the project involved 11 tasks, including technology reviews, research, process flow diagram development, mass balance estimation, and preliminary technical-economic analysis. The project team included researchers from the University of Kentucky, University of Alabama and Virginia Tech as well as process specialists from Argonne National Laboratory. MP Materials provided technical support regarding rare earth markets and processing while Alliance Coal performed resource assessment. The project included a market analysis for Nd/Pr, Tb, Dy, Gd, Y, Co, Mn, Li, Sr, Ga, Ni, Zn, and Ge. These analyses provided insights into the supply and demand trends as well as historic and future projections of market price relative to purity requirements for these elements. Two coal resources were selected for the project: the West Kentucky No. 13 (Baker) Seam and an undisclosed lignite resource in the Illinois coal basin. The estimated quantities of REEs in these resources were calculated based on production samples and drilling data. It was estimated that there is adequate supply for an operation producing one metric ton daily of higher purity mixed rare earth oxides (MREO) for approximately 20 years at a site located in western Kentucky. In Circuit 1, project data was obtained from a pilot heap leach and REE concentration facility. It was concluded that the existing circuit, which generated a MREO concentrate, two types of CM mixed products, and Li- and Sr-containing waters, would be suitable feed for circuits 2-4. Data from the first-of-its-kind coal coarse refuse heap leach pilot pad played a crucial role in estimating reliable elemental concentrations of the pregnant leaching solution (PLS). The average total REE concentration in the PLS was found to be 28.6 ppm. In Circuit 2, several concepts were explored including a novel process referred to as solvent-assisted chromatography (SAC). This concept involved a novel columnar reactor that incorporated multiple mixer/settlers, thereby enabling the operation of counter-flowing aqueous and organic phases. Unfortunately, due to project time constraints, a complete fundamental modeling analysis could not be completed to fully evaluate the technology. Molten salt electrowinning was considered as an alternative for circuit 3 following circuit 2 purification circuit utilizing the novel SAC process. A mass and energy balance of Nd reduction to metal in a fluoride containing molten salt electrolyte was conducted. Comparisons were made with the current state of Asian molten salt electrorefining, and potential improvements in siphoning rare earth metals (REM) from the reactor were presented. A cost estimate was performed for the production of 1 tonne per day, which yielded a total of $2.29 million for the nine electrowinning (EW) cells required. The selected option for circuits 2 and 3 was a plasma distillation process, which initially separates rare earth elements (REEs) from other elements. This is followed by selective electrowinning in various ionic liquids. The selection was made on the basis of thermodynamic modeling and experimental data previously published by a project partner. The combination offers an innovative approach to integrated refining and RE metal production. For Circuit 4, an extensive literature review was conducted for the processing of the CMs. The ultimate decision was to utilize a combined plasma and ionic liquid process as well to produce individual high-purity concentrates of Zn, Ni, Co, Mn, and Mg. A separate flowsheet for Li and Sr was recommended, which would yield carbonates of these elements. Due to the lack of suitable experimental data at this time, a process recommendation could not be provided but several methods have been proposed for consideration. Lastly, a techno-economic analysis (TEA) was conducted to assess the effectiveness of the proposed process for further investigation. The TEA results revealed a capital expense (CapEx) of $737 million and an annual operational expense (OpEx) of $220 million. Due to the selected elements, the hypothetical heap leach pad can produce 1 metric tonne per day of REO equivalent, but a conscious decision was made to only treat targeted REEs, resulting in the production of 0.4 metric tonne of REM. An estimated annual revenue of $90.87 million was projected based on standard market pricing information provided by the funding agency. During the TEA, ten different modules were evaluated for costing purposes. The precipitation circuit was identified as the largest single operational expense, followed by the Mg/Mn process due to the amount of treated metal. In terms of capital expenditures, the heap leach process incurred the highest cost, followed by the Mg/Mn process. The scalability of the plasma process is a crucial consideration since the reactors cannot be scaled beyond the largest demonstrated size due to their reliance on surface area of the slag and vapor phase. The purity estimate for the REEs are generally 98%±2% to produce a metal. The purity level being lower than the project objective was due to the lack of specific experimental data needed to tighten the tolerance of the estimates. Based on literature and previous experience, the CMs are estimated as follows; Ga (95%+, metal), Sr (95%+, carbonate), Li (95%+, carbonate), Ni (98%±2%, metal), Zn (95%+, metal sponge), Ge (95%+, metal), Co (98%±2%, metal), and Mn (98%±2%, metal).

01 COAL, LIGNITE, AND PEAT↗

DOE OSTI2021

SYMBIOSYS: A Methodology for Performance Analysis of Composable HPC Data Services

Microservices are a powerful new way of building, customizing, and deploying distributed services owing to their flexibility and maintainability. Several large-scale distributed platforms have emerged to serve the growing needs of data-centric workloads and services in commercial computing. Concurrently, high-performance computing (HPC) systems and software are rapidly evolving to meet the demands of diversified applications and heterogeneity. The interplay of hardware factors, software configuration parameters, and the flexibility offered with a microservice architecture makes it nontrivial to estimate the optimal service instantiation for a given application workload. Further, this problem is exacerbated when considering that these services operate in a dynamic and heterogeneous HPC environment. An optimally integrated service can be vastly more performant than a haphazardly integrated one. Existing performance tools for HPC either fail to understand the request-response model of communication inherent to microservices or they operate within a narrow scope, limiting the insight that can be gleaned from employing them in isolation. We propose a methodology for integrated performance analysis of HPC microservices frameworks and applications called SYMBIOSYS. We describe its design and implementation within the context of the Mochi framework. This integration is achieved by combining distributed callpath profiling and tracing with a performance data exchange strategy that collects fine-grained, low-level metrics from the RPC communication library and network layers. The result is a portable, low-overhead performance analysis setup that provides a holistic profile of the dependencies among microservices and how they interact with the Mochi RPC software stack. Using HEPnOS, a production-quality Mochi data service, we demonstrate the low-overhead operation of SYMBIOSYS at scale and use it to identify the root causes of poorly performing service configurations.

microservices↗

DOE OSTI2024

Search for the lepton flavor violating τ → 3μ decay in proton-proton collisions at s = 13 TeV

A search for the lepton flavor violating τ → 3 μ decay is performed using proton-proton collision events at a center-of-mass energy of 13 TeV collected by the CMS experiment at the LHC in 2017–2018, corresponding to an integrated luminosity of 97.7 fb − 1 . Tau leptons produced in both heavy-flavor hadron and W boson decays are exploited in the analysis. No evidence for the decay is observed. The results of this search are combined with an earlier null result based on data collected in 2016 to obtain a total integrated luminosity of 131 fb − 1 . The observed (expected) upper limits on the branching fraction B ( τ → 3 μ ) at confidence levels of 90 and 95% are 2.9 × 10 − 8 ( 2.4 × 10 − 8 ) and 3.6 × 10 − 8 ( 3.0 × 10 − 8 ), respectively.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2023

A Vision for Coupling Operation of US Fusion Facilities with HPC Systems and the Implications for Workflows and Data Management

The operation of large US Department of Energy (DOE) research facilities, like the DIII-D National Fusion Facility, results in the collection of complex multi-dimensional scientific datasets, both experimental and model-generated. In the future, it is envisioned that integrated data analysis coupled with large-scale high performance computing (HPC) simulations will be used to improve experimental planning and operation. Practically, massive data sets from these simulations provide the physics basis for generation of both reduced semi-analytic and machine-learning-based models. Storage of both HPC simulation datasets (generated from US DOE leadership computing facilities) and experimental datasets presents significant challenges. In this paper, we present a vision for a DOE-wide data management workflow that integrates US DOE fusion facilities with leadership computing facilities. Data persistence and long-term availability beyond the length of allocated projects is essential, particularly for verification and recalibration of artificial intelligence and machine learning (AI/ML) models. Because these data sets are often generated and shared among hundreds of users across multiple leadership computing facility centers, they would benefit from cross-platform accessibility, persistent identifiers (e.g. DOI, or digital object identifier), and provenance tracking. Here, the ability to handle different data access patterns suggests that a combination of low cost, high latency (e.g. for storing ML training sets) and high cost, low latency systems (e.g. for real-time, integrated machine control feedback) may be needed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2025

Machine Learning to Select Experiments Driven by Fundamental Science and Applications for Targeted Nuclear Data Improvement

This work describes a blueprint for a process that accelerates progress in science by quantitatively answering the following question: What is the optimal combination of fundamental-science and application-driven experiments to maximally reduce pertinent data uncertainties? Answering this question entails solving a high-dimensional and complex optimization problem that is best solved with advanced statistic techniques often classified as machine learning. We apply this process within the framework of nuclear data with the aim to select an experiment combination that will reduce uncertainties in 239 Pu nuclear data for neutron energies between 1 and 600 keV. In this field, fundamental-physics driven data, called differential, look at one nuclear physics observable at a time. They are contrasted to application-driven, integral, data where one or few resulting values inform a broad set of nuclear data across several nuclides and energies. The candidates for integral experiments are criticality measurements that were refined by a genetic algorithm to be maximally sensitive to 239 Pu fission cross sections in the desired energy range. Twenty-three candidate differential experiments were investigated and span multiple nuclear physics observables (e.g., total, capture cross sections) for isotopes appearing in the integral experiments. The optimal combination among these candidate experiments was investigated via generalized least squares fitting, augmented with Gaussian processes to ameliorate statistical irregularities in data, and the D-optimality criterion. The latter evaluates for each pair of candidates the joint reduction in uncertainties of all 12200 nuclear data appearing in the integral experiments compared to the knowledge we have from 168 past experiments, theory, and nuclear data. We chose as differential measurements those that investigate 63 Cu and 239 Pu total cross sections, based on D-optimality rank and feasibility constraints. Two integral (criticality) experiments were selected: An experiment with Al 2 ⁢O 3 and graphite interleaved with Pu and a thick Cu reflector explores 1–30 keV, while we target the 30–600 keV range with an experiment that swaps boron in place of graphite with a different geometry.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2023

Integrated deep learning framework for unstable event identification and disruption prediction of tokamak plasmas

Abstract The ability to identify underlying disruption precursors is key to disruption avoidance. In this paper, we present an integrated deep learning (DL) based model that combines disruption prediction with the identification of several disruption precursors like rotating modes, locked modes, H-to-L back transitions and radiative collapses. The first part of our study demonstrates that the DL-based unstable event identifier trained on 160 manually labeled DIII-D shots can achieve, on average, 84% event identification rate of various frequent unstable events (like H-L back transition, locked mode, radiative collapse, rotating MHD mode, large sawtooth crash), and the trained identifier can be adapted to label unseen discharges, thus expanding the original manually labeled database. Based on these results, the integrated DL-based framework is developed using a combined database of manually labeled and automatically labeled DIII-D data, and it shows state-of-the-art (AUC = 0.940) disruption prediction and event identification abilities on DIII-D. Through cross-machine numerical disruption prediction studies using this new integrated model and leveraging the C-Mod, DIII-D, and EAST disruption warning databases, we demonstrate the improved cross-machine disruption prediction ability and extended warning time of the new model compared with a baseline predictor. In addition, the trained integrated model shows qualitatively good cross-machine event identification ability. Given a labeled dataset, the strategy presented in this paper, i.e. one that combines a disruption predictor with an event identifier module, can be applied to upgrade any neural network based disruption predictor. The results presented here inform possible development strategies of machine learning based disruption avoidance algorithms for future tokamaks and highlight the importance of building comprehensive databases with unstable event information on current machines.

plasma instabilities↗

DOE OSTI2022

Integrating data types to estimate spatial patterns of avian migration across the Western Hemisphere

For many avian species, spatial migration patterns remain largely undescribed, especially across hemispheric extents. Recent advancements in tracking technologies and high-resolution species distribution models (i.e., eBird Status and Trends products) provide new insights into migratory bird movements and offer a promising opportunity for integrating independent data sources to describe avian migration. Here, we present a three-stage modeling framework for estimating spatial patterns of avian migration. First, we integrate tracking and band re-encounter data to quantify migratory connectivity, defined as the relative proportions of individuals migrating between breeding and nonbreeding regions. Next, we use estimated connectivity proportions along with eBird occurrence probabilities to produce probabilistic least-cost path (LCP) indices. In a final step, we use generalized additive mixed models (GAMMs) both to evaluate the ability of LCP indices to accurately predict (i.e., as a covariate) observed locations derived from tracking and band re-encounter data sets versus pseudo-absence locations during migratory periods and to create a fully integrated (i.e., eBird occurrence, LCP, and tracking/band re-encounter data) spatial prediction index for mapping species-specific seasonal migrations. To illustrate this approach, we apply this framework to describe seasonal migrations of 12 bird species across the Western Hemisphere during pre- and postbreeding migratory periods (i.e., spring and fall, respectively). We found that including LCP indices with eBird occurrence in GAMMs generally improved the ability to accurately predict observed migratory locations compared to models with eBird occurrence alone. Using three performance metrics, the eBird + LCP model demonstrated equivalent or superior fit relative to the eBird-only model for 22 of 24 species–season GAMMs. In particular, the integrated index filled in spatial gaps for species with over-water movements and those that migrated over land where there were few eBird sightings and, thus, low predictive ability of eBird occurrence probabilities (e.g., Amazonian rainforest in South America). This methodology of combining individual-based seasonal movement data with temporally dynamic species distribution models provides a comprehensive approach to integrating multiple data types to describe broad-scale spatial patterns of animal movement. Further development and customization of this approach will continue to advance knowledge about the full annual cycle and conservation of migratory birds.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2021

Uranium integral fission product yields for a spectrally-shaped 14.1 MeV neutron source at the National Ignition Facility

This paper describes the experimental results for an energy tuning assembly created to modify the National Ignition Facility deuterium–tritium fusion neutron source into a notional thermonuclear and prompt fission neutron spectrum, which has applications in integral measurements, nuclear data benchmarks, and radiation effects on microelectronics. The Monte Carlo neutron transport utilized MCNP5 to estimate the ETA-modified fluence using the ENDF-B/VIII.0 and IRDFF-II continuous energy nuclear data libraries, and SCALE Sampler was used to estimate the systematic nuclear data covariance using ENDF-B/VII.1 and IRDFF-II in a 252-group structure. The experiment fielded eight activation foils and a highly enriched uranium sample. This provided fifteen reaction channels that were used in a forward-fit comparison to the modeled results and to unfold the neutron spectrum using STAYSL. Gamma-ray spectrometry was performed on the activation and highly enriched uranium foils, and the reduced Χ 2 between the modeled and experimental values was 1.21. The results from the STAYSL unfold, reduced Χ 2 = 1.62, indicated that the modeled neutron spectrum was achieved and the systematic nuclear data uncertainty associated with the neutron transport and activation product cross sections was representative of the experiment. Integral cumulative fission product yield data were collected for 37 mass chains with a combination of gamma-ray spectrometry and radiochemical analysis. Fission product analysis was generally in agreement with two models using a semi-empirical fit and the General Observables of Fission code, with the exception of mass chains 88, 109, 111, 112, 113, 129, 139, 142, 144, 151, and 156.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗

DOE OSTI2020

Integrating Predictions for Improving Defect Classification Accuracy in NDT-based Assessment of Concrete - 20229

There is an increasing need to create predictive models for defect classification in concrete using the output of non-destructive testing (NDT) techniques. Recent advancement of machine-learning algorithms has offered several techniques for developing classification models for different types of data sets. However, the performance of these algorithms is very uncertain, mainly when applied to small and noisy datasets. For example, when human access is limited (e.g., nuclear facility), robot-based NDT is preferred. But compared to manual tests with humans present on site, the data sets are small, and more noise can exist. Therefore, it is imperative to develop new approaches to ensure a consistently high classification accuracy for inadequate data sets. This study explores the classification performance on NDT dataset using classifiers from different machine-learning algorithms, namely k-Nearest Neighbor (kNN), Decision Tree, Naive Bayes, Logistic Regression, and Support Vector Machine (SVM). The authors further integrated the predictions from these classifiers using proposed methods. The integration strategy combines the output of the classifiers based on two different measures, accuracy, and performance (ACC and PERF), using equations such as sum, average, and square-root-of-sums-of-squares (SRSS). Our results reveal varying classification accuracies across individual classifiers with different misclassifications across the test data set. The integration strategy provided significant improvement in the classification accuracy compared to the individual classifiers. Furthermore, the results indicate minimal variation across the integration methods as compared to the variation across the individual classifiers. To conclude, prediction integration offers a unique approach for combining the output of multiple classifiers to create redundancies with the potential of achieving high classification performance and improved reliability in predictive models for defect detection in concrete. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2023

Characterization and dynamics of the peculiar stream Jhelum: A tentative role for the Sagittarius dwarf galaxy

Stellar streams are a promising tool to study the Milky Way’s dark matter subhalo population, as interactions with subhalos are expected to leave visible imprints in the streams in the form of substructure. However, there may be other causes of substructure. Here we studied the kinematics and the unusual morphology of the stellar stream Jhelum. Using a combination of ground-based photometry and Gaia EDR3 astrometry, we characterized the morphology of Jhelum. We combined this new data with radial velocities from the literature to perform orbit integrations of the stream in static Galactic potentials. We also carried out N-body simulations in the presence of the Sagittarius dwarf galaxy. The new data reveal a previously unreported tertiary component in the stream, as well as several gaps and a kink-like feature in its narrow component. We find that for a range of realistic Galactic potentials, no single orbit is able to reproduce Jhelum’s radial velocity data entirely. A generic property of the orbital solutions is that they share a similar orbital plane to Sagittarius and this leads to repeated encounters with the stream. Using N-body simulations that include a massive Sagittarius, we explored its effect on Jhelum, and we show that these encounters are able to qualitatively reproduce the narrow and broad components in Jhelum, as well as create a tertiary component in some cases. We also find evidence that such encounters can result in an apparent increase in the velocity dispersion of the stream by a factor up to four due to overlapping narrow and broad components. Our findings suggest that the Jhelum stream is even more complex than once thought; however, its morphology and kinematics can tentatively be explained via the interactions with Sagittarius. In this scenario, the formation of Jhelum’s narrow and broad components occurs naturally, yet some of the smaller gap-like features remain to be explained.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2025

Merged aerosol size distribution from SMPS and OPC for SAIL

This dataset contains merged aerosol number size distribution data for the Surface Atmosphere Integrated Field Laboratory (SAIL) campaign. The merged size distribution data were constructed by combining measurements from a scanning-mobility particle sizer (SMPS) and an optical particle counter (OPC), covering a size range of 0.01–35 µm. The merging methodology follows the approach described by Hand and Kreidenweis (2002) and Marinescu et al. (2019). All aerosol data from the ARM archive were corrected to standard temperature (273.15 K) and pressure (101.3 kPa).

merged size distribution↗

DOE OSTI2026

JANUS: Resilient and Adaptive Data Transmission for Enabling Timely and Efficient Cross-Facility Scientific Workflows

In modern science, the growing complexity of large-scale scientific projects has led to an increasing reliance on cross-facility scientific workflows, where resources and expertise from multiple institutions and geographic locations are leveraged to accelerate scientific discovery. These workflows often require transmitting huge amounts of scientific data through wide-area networks. Although high-speed networks like ESnet and transfer services such as Globus have improved data mobility, several challenges remain. The sheer volume of data can overwhelm network bandwidth, widely used transport protocols such as TCP suffer from inefficiencies due to retransmissions triggered by packet loss, and existing fault-tolerance mechanisms like erasure coding introduce substantial overhead. In this paper, we propose Janus, a resilient and adaptable data transmission approach designed for cross-facility scientific workflows. Unlike traditional TCP-based methods, Janus leverages UDP, integrates erasure coding for fault tolerance, and combines it with error-bounded lossy compression to reduce overhead. This novel design allows users to balance data transmission time and accuracy, optimizing transfer performance based on specific scientific requirements. Additionally, Janus dynamically adjusts erasure coding parameters in response to real-time network conditions, ensuring efficient data transfers even in fluctuating environments. We develop optimization models for determining ideal configurations and implement adaptive data transfer protocols to enhance reliability. Through extensive simulations and real-network experiments, we demonstrate that Janus significantly improves transfer efficiency while maintaining data fidelity.

Esaulov, Vladislav [Georgia State University, Atla↗

DOE OSTI2026

Preliminary Assessment for the Electric Load Shifting Potential of Integrating Thermal Energy Storage with Heat Pumps in Residential Buildings in Texas of United States

The widespread adoption of electric-driven heat pumps for heating and cooling is expected to significantly increase electric demand. Cooling electric demand will result in an increase in peak hours electric loads, placing additional strain on the grid during peak hours. This challenge, combined with the current rapidly increasing demand from data centers, exacerbates the electric demand duck curve problem. Integrating thermal energy storage (TES) with heat pump can shift electric use for heating and cooling from peak to off-peak hours of the electric grid, which can help flatten the daily electric demand profile of a building. This paper presents a novel design that integrates heat pump with TES (HP-TES), which uses phase change materials (PCM). Heat pump charges TES by melting or freezing PCM during off-peak hours when there is no thermal demand from the building. TES is then discharged (i.e., by freezing or melting PCM) during peak hours to provide a more favorable heat source or heat sink for the heat pump to meet the thermal demand of the building with lower electricity use than conventional air-source heat pumps. Computer simulations were developed to predict the performance of HP-TES applied to a typical single-family house in the US. The building-level simulation results were scaled up to preliminarily assess the aggregated impacts of deploying HP-TES across all single-family houses in Texas of the United States, including reduction of peak demand of the electric grid.

Anees, Fady [ORNL]↗

DOE OSTI2023

The disCO2ver Platform: Curating Data and Tools for Geologic Carbon Sequestration and Deep Subsurface Research Systems

The U.S. DOE National Energy Technology Laboratory has invested 12+ years of development into the data repository and digital laboratory, the Energy Data eXchange (EDX, edx.netl.doe.gov). Supporting a variety of research areas across the DOE Office of Fossil Energy and Carbon Management, the platform has successfully curated and preserved thousands of data products from DOE research. The Carbon Storage Program has successfully supported data curation, upload, and publishing of data products on EDX for many years, demonstrating a success story of how resources like EDX can effectively help with long term preservation and publishing of DOE data products. EDX continues to shift towards cloud-supported infrastructure, taking a hybrid approach combining on-premises compute and storage integrated with cloud-hosted services. The integration of cloud compute and hybrid architecture enables the development of EDX-hosted platforms that tailor the data and tools hosted on them to a specific community, enables implementation of machine learning tools for data discovery and filtering, and enables the hosting of virtual (online user interface) tools. Geologic carbon sequestration (GCS) research continues to scale up in response to the current administration goals to reduce greenhouse gas emissions and transition the energy economy. Over the last year, EDX’s disCO2ver platform has been developed in response to the need for access to data products and tools to support the scaling up of GCS research. disCO2ver provides access to data resources and tools, produced by DOE and outside authoritative external resources. The platform also provides a user-access control component for the virtualization and cloud hosting of tools. Tools that need to be virtualized, to eliminate the need for users to download the tool and use local compute resources, is essential to supporting big-data analysis and machine learning that is becoming common place in carbon storage modeling, risk analysis, and data publishing practices. This talk will review the EDX’s disCO2ver platform and the current work ongoing to curate data and tools to support GCS and deep subsurface systems research.

Morkner, Paige↗

DOE OSTI2024

Identification of integrated proteomics and transcriptomics signature of alcohol-associated liver disease using machine learning

Distinguishing between alcohol-associated hepatitis (AH) and alcohol-associated cirrhosis (AC) remains a diagnostic challenge. In this study, we used machine learning with transcriptomics and proteomics data from liver tissue and peripheral mononuclear blood cells (PBMCs) to classify patients with alcohol-associated liver disease. The conditions in the study were AH, AC, and healthy controls. We processed 98 PBMC RNAseq samples, 55 PBMC proteomic samples, 48 liver RNAseq samples, and 53 liver proteomic samples. First, we built separate classification and feature selection pipelines for transcriptomics and proteomics data. The liver tissue models were validated in independent liver tissue datasets. Next, we built integrated gene and protein expression models that allowed us to identify combined gene-protein biomarker panels. For liver tissue, we attained 90% nested-cross validation accuracy in our dataset and 82% accuracy in the independent validation dataset using transcriptomic data. We attained 100% nested-cross validation accuracy in our dataset and 61% accuracy in the independent validation dataset using proteomic data. For PBMCs, we attained 83% and 89% accuracy with transcriptomic and proteomic data, respectively. The integration of the two data types resulted in improved classification accuracy for PBMCs, but not liver tissue. We also identified the following gene-protein matches within the gene-protein biomarker panels: CLEC4M-CLC4M, GSTA1-GSTA2 for liver tissue and SELENBP1-SBP1 for PBMCs. In this study, machine learning models had high classification accuracy for both transcriptomics and proteomics data, across liver tissue and PBMCs. The integration of transcriptomics and proteomics into a multi-omics model yielded improvement in classification accuracy for the PBMC data. The set of integrated gene-protein biomarkers for PBMCs show promise toward developing a liquid biopsy for alcohol-associated liver disease.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2025

TorchBraid: High-Performance Layer-Parallel Training of Deep Neural Networks with MPI and GPU Acceleration

TorchBraid is a high-performance implementation of layer-parallel training for deep neural networks (DNNs) supporting MPI-based parallelism and GPU acceleration. Layer-parallel training has been developed to overcome the serialization inherent in forward and backward propagation of DNNs that limits utilization of computational resources in the strong scaling limit. To achieve this, TorchBraid integrates the PyTorch neural network framework with the state-of-the-art XBraid time-parallel library. Furthermore, this article presents the use and performance of TorchBraid, in addition to solutions for overcoming the algorithmic challenges inherent in combining automatic differentiation with layer-parallel. Results are presented with and without GPU acceleration for the Tiny ImageNet and MNIST image classification data sets, as well as recurrent neural networks. Overall, TorchBraid enables fast training of DNNs, both in a strong and weak scaling context. In addition to the TorchBraid software, several new advances in applying layer-parallel algorithms are detailed. Integration of layer-parallel with data-parallel algorithms is presented for the first time, showing the computational advantages of the combination. Standard deep learning techniques, like batch-normalization, are developed for layer-parallel training. Finally, a new approach combining layer-parallel with spatial coarsening in order to accelerate training for 3D image classification shows roughly a 10× speedup over serial execution.

Layer-parallel↗

DOE OSTI2024

Reconstruction and Selection of Neutrino Interactions in MicroBooNE using Deep Convolutional Neural Networks

In this document, we describe a new reconstruction workflow developed for the MicroBooNE experiment. It features the use of Deep Convolutional Neural Networks trained to recognize key structures within the data sufficient for the 3D reconstruction of neutrino interactions within the detector. As a test of the reconstruction utility, the products of the reconstruction workflow are used to select inclusive charged-current (CC) $\nu_e$ and $\nu_\mu$ interactions in both simulated and real MicroBooNE data. In simulation, our $\nu_e$ and $\nu_\mu$ selections achieve an efficiency of 57% and 68\%, respectively, with a purity of 91% and 96%, respectively. We find that these selections are competitive with the inclusive selections used for the most recent MicroBooNE LEE searches. In particular, the CC-$\nu_e$ inclusive selection efficiency improves by over 20% while also improving sample purity. As a first step in quantifying potential bias, the data and Monte Carlo expectati ons are compared for both selections using the MicroBooNE open data. Within statistical and systematic uncertainties, both the electron and muon CC-inclusive event samples agree. A comparison of the real data events chosen by our work and another reconstruction framework shows that the two analyses each identify a sizeable fraction of events the other does not. This suggests that future analyses integrating the strengths of each could lead to combined gains. This work demonstrates, for the first time on real LArTPC data, state-of-the-art neutrino interaction reconstruction centered around deep learning algorithms.

43 PARTICLE ACCELERATORS↗