Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “federated learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 415 records · Page 23

Licensing and Operation of BEA Research Reactor Package for Fuel, Source and Target Payloads - 19198

The Battelle Energy Alliance (BEA) Research Reactor Package (BRR Package) is currently in use for a variety of payload types and operational scenarios. The BRR Package is licensed by the Nuclear Regulatory Commission (NRC), under Certificate of Compliance (CoC) number USA/9341/B(U)F-96. The original packaging design, testing, and safety analysis activities were conducted by Orano Federal Services (Orano FS, formerly AREVA Federal Services) for the Idaho National Laboratory (INL), operated by the Battelle Energy Alliance (BEA) for the U.S. Department of Energy (DOE). One package was built and delivered to the INL in 2009, and has seen routine use since that time, primarily by DOE University Research Reactor programs. This paper will provide a history and description of the original design and licensing of the package and subsequent amended applications for the addition of new payloads. Each additional payload type provided unique design, operational, and licensing challenges - these challenges will be discussed, and the results and lessons learned presented will be beneficial for application in other radioactive material packaging projects. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Moving from Bilateral to Multilateral Medical Operations

When the ISS Integrated Medical Group moved to a multilateral configuration for the ASTROLAB mission, several challenges were encountered and overcome that allowed for a streamlined operational experience. Dating back to the early 1990s, the European Space Agency (ESA) has sent flight surgeon and Biomedical Engineering (BME) personnel to NASA-JSC and Russia to train for space flight operational support. This training was tailored towards the needs of particular Shuttle/Soyuz missions, and more generally for eventual ISS support. With the announcement of the ASTROLAB mission, NASA and ESA personnel worked together to develop a detailed training template for ESA BMEs to ensure successful support of the mission from the European Astronaut Center (EAC). This training included the deployment of ESA BMEs to JSC, as well as the development of a rotation of ISS-certified NASA BMEs to the EAC. In addition to training, NASA, ESA, and the Russian Federal Space Agency (FSA) worked together preflight to develop multilateral flight control support concepts and implementation plans. This resulted in flight control support schedules, operational rules of engagement, and the delineation of responsibilities. NASA also assisted ESA with the development and deployment of workstation displays to allow the ESA medical flight control team to monitor ISS telemetry from the EAC. The goal of this presentation is to provide details of the preflight preparation and in-flight support of the ASTROLAB mission by the ESA, NASA, and FSA medical support teams. In addition, it will identify lessons learned that will be implemented for future multilateral endeavors.

Roden, S.↗

Analysis and Prediction of Weather Impacted Ground Stop Operations

When the air traffic demand is expected to exceed the available airport's capacity for a short period of time, Ground Stop (GS) operations are implemented by Federal Aviation Administration (FAA) Traffic Flow Management (TFM). The GS requires departing aircraft meeting specific criteria to remain on the ground to achieve reduced demands at the constrained destination airport until the end of the GS. This paper provides a high-level overview of the statistical distributions as well as causal factors for the GSs at the major airports in the United States. The GS's character, the weather impact on GSs, GS variations with delays, and the interaction between GSs and Ground Delay Programs (GDPs) at Newark Liberty International Airport (EWR) are investigated. The machine learning methods are used to generate classification models that map the historical airport weather forecast, schedule traffic, and other airport conditions to implemented GS/GDP operations and the models are evaluated using the cross-validations. This modeling approach produced promising results as it yielded an 85% overall classification accuracy to distinguish the implemented GS days from the normal days without GS and GDP operations and a 71% accuracy to differentiate the GS and GDP implemented days from the GDP only days.

Analysis↗

King County Metro Battery Electric Bus Demonstration: Preliminary Project Results

The U.S. Federal Transit Administration (FTA) funds a variety of research projects that support the commercialization of zero-emission bus technology. To evaluate projects funded through these programs, FTA has enlisted the help of the National Renewable Energy Laboratory (NREL) to conduct third-party evaluations of the technologies deployed under the FTA programs. NREL works with the selected agencies to evaluate the performance of the zero-emission buses compared to baseline conventional buses in similar service. The evaluation effort will advance the knowledge base of zero-emission technologies in transit bus applications and provide 'lessons learned' to aid other fleets in incrementally introducing next generation zero-emission buses into their operations. This report provides preliminary performance evaluation results from a demonstration of three zero-emission battery electric buses at King County Metro in King County, Washington. NREL developed this preliminary results report to quickly disseminate evaluation results to stakeholders. Detailed evaluation results will be published in future reports.

25 ENERGY STORAGE↗

County Connection Battery Electric Bus Demonstration: Preliminary Project Results

The U.S. Federal Transit Administration (FTA) funds a variety of research projects that support the commercialization of zero-emission bus technology. To evaluate projects funded through these programs, FTA has enlisted the help of the National Renewable Energy Laboratory (NREL) to conduct third-party evaluations of the technologies deployed under the FTA programs. NREL works with the selected agencies to evaluate the performance of the zero-emission buses compared to baseline conventional buses in similar service. The evaluation effort will advance the knowledge base of zero-emission technologies in transit bus applications and provide 'lessons learned' to aid other fleets in incrementally introducing next generation zero-emission buses into their operations. This report provides preliminary performance evaluation results from a demonstration of four all-electric trolley-replica buses and two electric vehicle charging stations at County Connection in the San Francisco Bay Area. NREL developed this preliminary results report to quickly disseminate evaluation results to stakeholders. Detailed evaluation results will be published in future reports.

25 ENERGY STORAGE↗

Selection Algorithm for electron neutrino charged current interactions in SBND

The Short Baseline Neutrino (SBN) program at Fermilab is a joint proposal by three experimental collaborations primarily for the investigation of the cause behind the low-energy electron-like event excess observed by the MiniBoone experiment. This dissertation focuses on the near detector of the project, named the Short Baseline Near Detector (SBND), a Liquid Argon Time Projection Chamber apparatus which will conduct searches for sterile neutrinos in the mass range of 1 ${eV}^2/{c}^4$, as well as provide cross-section measurements for neutrino interactions in argon and perform other beyond the standard model studies.\\ \indent As is the case for all detectors in the program, the SBND will use the Booster Neutrino Beam as its source, which will provide it with both muon and electron neutrinos. Given that the ability to discern between the neutrino flavors will be crucial to the fulfillment of the detector's physics goals, the objective of this work is to provide the collaboration with a tool capable of doing so. As such, we here present the development process for an inclusive selection algorithm for the identification of electron neutrino charged current (CC) events regardless of their interaction channel. This is done through a combination of traditional techniques, such as the implementation of cuts on the reconstructed interaction properties, with the use of the Convolutional Visual Network, a machine learning algorithm capable of classifying particle interactions through the analysis of the topology of their final states. With this approach, we have developed a selection process that is capable of identifying $\nu_e$ CC interactions across a wide range of topologies with 34.4\% efficiency, as well as a purity of 91.2\%, making it especially promising for use in cross section studies.

Freire, Hector Moya [ABC Federal U.] (ORCID:000900↗

Exploring the Effects of Population and Employment Characteristics on Truck Flows: An Analysis of NextGen NHTS Origin-Destination Data

Truck transportation remains the dominant mode of US freight transportation because of its advantages, such as the flexibility of accessing pickup and drop-off points and faster delivery. Because of the massive freight volume transported by trucks, understanding the effects of population and employment characteristics on truck flows is critical for better transportation planning and investment decisions. The US Federal Highway Administration published a truck travel origin-destination data set as part of the Next Generation National Household Travel Survey program. This data set contains the total number of truck trips in 2020 within and between 583 predefined zones encompassing metropolitan and nonmetropolitan statistical areas within each state and Washington, DC. In this study, origin-destination-level truck trip flow data was augmented to include zone-level population and employment characteristics from the US Census Bureau. Census population and County Business Patterns data were included. The final data set was used to train a machine learning algorithm-based model, Extreme Gradient Boosting (XGBoost), where the target variable is the number of total truck trips. Shapley Additive ExPlanation (SHAP) was adopted to explain the model results. Results showed that the distance between the zones was the most important variable and had a nonlinear relationship with truck flows.

Uddin, Majbah↗

Arctic Shield 2015 Field Campaign Report

During the week of July 13, 2015, the U.S. Coast Guard’s (USCG) Research and Development Center partnered with Conoco Phillips through a Cooperative Research and Development Agreement to conduct a Search and Rescue (SAR) exercise off of Oliktok Point, Alaska. The Coast Guard was interested in exploring how unmanned aircraft systems (UAS) can be used to enhance capabilities for its SAR mission and gain a better understanding of how it could work jointly with private industry for response operations in remote regions. Participants in the exercise included Coast Guard Pacific Area Command, Coast Guard Cutter Healy, Coast Guard District Seventeen, Coast Guard Air Station Kodiak, and Conoco Phillips. Joining Conoco Phillips were their partners Insitu (a Boeing company), Era Helicopter, and Era Helicopter’s partner Priority One. Other government agencies supporting the exercise were the U.S. Department of Energy’s (DOE) Atmospheric Radiation Measurement (ARM) Climate Research Facility, the National Oceanic and Atmospheric Administration, the Federal Aviation Administration, and the North Slope Borough of the state of Alaska. The exercise scenario involved a simulated small aircraft crash offshore where the survivors took refuge in a 6-man life raft. The aircraft’s last known position and asset availability required the Coast Guard to coordinate the response with Conoco Phillips. This included the use of an Insitu-operated ScanEagle UAS, flown from DOE-ARM’s Sandia National Laboratory-operated facility at Oliktok Point, and manned aircraft provided by both the Coast Guard’s Forward Operating Location in Deadhorse and Era Helicopter. Lessons learned from this exercise will help the Coast Guard understand how to best collaborate with private industry on the North Slope during response operations and develop requirements for UAS performing Coast Guard missions in the Arctic environment. For the ARM facility, the exercise demonstrated some of the opportunities and constraints of using UAS in the Arctic for research purposes.

54 ENVIRONMENTAL SCIENCES↗

(Re)inventing Government-Industry R and D Collaboration

This paper describes the lessons learned in developing and operating a large-scale strategic alliance whose organization and coordination is U.S. Government-led using new means for R&D collaboration. Consortia in the United States counter a century of 1884 Sherman Anti-Trust Law-based governmental and legal policy and a longstanding business tradition of unfettered competition. Success in public-private collaboration in America requires compelling vision and motivation by both partners to reinvent our ways of doing business. The foundations for reinventing government and alliance building were laid in 1994 with Vice President Al Gore's mandates for Federal Lab Reviews and other examinations of the roles and missions for the nation's more than 700 government labs. In addition, the 1984 National Cooperative Research Act (NCRA) set in motion the abilities for U.S. companies to collaborate in pre-competitive technology development. The budget realities of the 1990's for NASA and other government agencies demand that government discover the means to accomplish its mission by leveraging resources through streamlining as well as alliances. Federal R&D investments can be significantly leveraged for greater national benefit through strategic alliances with industry and university partners. This paper presents early results from one of NASA's first large-scale public/private joint R&D ventures.

Holmes, Bruce J.↗

Update on site selection for Canada's national repository for used nuclear fuel - 15481

In 2007, the Government of Canada selected Adaptive Phased Management as Canada's plan that provides for long-term management of Canada's used nuclear fuel in a deep geological repository, located in an informed and willing host. The Nuclear Waste Management Organization is tasked through federal legislation to select the site and develop and manage all aspects of Canada's plan. In May 2010 the Nuclear Waste Management Organization published and initiated the site selection process that serves as a road map for decision-making on the location for the deep geological repository. The Nuclear Waste Management Organization continues to lead the site selection process for a deep geological repository for the long term management of Canada's used nuclear fuel and centre of expertise. The screening down process is advancing and, from an initial starting point of 22 communities expressing interest in learning about the project, as of November 2014 14 communities are now the focus of more detailed studies. Preliminary assessments are underway with these communities, which is the third step in the 9 step site selection process. Preliminary assessments involve preliminary technical and social desktop and field assessments, engagement activities within and beyond the interested community and seeking involvement of Indigenous peoples and nearby municipalities in the planning and conduct of the work. The paper provides an update on the advancement of the site selection process. It describes the nature of the technical and social studies being conducted at this phase of work, including the progressively more detailed field studies which are the focus of technical work at this stage, approach to engagement and collaboration with communities to direct these studies, and the work underway to ensure the framework used for this assessment and engagement includes the range of priorities and perspectives of First Nations and Metis peoples and communities in the broader area. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Potential State Regulatory Pathways to Facilitate Low-Carbon Fuels

States and the federal government are increasingly engaged in the challenges around decarbonizing the electric grid. In particular, regulators, consumers, stakeholders, and utilities recognize the need to carefully consider the role natural gas will play in a decarbonized future. A variety of technology and policy options to reduce greenhouse gas emissions associated with natural gas use are available, including energy efficiency programs, demand reduction tools, strategic electrification, and strategies to reduce emissions from natural gas production, transportation, and consumption. Low-carbon fuels – mainly renewable natural gas (RNG) and clean hydrogen – are being considered an important component of decarbonization goals. RNG and hydrogen may be able to meaningfully reduce emissions from processes independent of geologic natural gas, displacing emissions of methane, a powerful greenhouse gas. Although RNG and hydrogen are not cost-competitive today with geologic natural gas and are smaller in scale and potential than other decarbonization options, they can be explored as potential critical tools to decarbonize sectors that are difficult to electrify or shift off of natural gas entirely, such as air travel, industrial processes, maritime transport, long-distance trucking, space heating on cold days, and railroads (Nadel, 2022). The role of this report is to provide informational context for state utility regulators to understand the impacts of and challenges associated with broader integration of low-carbon fuels, followed by examples of state regulatory actions taken to date to facilitate the development of low-carbon fuels. Setting clear guidance to calculate the environmental benefits of low-carbon fuels and continuing federal and state investments in research and development to reduce costs relative to fossil fuels will be important steps to take to signal the desire to grow the market for these fuels. State public utility commissions may play a key role in setting regulatory frameworks for low-carbon fuels and ensuring that ratepayer funds, if utilized, are done so to further the public interest. This report is intended to summarize decisions that states have made to date on low-carbon fuels. In the spirit of understanding the current market and sharing information, this report provides success stories, and lessons learned across states as regulators implement varying strategies to achieve decarbonization objectives while maintaining their focus on affordability, safety, and reliability of the energy system. The report begins with an introduction of the role of natural gas in the U.S. economy (Section I) and background information on natural gas use, decarbonization, and low-carbon fuels (Section II). Next, the report describes the current market by discussing the scale of current production, emissions intensity, resource potential, and costs of low-carbon fuels compared to geologic natural gas (Section III). Following these sections, the report describes four strategies states have employed to facilitate low-carbon fuels: opening exploratory dockets, approving voluntary tariffs for customers, approving interconnection tariffs for producers, and considering portfolio-wide procurement targets (Section IV). This section lists states that have taken actions in each category, citing utility filings, commission decisions, stakeholder comments, and other relevant sources. Finally, the report concludes with suggested questions regulators may wish to consider regarding low-carbon fuels, in the interest of preparing to make decisions in the future (Section V). These questions include: Are there existing regulatory or technical barriers to voluntary purchases of low-carbon fuels? Can customers work with utilities to procure low-carbon fuels; are producers able to interconnect projects without significant barriers to entry? Should the infrastructure and/or commodity costs of low-carbon fuels be socialized among all ratepayers, or borne solely by the large commercial and industrial (C&I) customers currently driving the market? Should regulated natural gas and/or electric utilities own and operate low-carbon fuel production? How should regulators consider the unique decarbonization potential of low-carbon fuels, particularly for hard-to-abate sectors, in decision-making? Is additional direction or clarity from state policymakers needed? What no-regrets approaches can help facilitate both near-term RNG development and long-term development of hydrogen and other zero-carbon fuels? We collectively wish to express our gratitude to the U.S. Department of Energy, Office of Fossil Energy and Carbon Management, for supporting this report and other technical assistance resources for state regulators on natural gas topics. State regulators operate under a variety of policy environments, and states have vastly different types of energy resources, infrastructure, and customers. While there is no optimal regulatory, policy, or technological solution that will be successful in every state, state regulators can benefit by exchanging lessons learned with their peers across the country. We look forward to continued engagement with our fellow commissioners, commission staff, NARUC, the U.S. Department of Energy, and other stakeholders to develop sound regulation in the public interest.

03 NATURAL GAS↗

NASA Ames summary high school apprenticeship research program, 1983 research papers

Engineering enrollments are rising in universities; however, the graduate engineer shortage continues. Particularly, women and minorities will be underrepresented for years to come. As one means of solving this shortage, Federal agencies facing future scientific and technological challenges were asked to participate in the Summer High School Apprenticeship Research Program (SHARP). This program was created 4 years ago to provide an engineering experience for gifted female and minority high school students at an age when they could still make career and education decisions. The SHARP Program is designed for high school juniors (women and minorities) who are U.S. citizens, are 16 years old, and who have unusually high promise in mathematics and science through outstanding academic performance in high school. Students who are accepted into this summer program will earn as they learn by working 8 hours a day in a 5-day work week. This work-study program features weekly field trips, lectures and written reports, and job experience related to the student's career interests.

Powell, P.↗

Data Sharing in Radiobiology; Towards FAIR

The value of scientific data depends on their findability, accessibility, integrability and reusability according to the FAIR principles. Together with the sustainability of data preservation and access, these principles underpin the long term benefits of scientific research. Within the domain of radiobiology we have a huge array of data types, themes and complexities which make standardisation of metadata, data structure and data integration very challenging. Moreover, it is clear that, for example, in the area of disaster preparedness, the ready discovery and availability of multiple types of data, for example on biological effects of exposure, climatology, ecology, human behavioural and attitudinal studies, is important for an integrated scientific approach. Because these data are spread over many databases, journal supplementary information resources and even the computers of the investigators, their discovery and reuse can be challenging. Despite exhortations from funding agencies and scientific institutions over the past two decades there is still a serious deficit in the willingness and in some cases the ability of investigators to share data, and although much may not be formally „Public domain“, information about the existence of the data, their metadata, and how to obtain them should always be available. We report the progress of work on three databases, the STORE and the NASA GeneLab and LSDA repositories to leverage the Radiation Biology Ontology (RBO), a structured terminology for metadata that can be used by all radiation biology-relevant databases to unite federated and automated data searches across multiple databases, for example using web services, and through semantic web technologies supporting data discovery. The initial primary use-cases for RBO were archiving data in the STORE database (https://www.storedb.org/), the repository used for the RadoNorm and Pianoforte Projects among others, and in the NASA Open Science Data Repository (https://osdr.nasa.gov/bio). The scope of radiobiology research ranges from basic physics to radiation oncology to sociolegal studies; no existing ontology had the necessary breadth or depth to fulfill this need. In addition, a formal ontology has the advantage of being usable for machine learning and, importantly, for tasks like data integration, knowledge extraction from the scientific literature and for query extension and data classification. Standardisation of metadata is one of the primary objectives of the FAIR principles for open data; RBO is an important landmark for FAIR-compliant radiation biology data sharing. The RBO is developed using the open-source tools of GitHub and the OBO Foundry-led Ontology Development Kit, and published through GitHub and the NIH/NCBI BioPortal website. This initial phase of concept modeling has yielded an ontology that has more than 300 declared concepts, with more than 3500 additional concepts imported from other OBO Foundry ontologies with relevance to radiation biology (for example, concepts from the ISO standard Basic Formal Ontology, the Environment Ontology and the Gene Ontology). We welcome input into the development of RBO and encourage its adoption.

ontologies↗

Data Sharing in Radiation Biology: Towards FAIR

The value of scientific data depends on their findability, accessibility, integrability and reusability according to the FAIR principles. Together with the sustainability of data preservation and access, these principles underpin the long term benefits of scientific research. Within the domain of radiobiology we have a huge array of data types, themes and complexities which make standardisation of metadata, data structure and data integration very challenging. Moreover, it is clear that, for example, in the area of disaster preparedness, the ready discovery and availability of multiple types of data, for example on biological effects of exposure, climatology, ecology, human behavioural and attitudinal studies, is important for an integrated scientific approach. Because these data are spread over many databases, journal supplementary information resources and even the computers of the investigators, their discovery and reuse can be challenging. Despite exhortations from funding agencies and scientific institutions over the past two decades there is still a serious deficit in the willingness and in some cases the ability of investigators to share data, and although much may not be formally "Public domain“, information about the existence of the data, their metadata, and how to obtain them should always be available. We report the progress of work on three databases, the STORE and the NASA GeneLab and LSDA repositories to leverage the Radiation Biology Ontology (RBO), a structured terminology for metadata that can be used by all radiation biology-relevant databases to unite federated and automated data searches across multiple databases, for example using web services, and through semantic web technologies supporting data discovery. The initial primary use-cases for RBO were archiving data in the STORE database (https://www.storedb.org/), the repository used for the RadoNorm and Pianoforte Projects among others, and in the NASA Open Science Data Repository (https://osdr.nasa.gov/bio). The scope of radiobiology research ranges from basic physics to radiation oncology to sociolegal studies; no existing ontology had the necessary breadth or depth to fulfill this need. In addition, a formal ontology has the advantage of being usable for machine learning and, importantly, for tasks like data integration, knowledge extraction from the scientific literature and for query extension and data classification. Standardisation of metadata is one of the primary objectives of the FAIR principles for open data; RBO is an important landmark for FAIR-compliant radiation biology data sharing. The RBO is developed using the open-source tools of GitHub and the OBO Foundry-led Ontology Development Kit, and published through GitHub and the NIH/NCBI BioPortal website. This initial phase of concept modeling has yielded an ontology that has more than 300 declared concepts, with more than 3500 additional concepts imported from other OBO Foundry ontologies with relevance to radiation biology (for example, concepts from the ISO standard Basic Formal Ontology, the Environment Ontology and the Gene Ontology). We welcome input into the development of RBO and encourage its adoption.

ontologies↗

Section 180(c) Policy Implementation Exercise: Multiple Views - 17383

The Department of Energy (DOE) Office of Nuclear Energy's Office of Integrated Waste Management (formerly the Nuclear Fuels Storage and Transportation Planning Project) recently completed a two-year Section 180(c) Proposed Policy Implementation Exercise (the Exercise) with volunteers from eight states and one Native American Tribe. Under Section 180(c) of the Nuclear Waste Policy Act of 1982, as amended (NWPA), DOE is responsible for providing technical and financial assistance to states and Tribes for training of local public safety officials through whose jurisdictions the Secretary of Energy plans to transport spent nuclear fuel (SNF) or high-level radioactive waste to a NWPA-authorized facility. In the 2000's, DOE staff worked closely with state and tribal representatives to develop a revised proposed policy to implement Section 180(c), including grants for assessment and planning activities, as well as grants for training public safety officials. This revised proposed policy was published in a Federal Register Notice in 2008 (2008 FRN) (73 Federal Register 64933, Oct. 31, 2008). The purpose of the Exercise was to evaluate the efficacy of DOE's 2008 revised proposed policy for implementing Section 180(c), and identify outstanding issues to be resolved. DOE presented an interim update on the Exercise at the 2016 Waste Management Symposium and the Exercise concluded in June 2016. This paper describes the remaining activities of the Exercise that occurred since the 2016 Waste Management Symposium, and presents the perspectives of one state and one Tribal participant in the Exercise as well as DOE's perspective. The paper concludes with a discussion of the lessons learned from the Exercise, what steps are next, and how the Exercise may inform and improve future consultations between DOE and state, tribal, and local public safety officials. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Neutrino interaction vertex reconstruction in DUNE with Pandora deep learning

The Pandora Software Development Kit and algorithm libraries perform reconstruction of neutrino interactions in liquid argon time projection chamber detectors. Pandora is the primary event reconstruction software used at the Deep Underground Neutrino Experiment, which will operate four large-scale liquid argon time projection chambers at the far detector site in South Dakota, producing high-resolution images of charged particles emerging from neutrino interactions. While these high-resolution images provide excellent opportunities for physics, the complex topologies require sophisticated pattern recognition capabilities to interpret signals from the detectors as physically meaningful objects that form the inputs to physics analyses. A critical component is the identification of the neutrino interaction vertex. Subsequent reconstruction algorithms use this location to identify the individual primary particles and ensure they each result in a separate reconstructed particle. A new vertex-finding procedure described in this article integrates a U-ResNet neural network performing hit-level classification into the multi-algorithm approach used by Pandora to identify the neutrino interaction vertex. The machine learning solution is seamlessly integrated into a chain of pattern-recognition algorithms. The technique substantially outperforms the previous BDT-based solution, with a more than 20% increase in the efficiency of sub-1 cm vertex reconstruction across all neutrino flavours.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Hawaii Space Grant Consortium

The Hawai'i Space Grant Consortium is composed of ten institutions of higher learning including the University of Hawai'i at Manoa, the University of Hawai'i at Hilo, the University of Guam, and seven Community Colleges spread over the 4 main Hawaiian islands. Geographic separation is not the only obstacle that we face as a Consortium. Hawai'i has been mired in an economic downturn due to a lack of tourism for almost all of the period (2001 - 2004) covered by this report, although hotel occupancy rates and real estate sales have sky-rocketed in the last year. Our challenges have been many including providing quality educational opportunities in the face of shrinking State and Federal budgets, encouraging science and technology course instruction at the K-12 level in a public school system that is becoming less focused on high technology and more focused on developing basic reading and math skills, and assembling community college programs with instructors who are expected to teach more classes for the same salary. Motivated people can overcome these problems. Fortunately, the Hawai'i Space Grant Consortium (HSGC) consists of a group of highly motivated and talented individuals who have not only overcome these obstacles, but have excelled with the Program. We fill a critical need within the State of Hawai'i to provide our children with opportunities to pursue their dreams of becoming the next generation of NASA astronauts, engineers, and explorers. Our strength lies not only in our diligent and creative HSGC advisory board, but also with Hawai'i's teachers, students, parents, and industry executives who are willing to invest their time, effort, and resources into Hawai'i's future. Our operational philosophy is to FACE the Future, meaning that we will facilitate, administer, catalyze, and educate in order to achieve our objective of creating a highly technically capable workforce both here in Hawai'i and for NASA. In addition to administering to programs and educating the public in the traditional sense, we also work to facilitate partnerships between other departments (geology & geophysics, engineering, geography, astronomy), state and federal government agencies in Hawai'i, and private industry. In some cases, we are the catalyst for new partnerships between private agency sponsors and education projects or for new joint research and education projects between industry and the University faculty.

Flynn, Luke P.↗

Considerations for Introducing Artificial Intelligence into Nuclear Power Plants

Advanced computational tools and techniques such as artificial intelligence and machine learning (AI/ML) can transform the nuclear power industry. This is necessary given that the economic viability of the existing fleet is in jeopardy and its labor-centric approach to operations and maintenance. Currently, AI/ML research is being undertaken for reactor system design and analysis including fault and accident prognosis, nuclear risk analysis such as plant safety and security evaluation, and plant operations and maintenance including predictive maintenance. Applications include both existing and advanced reactor technologies with the aim of improving operational and business efficiencies. Most every aspect of the organization can benefit, from instrumentation and control, to work planning, to human-machine interactions and business management. AI/ML in nuclear can simplify complex problems and produce more effective decision-making. Nonetheless, careful consideration must be given to the implementation of an AI/ML initiative. The aims of this research are to 1) review barriers to AI/ML adoption within the nuclear power industry, and 2) suggest potential solutions. These barriers are organized along five distinct categories (Figure 1) that are interconnected. The first are historical barriers that track the industry’s development over the decades including worldwide nuclear events that shaped public perceptions. The resulting federal scrutiny and intense safety culture that emerged are discussed. Technical barriers to AI/ML adoption are considerable, and include data privacy concerns, data governance, and the current lack of AI/ML expert knowledge at the plants. The main business case barrier remains cost, but an absence of an industry-wide vision and wide-scale adoption also produces reluctance. Stakeholder readiness is reviewed with special attention given to regulatory readiness. The 5-year strategic plan for AI readiness recently published by the U.S. Nuclear Regulatory Commission is highlighted. Last, adoption barriers at the user level are addressed including the importance of user experience and explainable AI. The AI adoption barriers described here are inter-related and ideally should be addressed in a holistic fashion.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗