Search NASA⌕ Search

SEARCH · Search NASA

Results for “task 4”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Laboratory earthquake forecasting: A machine learning competition

Earthquake prediction, the long-sought holy grail of earthquake science, continues to confound Earth scientists. Could we make advances by crowdsourcing, drawing from the vast knowledge and creativity of the machine learning (ML) community? We used Google’s ML competition platform, Kaggle, to engage the worldwide ML community with a competition to develop and improve data analysis approaches on a forecasting problem that uses laboratory earthquake data. The competitors were tasked with predicting the time remaining before the next earthquake of successive laboratory quake events, based on only a small portion of the laboratory seismic data. The more than 4,500 participating teams created and shared more than 400 computer programs in openly accessible notebooks. Complementing the now well-known features of seismic data that map to fault criticality in the laboratory, the winning teams employed unexpected strategies based on rescaling failure times as a fraction of the seismic cycle and comparing input distribution of training and testing data. In addition to yielding scientific insights into fault processes in the laboratory and their relation with the evolution of the statistical properties of the associated seismic data, the competition serves as a pedagogical tool for teaching ML in geophysics. The approach may provide a model for other competitions in geosciences or other domains of study to help engage the ML community on problems of significance.

58 GEOSCIENCES↗
DOE OSTI2021

Experimental Evaluation of Deformation and Fracture Mechanisms in Highly Irradiated Austenitic Steels

The present report documents recent experimental results of analysis using scanning electron microscopy/electron backscatter diffraction (SEM-EBSD) of plastic deformation mechanisms and strain localization phenomena in austenitic steels irradiated by neutrons. Experiments were performed with specimens irradiated to 125 dpa and, additionally, with specimens that experienced radiation-induced swelling up to 3%. Section 1 briefly analyzes the deformation localization in irradiated steels and its consequences on the material performance. The section describes the advantages and importance of the SEM-EBSD approach combined with in situ mechanical testing capability. Section 2 briefly introduces the experimental tools and methods (i.e., SEM/EBSD in situ tensile frame, electric discharge machine to manufacture irradiated specimens) and describes the investigated materials (i.e., element composition, irradiation conditions, and general microstructure). Section 3 describes the key experimental results and provides a brief analysis and comparison with the datasets obtained earlier within the same task (i.e., low-dose specimens). The discussion focuses on EBSD microstructure maps with strain localization features, misorientation evolution as a function of strain, and observed deformation mechanisms. Section 4 evaluates data collected in recent years on highly irradiated steel and estimates the possible misorientation evolution under irradiation. The section introduces and discusses the concept of in-service-induced damage as an irradiation-assisted stress-corrosion cracking precursor. Section 5 summarizes the work performed. As expected, the present work results are beneficial for exploring and understanding degradation mechanisms in highly irradiated in-core materials found in light water reactors after long-term in-service life.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

Components of aircraft life support systems interact with each other and the user

The life support system in a tactical aircraft provides necessary supplemental oxygen to the aircrew. However, interactions among its various components may generate unexpected breathing loads. We focus here on the interactions between a regulator and breathing mask commonly used together in the U.S. Navy, the CRU-103 regulator and MBU 23/P mask, and some effects of the interactions on the user. The data reported were collected during a larger research effort examining potential physiological and cognitive effects of low regulator inlet pressures. Seventeen participants completed a series of tasks under mild exercise while breathing 40% O 2 (balance N 2 ) from an MBU-23/P mask supplied by a CRU-103 regulator with supply pressures 10, 6, 4, and 2 psig (CRU-103 specifications are for inlet pressures from 5 to 120 psig). Variables measured included flow to the mask and pressures at the regulator supply, in the hose to the mask, and in the mask. In addition to restricting inspiratory flow, low inlet pressure to the CRU-103 caused a counterintuitive overshoot in gas delivery pressure at end-inspiration, a mean increase of 1.5 cm H 2 O between the 10- and 2 psig conditions. The added pressure to the exhalation valve increased the expiratory threshold, the pressure to start expiratory flow, by approximately 2 cm H 2 O, increasing the effort needed to exhale.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Efficient Anomaly Detection Driven By Different Machine Learning Architectures And Models

The rapid growth and ubiquitous adoption of the internet and cyber-physical systems (CPS) have fundamentally transformed modern communication, work, and human-system interactions. While networks now form the backbone of critical digital ecosystems, enabling seamless data transmission across diverse, interconnected systems, this increased connectivity also expands the attack surface, making real-time detection of network intrusions and anomalies a pressing challenge. Detecting unusual activities within network infrastructure requires advanced data traffic analysis to differentiate between legitimate and malicious interactions. Traditional approaches to network anomaly detectionâ??such as rule-based and signature-based systemsâ??often depend on predefined patterns to identify known anomalies, limiting their effectiveness against emerging, stealthy, or previously unseen threats. These conventional methods suffer from high false alarm rates and fail to adapt to the ever-evolving nature of network traffic, particularly in large-scale, decentralized environments where data volume, velocity, and variety are constantly increasing. This dissertation presents artificial intelligence (AI)-driven approaches to anomaly detection that leverage graphics processing unit (GPU)-enabled high-performance computing (HPC) platforms for processing massive network traffic data and monitoring the components of cyber-physical systems (CPS) for potentially hazardous conditions. The research advances several key contributions: (1) Designing efficient machine learning techniques for CPS condition monitoring and anomaly detection; (2) enabling federated learning (FL) frameworks that enable distributed detection while preserving data privacy and system resilience; (3) exploring graph-based methodologies combining graph neural networks (GNN) and graph machine learning (ML) approaches for the Internet of Things (IoT) and automotive network security, and (4) performing distributed edge computing optimizations that integrate FL with scalable technologies for reduced communication overhead. Through extensive experiments, these methodologies demonstrate that complex anomaly detection and condition monitoring tasks can be achieved while balancing computational efficiency and detection accuracy through fine-grained network information processing. The frameworks developed in this research establish a robust foundation for network anomaly detection, providing scalable, adaptive, and privacy-preserving solutions for safeguarding CPS and IoT networks in an increasingly interconnected digital landscape. The practical implications of these research findings are significant, as they can inform the development of next-generation network security systems and contribute to the protection of critical infrastructure against sophisticated cyber attacks.

Marfo, William↗
DOE OSTI2022

Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties

Polymer electrolytes are promising candidates for the next generation lithium-ion battery technology. Large scale screening of polymer electrolytes is hindered by the significant cost of molecular dynamics (MD) simulation in amorphous systems: the amorphous structure of polymers requires multiple, repeated sampling to reduce noise and the slow relaxation requires long simulation time for convergence. Here, we accelerate the screening with a multi-task graph neural network that learns from a large amount of noisy, unconverged, short MD data and a small number of converged, long MD data. We achieve accurate predictions of 4 different converged properties and screen a space of 6247 polymers that is orders of magnitude larger than previous computational studies. Further, we extract several design principles for polymer electrolytes and provide an open dataset for the community. Our approach could be applicable to a broad class of material discovery problems that involve the simulation of complex, amorphous materials.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Epitaxial Growth Development: CRADA Final Report

The purpose of this CRADA is to assist Trumpf Photonics in developing a procedure to grow ZnSe epilayers on the (110) facets of AlGaAs/InGaAs laser diodes that will provide high degrees of electronic passivation and performance reliability. Work will be divided into four tasks: 1) characterization of material growth at Trumpf Photonics, 2) development of a highly effective AlGaAs facet cleaning procedure at NREL, 3) development of a ZnSe epitaxy procedure at NREL, and 4) transfer of the procedures developed at NREL to the Trumpf Photonics site. This CRADA is designed to last 3 years total.

36 MATERIALS SCIENCE↗
DOE OSTI2025

HP-MDR: High-performance and Portable Data Refactoring and Progressive Retrieval with Advanced GPUs

Scientific applications produce vast amounts of data, posing grand challenges in the underlying data management and analytic tasks. Progressive compression is a promising way to address this problem, as it allows for on-demand data retrieval with significantly reduced data movement cost. However, most existing progressive methods are designed for CPUs, leaving a gap for them to unleash the power of today’s heterogeneous computing systems with GPUs.In this work, we propose HP-MDR, a high-performance and portable data refactoring and progressive retrieval framework for GPUs. Our contributions are four-fold: (1) We carefully optimize the bitplane encoding and lossless encoding, two key stages in progressive methods, to achieve high performance on GPUs; (2) We propose pipeline optimization and incorporate it with data refactoring and progressive retrieval workflows to further enhance the performance for large data process; (3) We leverage our framework to enable high-performance data retrieval with guaranteed error control for common Quantities of Interest; (4) We evaluate HP-MDR and compare it with state of the arts using five real-world datasets. Experimental results demonstrate that HP-MDR delivers an average 13.68 × and 6.31 × throughput in data refactoring and progressive retrieval tasks, respectively. It also leads to 11.22 × throughput for recomposing required data representations under Quantity-of-Interest error control and 6.04 × performance for the corresponding end-to-end data retrieval, when compared with state-of-the-art solutions.

Li, Yanliang [University of Oregon]↗
DOE OSTI2026

Short-term electricity load forecasting: Application-driven evaluation of machine learning models across spatial and temporal scales

As we transition towards a decarbonized economy, the integration of variable renewable energy resources and new demands (e.g., electric vehicles, heat pumps) into the electricity grid places unprecedented pressure on grid operators to effectively anticipate and manage peak load. In this context, machine learning algorithms are proving to be indispensable for accurate short-term load forecasting, a crucial task to address these challenges. This study benchmarks 6 machine learning algorithms, including three neural networks and three tree-based algorithms, across various levels of spatial aggregation and time horizons (1, 4, 8, 24, and 48 h). The central contribution of this work is the comparison and analysis of load forecasting models not only based on statistical metrics, but also based on a novel error metric, which evaluates the cost implications of forecast errors for power system stakeholders. Results show that tree-based models outperform neural networks, based on statistical metrics, and yield less skewed error distributions for most spatial scales. However, through the lens of the novel error metric, neural networks are the more competitive choice, especially for forecast horizons that exceed 8 h. The study concludes with actionable recommendations to grid operators and highlights the need for the development of error metrics that link forecasting accuracy to operational costs. To promote transparency and open science, the datasets and Python code are open-sourced via a supplementary repository.

Houben, Nikolaus↗
DOE OSTI2020

Regional Geologic Cross Sections for Potential Storage and Containment Zones in the MRCSP Region [plus Plates 1-6]

The regional characterization work conducted by the Geoteams during the MRCSP Phase III project period (2010 –2019) focused on the following tasks: (1) refinement of geologic seals/reservoir systems; (2) assessment of Atlantic Coastal Plain and offshore opportunities; (3) expanded assessments of oil and gas fields, particularly as they relate to enhanced recovery opportunities; (4) regional support for implementation of carbon capture utilization and storage (CCUS) in the partnership area; and (5) communication and data sharing. This report, entitled Regional Geology, has been prepared in association with (4), regional support for implementation of CCUS in the partnership area..

58 GEOSCIENCES↗
DOE OSTI2020

Enhanced Recovery Opportunities in the Appalachian Basin

The Midwest Regional Carbon Sequestration Partnership (MRCSP) has incorporated the work of geologic research teams (Geoteams) in its regional characterization, project planning and carbon dioxide (CO2) injection implementation work since the partnership was established by the U.S. Department of Energy (DOE) in 2003. Over this 16-year period, the cohort of Geoteams has grown from five to ten states and has contributed to the characterization of geologic sequestration opportunities, refinement of reservoir and seal data, and supported injection efforts through both predictive and post-injection assessments. The regional characterization work conducted by the Geoteams during the MRCSP Phase III project period (2010 – 2019) focused on the following tasks: (1) refinement of geologic seals/reservoir systems; (2) assessment of Atlantic Coastal Plain and offshore opportunities; (3) expanded assessments of oil and gas fields, particularly as they relate to enhanced recovery opportunities; (4) regional support for implementation of carbon capture utilization and storage (CCUS) in the partnership area; and (5) communication and data sharing. The findings of this work are summarized in the final report entitled Final Report of Geologic Carbon Capture Utilization and Storage Opportunities in the form of a state-by-state presentation for the MRCSP Region. In addition to the capstone deliverable mentioned above, the Geoteams have also prepared a series of topical reports to elaborate on specific geologic intervals and/or geographic areas of study completed during the Phase III project period. Specifically, these topical reports address: (1) the Atlantic Coastal Plain and adjacent offshore; (2) Cambro-Ordovician reservoirs/seals in the region; (3) enhanced oil and gas recovery opportunities in the Appalachian Basin; and (4) enhanced oil recovery (EOR) in the Michigan Basin. The remainder of this topical report presents our findings relative to enhanced recovery opportunities in the Appalachian Basin.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Performance Year 1 Technical Report - OPEN COG Grid: Extendable Coherent Models-Datasets for Cognitive Power Grids

The OPEN COG Grid project is a collaborative effort between LLNL, NREL, and Texas A&M University (TAMU) to develop synthetic power system datasets that (i) contain all technical information that would be available in a real system, allowing to conduct studies ranging from dynamic simulation to long term planning studies; ii) are accessible to researchers from the broader data sciences community, as oppossed to power system experts only; and (iii) This report summarizes the work conducted during the first 15 months of execution of the project. These activities encompassed: 1. Conduct a survey of existing open data sets and open source power systems simulators, their supported use cases, and accessibility (Chapter 1). 2. Define a new extensible specification for power system data, covering all parameters necessary for most computational use cases (Chapter 2). 3. Collecting real technical system data to complete missing parameters in existing open source datasets (Chapter 3). 4. Develop models that capture the behavior of emergent actors in power grids, neglected by existing datasets; aggregated residential demand response (Chapter 4) and demand response of cryptocurrency miners (Chapter 5). 5. Collect detailed spatial information on distributed energy resources, particular, solar photovoltaic facilities (Chapter 6). The following chapters provide detailed descriptions of these tasks, the assumptions taken, and their findings. In conducting these tasks, the project team produced: two (accepted) conference papers; one journal paper under submission; one draft journal paper pending submission; released one repository with the developed power system data specification, with documentation and examples; and one extended dataset for the Texas power grid under review for release. The team hopes these contributions will enhance access to power system data and remove barriers to the development of new computational techniques for power systems, particularly, those inspired by cognitive sciences.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Automation of Solid Oxyde Electrolyzer Cell (SOEC) & Stack Assembly

The work performed under this agreement before the No/Go decision amounted to the following: 1. Preliminary manufacturing requirements defined by business sensitivity, baseline processes & risk assessment; 2. Process & materials development, in-line gauge exploration, and preliminary automation work used to reduce risk & further refine equipment specifications; 3. “Request for Quote” issued to multiple suppliers for major equipment; 4. Application specific equipment, hardware, and fixturing will be more beneficial to fabricate inhouse; 5.Current proposals & estimates meet cycle time, capital spend, & direct labor; space is on target but requires awareness; 6. Team will continue to explore opportunities to reduce risk (dry time, traceability); 7. Go / No-Go, Purchase Orders, Equipment build & commissioning next All other future task were not completed because during the Go /No-Go decision it was confirmed this project was a "No-Go" and did not proceed past BP1; these included the following: 1. Preliminary manufacturing requirements defined by business sensitivity, baseline processes & risk assessment; 2. Process & materials development, in-line gauge exploration, and preliminary automation work used to reduce risk & further refine equipment specifications; 3. “Request for Quote” issued to multiple suppliers for major equipment; 4. Application specific equipment, hardware, and fixturing will be more beneficial to fabricate inhouse; 5. Current proposals & estimates meet cycle time, capital spend, & direct labor; space is on target but requires awareness; 6. Team will continue to explore opportunities to reduce risk (dry time, traceability) In final preparation of the termination of the Automation of Solid Oxyde Electrolyzer Cell (SOEC) & Stack Assembly, Cummins has purchased no equipment with government funds, and there is no government-owned property in Cummins possession related to this project. Minimal labor and travel were completed and paid. This acts as the Final technical report and concludes our business with DOE on this grant.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Benchmarking materials property prediction methods: the Matbench test set and Automatminer reference algorithm

Abstract We present a benchmark test suite and an automated machine learning procedure for evaluating supervised machine learning (ML) models for predicting properties of inorganic bulk materials. The test suite, Matbench, is a set of 13 ML tasks that range in size from 312 to 132k samples and contain data from 10 density functional theory-derived and experimental sources. Tasks include predicting optical, thermal, electronic, thermodynamic, tensile, and elastic properties given a material’s composition and/or crystal structure. The reference algorithm, Automatminer, is a highly-extensible, fully automated ML pipeline for predicting materials properties from materials primitives (such as composition and crystal structure) without user intervention or hyperparameter tuning. We test Automatminer on the Matbench test suite and compare its predictive power with state-of-the-art crystal graph neural networks and a traditional descriptor-based Random Forest model. We find Automatminer achieves the best performance on 8 of 13 tasks in the benchmark. We also show our test suite is capable of exposing predictive advantages of each algorithm—namely, that crystal graph methods appear to outperform traditional machine learning methods given ~10 4 or greater data points. We encourage evaluating materials ML algorithms on the Matbench benchmark and comparing them against the latest version of Automatminer.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Toward Large-Scale Image Segmentation on Summit

Semantic segmentation of images is an important computer vision task that emerges in a variety of application domains such as medical imaging, robotic vision and autonomous vehicles to name a few. While these domain-specific image analysis tasks involve relatively small image sizes (~ 10 2 × 10 2 ), there are many applications that need to train machine learning models on image data with extents that are orders of magnitude larger (~10 4 × 10 4 ). Training deep neural network (DNN) models on large extent images is extremely memory-intensive and often exceeds the memory limitations of a single graphical processing unit, a hardware accelerator of choice for computer vision workloads. Here, an efficient, sample parallel approach to train U-Net models on large extent image data sets is presented. Its advantages and limitations are analyzed and near-linear strong-scaling speedup demonstrated on 256 nodes (1536 GPUs) of the Summit supercomputer. Using a single node of the Summit supercomputer, an early evaluation of a recently released model parallel framework called GPipe is demonstrated to deliver ~ 2X speedup in executing a U-Net model with an order of magnitude larger number of trainable parameters than reported before. Performance bottlenecks for pipelined training of U-Net models are identified and mitigation strategies to improve the speedups are discussed. Together, these results open up the possibility of combining both approaches into a unified scalable pipelined and data parallel algorithm to efficiently train U-Net models with very large receptive fields on data sets of ultra-large extent images.

Seal, Sudip↗
DOE OSTI2024

Marine Algae Industrialization Consortium (MAGIC): Combining biofuel and high-value bioproducts to meet the RFS

The Marine Algae Industrialization Consortium (MAGIC) was formed to address pressing challenges in the commercialization of microalgae as a source of biofuel. The “Marine Algae Industrialization Consortium (MAGIC): Combining biofuel and high-value bioproducts to meet the RFS” project formally addressed two US Department of Energy Bioenergy Technologies Office (BETO) goals: (1) Model the sustainable supply of 1 million metric tonnes ash free dry weight (AFDW) cultivated algal biomass and (2) Demonstrate valuable co-products produced along with biofuel intermediates to increase value of algal biomass by 30%. To achieve these goals, the project demonstrated and validated high-value co-products to drive down the cost of biofuel by increasing the value of algae “co-products” towards increasing the selling price of total algae biomass as one of the key drivers of economics and adoption. This was accomplished through five core, interdependent tasks including: (1) strain selection to identify and deliver strains for mass culture, (2) mass culture using a hybrid cultivation system and following key operating parameters for downstream applications to provide algae feedstock, (3) recovery and conversion to evaluate two alternative methods to separate dry algae biomass into oil and residuals for downstream testing, (4) product assessment to determine biofuel, aquafeed or poultry feed product efficacy using algae biomass fractions as well as to provide critical performance data for valuation and (5) commercialization to use technoeconomic and life cycle assessments (TEA/LCA) as iterative design and assessment tools including consideration of target markets, competitors, and distribution channels to guide product assessment, development and valuation. A total of 46 peer-review publications, many open-access, provide detail of much of the work carried out and the results of the tasks. Additional reports and presentations provide other technical and public engagement material. At a high level, using a variety of approaches, more than 1000 marine microalgae strains were evaluated to ultimately identify the seven winners that were down-selected to be grown in mass culture. Strain selection demonstrated that there were no ‘super strains’ and that each candidate had strengths and limitations for specific products, growth conditions or operational considerations. Mass culture growth of these seven strains at >5000 L / 29 m 2 scale found that four them were suitable for product assessment. More than 250 kg of biomass was produced across hundreds of pond runs along with thousands of cultivation entries on the growth and biomass characteristics as well as environmental parameters. In the process, dozens of standard operating procedures were generated as was custom software to process and analyze cultivation data. Recovery and conversion of algae biomass demonstrated that a hexane solvent based extraction protocol was most effective at recovering oil (biocrude) from algae and four strains were processed to produce oil and lipid extracted algae (residuals) for downstream testing. Membrane-based oil separation was less successful, but may still be applicable to other commercial applications in the future. Product testing demonstrated that algae biocrude is of high quality and hydrotreating generated numerous fractions of high quality composition for fuel and lubricate based applications. Aquafeed studies performed at a variety of scales showed that both whole and defatted (lipid extracted algae) microalgae were suitable as a feed ingredient, but that the specifics of the fed animal and biochemical composition of the algae are critical factors when determining formulation. Similarly, poultry studies on whole and defatted microalgae generally showed positive outcomes on animal growth and health, with some microalgae providing enhanced nutritional composition of the animal product. Economic and life cycle assessments covered a wide range of possible commercialization and sustainability scenarios. Replacement value, improved product value added, consumer values marketing added valuation and improved animal health were considered as alternatives for microalgae valuation. Using the open pond system, algae productivity was identified as the key driver of commercialization economics, but combination of co-products (e.g. animal feed) with biofuel production substantially increased the total selling price of algae. Modeled microalgae selling price exceeded $\$$1500/tonne and could generate competitive biofuel selling prices below $\$$5 gallon gas equivalents using realistic algal productivities. Short (process scale) and longer (decadal trends) sustainability assessments show that marine microalgae can enhance the sustainability of energy production and lead to other realized benefits in water, fertilizer and land use for other sectors (e.g. agriculture). This project successfully demonstrated all of the components of an end-to-end process from mass microalgae cultivation and dewatering, to recovery and conversion of algae biomass components, to final product demonstration and process valuation; the combined results provide a framework for future commercialization of algae based biofuels.

09 BIOMASS FUELS↗
DOE OSTI2026

Classic and Quantum Task-Based Intelligent Runtime for QIRs Running on Multiple QPUs

High-performance computing systems are rapidly evolving into heterogeneous platforms that fuse quantum accelerators with traditional classical processing units (CPUs) and graphical processing units (GPUs). This convergence calls for runtimes capable of managing both classical and quantum workloads in a unified manner. We introduce an intelligent, task-based runtime that marries the Intelligent RuntIme System (IRIS) asynchronous scheduler with a quantum programming stack through the Quantum Intermediate Representation Execution Engine (QIR-EE). Our design allows programs written in the quantum intermediate representation (QIR) to be dispatched concurrently to a variety of back-ends, including multiple quantum simulators and nascent quantum processors, enabling genuine hybrid execution on a single node. To illustrate its practicality, we partition a 4-qubit and 20-qubit circuit into three sub-circuits using quantum circuit cutting via the QCut library. Each sub-circuit is simulated independently by the QIR-EE driver within IRIS, after which a classical post-processing step merges the simulation results to recover the outcome of the original full-circuit computation. This case study demonstrates how finer task granularity can enable the parallel execution and lower the simulation burden per quantum task while preserving overall accuracy, highlighting the feasibility of our hybrid approach.

Miniskar, Narasinga Rao [ORNL] (ORCID:000000018259↗
DOE OSTI2022

Mitigate: An Adaptive Network Data Anonymization Tool Using Condensation-Based Differential Privacy

Modern network devices collect a large amount of data that can be analyzed to identify bottlenecks, anomalies, cyber-attacks, etc. Therefore, there is often a need to analyze such collections of network data quite often by an external expert or by the research community. However, these collections of data contain sensitive, proprietary information. In order for the network data to be shared, it must first be anonymized. The overall objective of this project is to develop an innovative privacy management tool to anonymize network data and achieve sufficient privacy, acceptable data utility, and efficient data analysis at the same time. No existing anonymization methods can achieve all of these at the same time. The core of this technology is a differential private clustering algorithm that provides strong privacy protection, preserves data properties important for subsequent analysis, and allows the party receiving the anonymized data to conduct analysis directly on anonymized data without the need of decryption or any extra processing. The research carried out was to design, implement and verify a solution to this problem by completing the following tasks: 1) developing the core technology; 2) developing a context based method that automatically recommends fields that must be anonymized; 3) conducted experiments showing superior results using our approach compared to existing tools, and 4) developed an intuitive but basic user interface. The research that was conducted generated novel algorithmic techniques that utilize state-of-the-art methods such as condensation, differential privacy preservation, clustering, automated tuning based on contextual awareness, and recommendation techniques to specify columns to users for anonymization leading to optimal privacy that allows research analysis on the dataset. Experiments were conducted to evaluate the efficacy of these novel algorithmic techniques by performing analysis on original non-anonymized datasets, then conducting analysis on the same yet anonymized datasets and comparing the results of the analyses. Overall, the anonymized analysis results were within 1% of the original results, verifying that the generated technology not only guarantees a high level of privacy but also enables research analysis as if it were conducted on the original dataset. Potential applications of this technology include anonymization of any type of structured network datasets that contain sensitive identifiers, such as IP addresses, that can be used in multiple applications. For example, to create an AI or machine learning model for cyber security, e.g., to detect attacks, or for performance analysis, e.g., identify bottlenecks or predict performance. In addition, a market analysis that was conducted for potential applications of this technology identified a broader range of applications of our anonymization technology beyond the network sector that includes healthcare, banking, insurance, securities, finance (FISB), data brokering, cloud services, ad sales, and government.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

BUILD: Binary Understanding and Integration Logic for Dependencies (Final Report)

Increasingly diverse mission needs, the emergence of AI and cloud, and increasing hardware diversity are driving HPC software to be more complex. Modern codes are built from hundreds of small, complex components, and much of the software development process involves integrating these components rather than developing new components from scratch. The goal of the BUILD project was to ease the task of software integration for developers across LLNL’s programs. The project focused on (1) modeling software compatibility, (2) modeling ABI compatibility with binary analysis, (3) developing solver techniques to reason about compatibility, and (4) developing AI/ML models to fill gaps in our understanding of software compatibility. The project has developed several key technologies that help developers—by accelerating development workflows, removing the need for rebuilds, and enabling faster, automatic, and less error-prone code sharing. These technologies are used in LLNL codes and will be ready for the new El Capitan Exascale system in Livermore Computing. Many of these technologies have been hardened and integrated with LLNL’s Spack package manager, and they are already in use by production code teams. Results of BUILD have laid the groundwork for future advances in software integration—the ML and binary modification techniques developed in this project still need to be operationalized but have great potential to further speed up software integration.

97 MATHEMATICS AND COMPUTING↗