Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Online 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 685 records · Page 38

Intelligent Experiments Through Real-time AI: Fast Data Processing and Autonomous Detector Control for sPHENIX and Future EIC Detectors (Final Report)

The overall vision of this project was to integrate real-time artificial intelligence (AI) directly into the data acquisition and detector-control systems of nuclear physics experiments, including both fast online event selection and an autonomous detector-control feedback loop. The work carried out under the award focused on the fast online event-selection half of that vision: the efficient recording of low-momentum heavy-flavor (HF) hadron decays in proton-proton collisions at the sPHENIX experiment at the Relativistic Heavy Ion Collider (RHIC)—an observable that requires fast tracking and topological trigger selection not previously demonstrated at RHIC, and that is essential for QCD studies at future facilities such as the Electron-Ion Collider (EIC). The autonomous detector-control (GPU-based feedback) component named in the project title remained a design concept and was not implemented under this award. The Massachusetts Institute of Technology (MIT) group led the offline simulation and data processing needed to train the machine-learning (ML) models, the translation of trained models to Field-Programmable Gate Array (FPGA) firmware using the hls4ml framework, and the physics validation of heavy-flavor reconstruction. Over the award period, the team developed and hardware-tested the principal components of an AI-based heavy-flavor trigger on simulated and recorded sPHENIX tracker data: a software Bipartite Graph Attention Network (BiGAT) trigger model reaching > 95% signal efficiency at 99% background rejection; an FPGA-native hit clusterizer matching the offline clustering; smaller networks synthesized to FPGA within the required sub-10 µs latency; and an assembled decoder–clusterizer–inference firmware chain exercised on the FELIX readout board. A complete, fully integrated hardware demonstrator was not finished within the award period. This report documents the project goals, the MIT group’s contributions, the technical accomplishments, and the outlook toward applications at the future EIC ePIC detector.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Semi-Supervised Novelty Detection with Adaptive Eigenbases, and Application to Radio Transients

We present a semi-supervised online method for novelty detection and evaluate its performance for radio astronomy time series data. Our approach uses adaptive eigenbases to combine 1) prior knowledge about uninteresting signals with 2) online estimation of the current data properties to enable highly sensitive and precise detection of novel signals. We apply the method to the problem of detecting fast transient radio anomalies and compare it to current alternative algorithms. Tests based on observations from the Parkes Multibeam Survey show both effective detection of interesting rare events and robustness to known false alarm anomalies.

anomaly detection↗

NeMO-Net - The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment

In the past decade, coral reefs worldwide have experienced unprecedented stresses due to climate change, ocean acidification, and anthropomorphic pressures, instigating massive bleaching and die-off of these fragile and diverse ecosystems. Furthermore, remote sensing of these shallow marine habitats is hindered by ocean wave distortion, refraction and optical attenuation, leading invariably to data products that are often of low resolution and signal-to-noise (SNR) ratio. However, recent advances in UAV and Fluid Lensing technology have allowed us to capture multispectral 3D imagery of these systems at sub-cm scales from above the water surface, giving us an unprecedented view of their growth and decay. By combining spatial and spectral information from varying resolutions, we seek to augment and improve the classification accuracy of previously low-resolution datasets at large temporal scales.NeMO-Net, the first open-source deep convolutional neural network (CNN) and interactive learning and training software, currently being developed at NASA Ames, is aimed at assessing the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology. The latest iteration uses fully convolutional networks to segment and identify coral imagery taken by UAVs and satellites, including WorldView-2 and Sentinel. We present results taken from the Indian Ocean where classification accuracy has exceeded 91% for 24 geomorphological classes given ample training data. In addition, we utilize deep Laplacian Pyramid Super-Resolution Networks (LapSRN) to reconstruct high resolution information from low resolution imagery, trained from various UAV and satellite datasets. Finally, in the case of insufficient training data, we have developed an interactive online platform that allows users to easily segment and submit their classifications, which has been integrated with the current NeMO-Net workflow. Specifically, we present results from the Fiji islands in which preliminary user data has allowed for the accurate identification of 9 separate classes, despite issues such as cloud shadowing and spectral variation. The project is being supported by NASA's Earth Science Technology Office (ESTO) Advanced Information Systems Technology (AIST-16) Program.

Neural↗

Stuff- The Materials that Shape our World - Experimental Learning Opportunities

Making Stuff is a four-part series that explores how materials changed history and are shaping the future. To further enhance public engagement in and understanding of materials science, the project convened an extensive network of community coalitions across the country that hosted Making Stuff outreach activities and events, science cafes, and educator workshops in their local areas. Department Of Energy funding enabled us to increase the number of communities formally involved in the project, from 10 to 20 community hubs. Department of Energy funding also made it possible to develop a collection of materials science resources, activities and hands-on demonstrations for use in a variety of formal and informal settings, and Making Stuff activities were presented at science conferences and festivals around the country. The design, printing and national dissemination of the Making Stuff afterschool activity guide were also developed with DOE funding, as well as professional webinar trainings for scientists and educators to help facilitate many of the community activities and other online and print materials. Thanks to additional funding from the Department of Energy, we were able to expand the reach and scope of the project's outreach plan, specifically in the areas of: 1) content development, 2) training/professional development, 3) educational activities and 4) community partnerships. This report documents how the following DOE project goals were met: (1) Train scientists and provide teachers and informal educators with resources to engage youth with age appropriate information about materials science; (2) Provide activities and resources to five selected communities with ties to DOE researchers; (3) Increase interest in STEM.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Distributed Reinforcement Learning with ADMM-RL

NREL researcher Peter Graf discusses distributed reinforcement learning with ADMM-RL as part of the Innovative Optimization and Control Methods for Highly Distributed Autonomous Systems workshop. NREL hosted the workshop to exchange ideas on state-of-the-art control and optimization strategies as well as get feedback on work being done at NREL.

97 MATHEMATICS AND COMPUTING↗

Investigating the interconnectedness of active transportation and public transit usage as a primer for Mobility-as-a-Service adoption and deployment

With the advent of Mobility-as-a-Service packages to reduce car usage and (by extension) greenhouse gas emissions, it is crucial that researchers and practitioners consider mutual determinants and outcomes that link the adoption of multiple alternative modes. This study therefore investigates the joint usage of active travel (walking, cycling, bike-sharing) and public transit (bus, rail) modes with respect to personal and situational contexts. Online survey data (n = 826) were collected across six Midwestern U.S. states using Amazon MTurk. Respondents indicated their average weekly usage of eight travel modes across three trip purposes so that multimodality could be assessed. Several psychological constructs were extracted via (a) the stages of change framework, used to indicate willingness to adopt new behavior, and (b) confirmatory factor analysis conducted on Likert scales rooted in theories of community, identity, norms, personality, and well-being. A multiple-indicators multiple-causes structural equation model is then employed to investigate the process of adopting a modality style that incorporates active and transit modes. The model confirms that compatible physical and social contexts, as well as navigational skills and openness to learning, are key primers of multimodalism. However, a path juncture stemming from neighborhood support for mobility innovation illustrates a potential polarity in outcomes between individuals and communities. In addition, the stage of active mobility adoption is linked to identity and norm activation, offering further guidance on what influences readiness for change. The seamless integration of mobility services is critical to matching the convenience and comfort of the private vehicle; understanding potential pathways to sustainable mobility, though, requires analyses and interventions that are driven by well-being outcomes and grounded in rigorous psychological frameworks. Here, the research findings offer practical guidance for identifying intervention opportunities to be linked with MaaS enrollment while demonstrating the need to illuminate how mobility might relate to social cohesion, identity expression, and various sources of satisfaction.

42 ENGINEERING↗

A Three-fold Outlook of the Ultra-Efficient Engine Technology Program Office (UEET)

The Ultra-Efficient Engine Technology (UEET) Office at NASA Glenn Research Center is a part of the Aeronautics Directorate. Its vision is to develop and hand off revolutionary turbine engine propulsion technologies that will enable future generation vehicles over a wide range of flight speeds. There are seven different technology area projects of UEET. During my tenure at NASA Glenn Research Center, my assignment was to assist three different areas of UEET, simultaneously. I worked with Kathy Zona in Education Outreach, Lynn Boukalik in Knowledge Management, and Denise Busch with Financial Management. All of my tasks were related to the business side of UEET. As an intern with Education Outreach I created a word search to partner with an exhibit of a Turbine Engine developed out of the UEET office. This exhibit is a portable model that is presented to students of varying ages. The word search complies with National Standards for Education which are part of every science, engineering, and technology teachers curriculum. I also updated a Conference Planning/Workshop Excel Spreadsheet for the UEET Office. I collected and inputted facility overviews from various venues, both on and off site to determine where to hold upcoming conferences. I then documented which facilities were compliant with the Federal Emergency Management Agency's (FEMA) Hotel and Motel Fire Safety Act of 1990. The second area in which I worked was Knowledge Management. a large knowledge management system online which has extensive documentation that continually needs reviewing, updating, and archiving. Knowledge management is the ability to bring individual or team knowledge to an organizational level so that the information can be stored, shared, reviewed, archived. Livelink and a secure server are the Knowledge Management systems that UEET utilizes, Through these systems, I was able to obtain the documents needed for archiving. My assignment was to obtain intellectual property including reports, presentations, or any other documents related to the project. My next task was to document the author, date of creation, and all other properties of each document. To archive these documents I worked extensively with Microsoft Excel. different financial systems of accounting such as the SAP business accounting system. I also learned the best ways to present financial data and shadowed my mentor as she presented financial data to both UEET's project management and the Resources Analysis and Management Office (RAMO). I analyzed the June 2004 financial data of UEET and used Microsoft Excel to input the results of the data. This process made it easier to present the full cost of the project in the month of June. In addition I assisted in the End of the Year 2003 Reconciliation of Purchases of UEET.

Graham, La Quilia E.↗

Exploring and Analyzing Climate Variations Online by Using NASA MERRA-2 Data at GES DISC

NASA Giovanni (Goddard Interactive Online Visualization ANd aNalysis Infrastructure) (http:giovanni.sci.gsfc.nasa.govgiovanni) is a web-based data visualization and analysis system developed by the Goddard Earth Sciences Data and Information Services Center (GES DISC). Current data analysis functions include Lat-Lon map, time series, scatter plot, correlation map, difference, cross-section, vertical profile, and animation etc. The system enables basic statistical analysis and comparisons of multiple variables. This web-based tool facilitates data discovery, exploration and analysis of large amount of global and regional remote sensing and model data sets from a number of NASA data centers. Long term global assimilated atmospheric, land, and ocean data have been integrated into the system that enables quick exploration and analysis of climate data without downloading, preprocessing, and learning data. Example data include climate reanalysis data from NASA Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2) which provides data beginning in 1980 to present; land data from NASA Global Land Data Assimilation System (GLDAS), which assimilates data from 1948 to 2012; as well as ocean biological data from NASA Ocean Biogeochemical Model (NOBM), which provides data from 1998 to 2012. This presentation, using surface air temperature, precipitation, ozone, and aerosol, etc. from MERRA-2, demonstrates climate variation analysis with Giovanni at selected regions.

knowledge base↗

Misleading or Falsification? Inferring Deceptive Strategies and Types in Online News and Social Media

Deceptive information in online news and social media has had dramatic effect on our society in recent years. This study is the first to gain deeper insights into writers' intent behind digital misinformation by analyzing psycholinguistic signals: moral foundations and connotations extracted from different types of deceptive news ranging from strategic disinformation to propaganda and hoaxes. To ensure consistency of our findings and generalizability across domains, we experiment with data from: (1) confirmed cases of disinformation in news summaries, (2) {propaganda}, hoax, and disinformation news pages, and (3) social media news. We first contrast lexical markers of biased language, syntactic and stylistic signals, and connotations across deceptive news types including disinformation, propaganda, and hoaxes, and {deceptive} strategies including misleading or falsification. We then incorporate these insights to build machine learning and deep learning predictive models to infer deception strategies and deceptive news types. Our experimental results demonstrate that unlike earlier work on deception detection, content combined with biased language markers, moral foundations, and connotations leads to better predictive performance of deception strategies compared to syntactic and stylistic signals (as reported in earlier work on deceptive reviews). Falsification strategy is easier to identify than misleading strategy. Disinformation is more difficult to predict than to propaganda or hoaxes. Deceptive news types (disinformation, propaganda, and hoaxes), unlike deceptive strategies (falsification and misleading), are more salient, and thus easier to identify in tweets than in news reports. Finally, our novel connotation analysis across deception types provides deeper understanding of writers' perspectives and therefore reveals the intentions behind digital misinformation.

deception↗

The CNSC's Inspector Training and Qualification Program and its Importance to the Nuclear Industry - 19370

Trained, qualified, and designated staff at the Canadian Nuclear Safety Commission (CNSC) conduct inspections of licensed nuclear sites as a method of compliance verification. This paper will describe the unique and comprehensive qualification process for CNSC inspectors, known as the Inspector Training and Qualification Program (ITQP). The ITQP includes service-line-specific training that is unique to each inspection group within the CNSC, dependent on the facility/industry type. The training requirements specific to staff in the Wastes and Decommissioning Division and its impact on safety at waste management sites across Canada will be discussed. This paper will specifically identify the importance of CNSC inspector training and detail how the unique training program requirements enable the CNSC to better identify and encourage compliance among nuclear waste and decommissioning sites in Canada. CNSC inspectors are designated under section 29 of the Nuclear Safety and Control Act (NSCA), and the powers of inspectors are outlined in section 32 of the NSCA. Having trained, qualified, and designated inspectors is paramount for both the CNSC and the nuclear industry. For the CNSC, this ensures that staff in the field are aware of potential hazards and how to mitigate such hazards (if applicable), that staff understand the regulatory framework and how to measure compliance against it, and that staff consistently apply CNSC values across the nuclear industry. For the industry, this ensures that staff present at nuclear facilities are knowledgeable and professional, that inspections are conducted in a consistent manner, and that any compliance actions issued are measurable and defendable against the regulatory framework. The CNSC's ITQP incorporates both theoretical (in-class and online) and practical training, and is broken down into six categories: mandatory training for all new employees; core training; service-line-specific training; on-the-job training; CNSC regulations training; and, recommended additional training. This paper will discuss in detail the specific aspects of each of these categories, the importance of each category including the difference between knowledge and skills acquired in theoretical versus hands-on training, and how CNSC staff in designated inspector positions (inspectors-in-training) progress through the program. The complete list of core training and service-line-specific training for inspectors in the Wastes and Decommissioning Division, including re-qualification requirements, will be explored throughout the paper. It is further important that CNSC designated inspectors undergo continuous learning to ensure that their skills remain up to date, as well as to ensure that inspectors requalify at defined intervals to enable the maintenance of the core knowledge and skills with which the determination of the person's qualification was based. The steps involved in this requalification process, as well as the importance of continuous learning and the maintenance of skills and knowledge will be further discussed. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Intervening alcohol marketing to reduce harmful alcohol use and lessons learned from the theory of changes: Case studies in Thailand

Objectives Globally, the burden of disease caused by alcohol use has been steadily increasing, including in Thailand. In this study, we aim to test the effectiveness of Anderson et al.‘s suggested three approaches to change the collective social norms, which comprise of: (1) providing information and an understanding about alcohol use behaviour, its causes and distribution; (2) focusing strategies on groups rather than individuals; and (3) strengthening supportive laws, regulations and approaches. Study design We employed a mixed-methods approach. Evidence was gathered from literature review and in-depth interviews with key individuals who are responsible for community-based interventions to alcohol marketing strategies in Thailand. Methods We chose to focus on two case studies in Nan and Surin provinces, where hospital-based longitudinal data (8 years) were available. Changes in casualties related to the harmful use of alcohol, resulting from interactions between community-based interventions and alcohol marketing during the time of annual festivals were investigated. We employed the theory of change (ToC) defined by Vogel to guide the data collection and analysis. We reviewed literature from online databases and grey literature to generate causal-loop diagrams. Results We created a causal-loop diagram to describe the complexity of harmful alcohol use, its related factors, context, interventions and outcomes. Over the decade between 2006 and 2015, community-based strategies led to a substantial reduction of casualties (initially a 50% reduction, rising to an 80–90% reduction by the end of the study period) during the time of the festivals. Conclusions The reduction in injuries and fatalities could be a result of the concerted actions, including legal sanctions of alcohol beverage sales and advertisement, and public education to raise awareness and impart knowledge of the harmful use of alcohol. The actions were organised by a coalition of civil society, health professionals, public authorities and community leaders using hospital-based data on the adverse effects of harmful alcohol use to mobilise political support at the provincial level. The availability of long-term financial support as a catalytic source of funds and the presence of a comprehensive alcohol control act enabled framing and mobilisation of local resources and political support.

60 APPLIED LIFE SCIENCES↗

Method for Hot Real-Time Sampling of Pyrolysis Vapors

Biomass Pyrolysis has been an increasing topic of research, in particular as a replacement for crude oil. This process utilizes moderate temperatures to thermally deconstruct the biomass which is then condensed into a mixture of liquid oxygenates to be used as fuel precursors. Pyrolysis oils contain more than 400 compounds, up to 60 percent of which do not re-volatilize for subsequent chemical analysis. Vapor chemical composition is also complicated as additional condensation reactions occur during the condensation and collection of the product. Due to the complexity of the pyrolysis oil, and a desire to catalytically upgrade the vapor composition before condensation, online real-time analytical techniques such as Molecular Beam Mass Spectrometry (MBMS) are of great use. However, in order to properly sample hot pyrolysis vapors, many challenges must be overcome. Sampling must occur within a narrow range of temperatures to reduce product composition changes from overheating or partial condensation or plugging of lines from condensed products. Residence times must be kept at a minimum to reduce further reaction chemistries. Pyrolysis vapors also form aerosols that are carried far downstream and can pass through filters resulting in build-up in downstream locations. The co-produced bio-char and ash from the pyrolysis process can lead to plugging of the sample lines, and must be filtered out at temperature, even with the use of cyclonic separators. A practical approach for considerations and sampling system design, as well as lessons learned are integrated into the hot analytical sampling system of the National Renewable Energy Laboratory's (NREL) Thermochemical Process Development Unit (TCPDU) to provide industrially relevant demonstrations of thermochemical transformations of biomass feedstocks at the pilot scale.

09 BIOMASS FUELS↗

Machine learning predicts new anti-CRISPR proteins

The increasing use of CRISPR–Cas9 in medicine, agriculture, and synthetic biology has accelerated the drive to discover new CRISPR–Cas inhibitors as potential mechanisms of control for gene editing applications. Many anti-CRISPRs have been found that inhibit the CRISPR–Cas adaptive immune system. However, comparing all currently known anti-CRISPRs does not reveal a shared set of properties for facile bioinformatic identification of new anti-CRISPR families. Here, we describe AcRanker, a machine learning based method to aid direct identification of new potential anti-CRISPRs using only protein sequence information. Using a training set of known anti-CRISPRs, we built a model based on XGBoost ranking. We then applied AcRanker to predict candidate anti-CRISPRs from predicted prophage regions within self-targeting bacterial genomes and discovered two previously unknown anti-CRISPRs: AcrllA20 (ML1) and AcrIIA21 (ML8). We show that AcrIIA20 strongly inhibits Streptococcus iniae Cas9 (SinCas9) and weakly inhibits Streptococcus pyogenes Cas9 (SpyCas9). We also show that AcrIIA21 inhibits SpyCas9, Streptococcus aureus Cas9 (SauCas9) and SinCas9 with low potency. The addition of AcRanker to the anti-CRISPR discovery toolkit allows researchers to directly rank potential anti-CRISPR candidate genes for increased speed in testing and validation of new anti-CRISPRs. A web server implementation for AcRanker is available online at http://acranker.pythonanywhere.com/.

59 BASIC BIOLOGICAL SCIENCES↗

Early Alarm: Robust Event Analysis for Power Systems using 1-D Fully Convolutional Network

This work presents a novel deep learning model for early, accurate, and robust detection, recognition, and temporal localization of multi-type events in large-scale power systems. The proposed method develops a unified 1-D fully convolutional network (FCN) model that takes time series of raw frequency signals measured from a power system as input, extracts distinguishing features, and predicts at every temporal point in the time series if an event is happening and what the type of the event is. Compared to existing methods, the proposed model eliminates the necessity for hand-crafted feature extraction or complicated data pre-processing, can flexibly handle input signals of arbitrary length, and precisely infer the event occurrence time. Most importantly, the model is intentionally trained with incomplete patterns, such that it is more robust to partial features of an event which is common in real-world online recognition, resulting in early alarm for power system failures. Extensive experimental results demonstrate that the proposed method achieves superior performance to the state-of-the-art, and also shows strong robustness to noise and system oscillations.

Li, Chengcheng↗

2011 Performance Assessment Community of Practice Technical Exchange – Summary

The Performance Assessment Community of Practice (PA CoP) was developed in 2008 to improve consistency and quality in the preparation of performance assessments (PAs) and risk assessments across the Department of Energy (DOE) Complex. The term, PA, is used to represent all of these modeling applications in this report. The PA CoP goals are to foster the exchange of information among PA practitioners and to share lessons learned from PAs conducted for DOE, commercial disposal facilities, and international entities. Technical exchanges and workshops are a cornerstone of PA CoP activities. Previous technical exchanges have addressed Engineered Barriers (2009 - http://www.cresp.org/education/workshops/pacop/), the Advanced Simulation Capability for Environmental Management and the Cementitious Barriers Partnership (2010 - http://srnl.doe.gov/copexchange/links.htm). Each technical exchange also includes summary presentations regarding activities at DOE, the Nuclear Regulatory Commission (NRC) and other organizations (e.g., International Atomic Energy Agency (IAEA)) as well as a number of presentations from selected sites to provide insight and perspective from on-going modeling activities. Through the deployment of PA Assistance Teams, the PA CoP has also been engaged in the development of new PAs across the DOE Complex. As a way of improving consistency in the preparation of new PAs, the teams provide technical advice and share experiences, noteworthy practices, and lessons learned from previous Low-Level Waste Disposal Facility Federal Review Group (LFRG) reviews. Teams have provided support for PAs at Hanford, Idaho, Paducah and Portsmouth. The third annual PA CoP Technical Exchange was held on May 25-26, 2011 in Atlanta, GA. The PA CoP Steering Committee Meeting held its first meeting on May 24 prior to the Technical Exchange. Decision making using models and software quality assurance were the topical emphasis for the exchange. A new feature at the 2011 technical exchange was the use of panel discussions to solicit feedback from regulators and practitioners. This report summarizes discussions and recommendations from the steering committee meeting and presentations and feedback obtained at the technical exchange. Appendix I includes the steering committee meeting agenda and Appendix II includes the agenda for the technical exchange and a screenshot of the presentations and video files that are available online.

99 GENERAL AND MISCELLANEOUS↗

Predicting departure from nucleate boiling with advanced data- and physics-driven approaches

The subcooled and low-quality saturated flow boiling critical heat flux (CHF) corresponding to the departure from nucleate boiling (DNB) is one of the major limiting factors in the design and operation of pressurized water reactors (PWRs). Due to lack of agreement on its physical mechanisms, development of an accurate DNB-type CHF model has been elusive. The various steady-state (SS) predictive tools that have been proposed can be grouped into two categories: (1) data-driven methods—namely best-fit empirical correlations and look-up tables that result in relatively good agreement with specific experimental datasets but often fail to extend beyond their ranges of validity, and (2) the physics-based mechanistic models that rely on reasonable yet limited understanding of the underlying physics and apply constitutive relations to close the conservation equations. On one hand, with recent advances in computational capabilities and optimization techniques, machine learning (ML)-based methods constitute an alternative and a more advanced, data-driven approach. With enough data, they can be particularly useful in engineering fields where the physical phenomena are complex and challenging to model. On the other hand, a state-of-the-art physics-driven approach would not only provide more accurate prediction of SS CHF, but it would also help better understand and model transient applications. The data-driven regression models use deep feed-forward neural networks (NNs) and random forests to cross-validate with 1,865 CHF test cases, covering a wide range of flow conditions and channel geometries. The best-estimate ML-based predictors compare favorably with the widely used look-up table for annulus and plate, and sensitivity analysis has confirmed their effectiveness. The key advantage of ML-based methods is their online extensibility of applicability domain. The proposed physics-driven approach combines key assumptions and parameters in the relatively well-accepted theories of liquid sublayer dryout and near-wall bubble crowding. A more realistic understanding of local mechanisms has been modeled. The new model has been optimized and validated against 1,439 tube data, and it shows considerably improved performance when compared to a recent mechanistic model, demonstrating unbiased close agreement with measurements over a wide range of operating conditions. Future work will extend the improved physics-driven model to non-tube geometry applications and will couple the model with ML via a hybrid approach. The mechanistic SS work will also serve to improve understanding and to model transient CHF scenarios.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

NASA POWER: Providing Analysis-Ready, Cloud-Optimized Data for AI /ML Training and Applications in Earth Science

As global demand for sustainable development grows, the integration of Earth Observation (EO) data into decision making frameworks has become a primary objective for the scientific community. The NASA Prediction of Worldwide Energy Resources (POWER) project serves as a bridge between NASA EO data and the specialized needs of the renewable energy, sustainable infrastructure and agroclimatology communities. In this poster presentation we will present an overview of POWER data products and services along with its use in diverse research to decision-making workflows. By providing over 40 years of high-resolution historical, hourly and daily solar and meteorological data, POWER transforms satellite observations and global model reanalysis into actionable, Analysis-Ready Dataset (ARD). Currently, the project delivers over 250 industry-friendly parameters to the users from different NASA datasets like CERES SYN1Deg, MERRA-2, and IMERG alongside downscaled CMIP6 climate model data, fulfilling over 16 million requests from 50,000 unique users monthly. To ensure data quality and traceability, these parameters are rigorously validated against the ground-based observations from the Baseline Surface Radiation Network (BSRN) and the Global Surface Summary of the Day (GSOD) – these results will be discussed in the presentation. A newly introduced web-based PaRameter Uncertainty ViEwer (PRUVE) tool will be presented that provides an online validation platform to the users that benchmarks satellite-based and assimilation data products against these surface measurements. To reduce technical barriers to data adoption, POWER data is accessible through RESTful APIs, ESRI ArcGIS Image Services, a web-based Data Access Viewer tool, allowing users to visualize, validate and apply the dataset. For efficient data delivery POWER data is cloud-optimized into Zarr datastore accessible through NASA managed Amazon S3 ensures high-performance allowing users to integrate EO directly into operational pipelines. These customized services will be presented. Use cases from application will be presented from the energy sector - such as for design of generation systems, performance monitoring of solar power plants, in infrastructure sector- optimizing building energy efficiency and thermal comfort, in agriculture – such as driving crop simulation and yield forecasting models to enable climate resilient farming. Furthermore, the shift toward machine learning (ML) in EO research that has positioned POWER as a key provider for training datasets which will be discussed. Use-cases will be presented to showcase how NASA data is enabling the development of predictive tools for climate variability and resource management. The poster will present POWER’s future plans including technology development to enhance data traceability and reproducibility and improving I/O performance to support the rapid integration of new EO products, ensuring that POWER remains a robust scalable backend for the evolving landscape of AI-driven Earth Science. Additionally, POWER is developing an AI Agent and an MCP-Server to enable industry AI-Agentic workflows.

Neha Khadka↗

Distributive On-line Processing, Visualization and Analysis System for Gridded Remote Sensing Data

The ability to use data stored in the current Earth Observing System (EOS) archives for studying regional or global phenomena is highly dependent on having a detailed understanding of the data's internal structure and physical implementation. Gaining this understanding and applying it to data reduction is a time- consuming task that must be undertaken before the core investigation can begin. This is an especially difficult challenge when science objectives require users to deal with large multi-sensor data sets that are usually of different formats, structures, and resolutions, for example, when preparing data for input into modeling systems. The NASA Goddard Earth Sciences Data and Information Services Center (GES DISC) has taken a major step towards meeting this challenge by developing an infrastructure with a Web interface that allows users to perform interactive analysis online without downloading any data, the GES-DISC Interactive Online Visualization and Analysis Infrastructure or "Giovanni." Giovanni provides interactive, online, analysis tools for data users to facilitate their research. There have been several instances of this interface created to serve TRMM users, Aerosol scientists, Ocean Color and Agriculture applications users. The first generation of these tools support gridded data only. The user selects geophysical parameters, area of interest, time period; and the system generates an output on screen in a matter of seconds. The currently available output options are: Area plot averaged or accumulated over any available data period for any rectangular area; Time plot time series averaged over any rectangular area; Time plots image view of any longitude-time and latitude-time cross sections; ASCII output for all plot types; Image animation for area plot. In the future, we will add correlation plots, GIS-compatible outputs, etc. This allow user to focus on data content (i.e. science parameters) and eliminate the need for expensive learning, development and processing tasks that are redundantly incurred by an archive's user community. The current implementation utilizes the GrADS-DODS Server (GDS), a stable, secure data server that provides subsetting and analysis services across the Internet for any GrADS-readable dataset. The subsetting capability allows users to retrieve a specified temporal and/or spatial subdomain from a large dataset, eliminating the need to download everything simply to access a small relevant portion of a dataset. The analysis capability allows users to retrieve the results of an operation applied to one or more datasets on the server. In our case, we use this approach to read pre-processed binary files and/or to read and extract the needed parts from HDF or HDF-EOS files. These subsets then serve as inputs into GrADS processing and analysis scripts. It can be used in a wide variety of Earth science applications: climate and weather events study and monitoring; modeling. It can be easily configured for new applications.

Leptoukh, G.↗