Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network regularization”

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 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
NASA NTRS2001

Implementation of a General Real-Time Visual Anomaly Detection System Via Soft Computing

The intelligent visual system detects anomalies or defects in real time under normal lighting operating conditions. The application is basically a learning machine that integrates fuzzy logic (FL), artificial neural network (ANN), and generic algorithm (GA) schemes to process the image, run the learning process, and finally detect the anomalies or defects. The system acquires the image, performs segmentation to separate the object being tested from the background, preprocesses the image using fuzzy reasoning, performs the final segmentation using fuzzy reasoning techniques to retrieve regions with potential anomalies or defects, and finally retrieves them using a learning model built via ANN and GA techniques. FL provides a powerful framework for knowledge representation and overcomes uncertainty and vagueness typically found in image analysis. ANN provides learning capabilities, and GA leads to robust learning results. An application prototype currently runs on a regular PC under Windows NT, and preliminary work has been performed to build an embedded version with multiple image processors. The application prototype is being tested at the Kennedy Space Center (KSC), Florida, to visually detect anomalies along slide basket cables utilized by the astronauts to evacuate the NASA Shuttle launch pad in an emergency. The potential applications of this anomaly detection system in an open environment are quite wide. Another current, potentially viable application at NASA is in detecting anomalies of the NASA Space Shuttle Orbiter's radiator panels.

Dominguez, Jesus A.↗
NASA NTRSDate not supplied

Validation of Remotely Sensed and Modeled Soil Moisture at Forested and Unforested Sites

Soil moisture is an important driver for forest ecosystems, influencing fire occurrence and extent, insect and pathogen impacts, and tree growth, which creates a need for regular, globally extensive soil moisture information that only satellite-based sensors or models can achieve. However, the reliability of soil moisture measurements in forests is not well understood due to a lack of suitable validation sites (especially relative to unforested ecosystems) and interference caused by high vegetation water content on remotely sensed measurements; although recent studies have started to address this gap [1], [2], [3], [4]. Here we validate the performance of multiyear remotely sensed (SMAP/Sentinel), remotely sensed data assimilation modelled (SMAP-L4), and modelled (NLDAS) surface and root zone (0-1 m) soil moisture datasets with data from in-situ sensors at 39 National Ecological Observatory Network (NEON) sites throughout the contiguous US. Due to differences in spatial resolution, NEON soil moisture (~0.2 km measurement zone) correlations were expected to be stronger with the SMAP/Sentinel product (3 km resolution) than with coarser resolution SMAP-L4 (9 km resolution) or NLDAS products (13 km resolution). However, given the sensitivity of satellite measurements to vegetation water content we expected a deterioration in the correlations based on remotely sensed measurements (SMAP/Sentinel and SMAP-L4) as aboveground biomass increased, whereas the model-based data (NLDAS) was expected to be largely insensitive to vegetation type. We recognize that the SMAP/Sentinel product was developed for unforested regions, therefore our application is outside its primary use case. Soil moisture is measured at up to 8 depths in five soil plots spaced up to 40 m apart at each NEON terrestrial site. Correlation parameters were calculated for the three remotely sensed and modelled data products relative to in-situ measurement following Entekhabi et al. [5]. The datasets comprised 94 (SMAP-L4), 28 (SMAP/Sentinel), and 106 (NLDAS) sites-years for surface soils and 13 (SMAP-L4) and 14 (NLDAS) site-years for the root zone. At unforested sites, the performance of the three remotely sensed and modelled data products was similar for surface soils (Table 1). For example, unbiased RMSD (ubRMSD), which SMAP uses as its primary performance metric [6], ranged from 0.05 to 0.06 m3 m-3 (Table 1), indicating the ability of all three products to track changes in soil moisture over time. The performance of the three products deteriorated at forested sites, however, while the difference in performance was modest for SMAP-L4 and NLDAS, the deterioration in SMAP/Sentinel performance was substantial. For instance, SMAP/Sentinel ubRMSD increased from 0.06 to 0.11 m3 m-3 and absolute mean difference (Abs MD; which includes measurement bias and spatial representativeness errors) increased from 0.06 to 0.16 m3 m-3, indicating both a reduction in ability to track temporal changes and absolute amounts of soil moisture in forest ecosystems. SMAP-L4 and NLDAS had lower unbiased RMSD for root zone (0-1 m) than surface soils at both forested and unforested sites (Tables 1 and 2; SMAP/Sentinel does not produce a root zone measurement). However, in most cases the correlation coefficient (r) was lower for the root zone than surface soils, suggesting the lower unbiased RMSD may be attributed to greater temporal stability of soil moisture in the root zone rather than improved data product performance. Mean difference and absolute mean difference, which encompass measurement bias and spatial representativeness errors, were greater for root zone than surface soils at unforested sites for both data products, but the opposite was generally true at forested sites. As with surface soils, there was relatively little change in the performance of SMAP-L4 and NLDAS between the unforested and forested sites. In summary, all three data products were able to adequately represent soil moisture at unforested sites, at least when aggregating across sites. However, while the performance of all three products deteriorated at forested sites, SMAP-L4 and NLDAS maintained sufficient performance to remain suitable for some use cases (ubRMSD <0.06 m3 m-3 and RMSD <0.13 m3 m-3). In contrast, the relatively poorer performance of the SMAP/Sentinel product at forested sites seems insufficient for most use cases (ubRMSD >0.1 m3 m-3 and RMSD >0.2 m3 m-3). We attribute the large reduction in the performance of the SMAP/Sentinel product in forests to its use of C-band wavelengths, which are particularly sensitive to vegetation interference, and apparently outweighed any gains provided by its higher spatial resolution. A combined SMAP/NISAR soil moisture product may provide improved performance relative to SMAP/Sentinel due to NISAR’s use of L-band wavelengths, which are less sensitive to vegetation (NISAR is scheduled for launch in early 2024).

Edward Ayres↗
NASA NTRSDate not supplied

An Evening with NASA Scientists and Engineers: A Senior Living Community Outreach Program

Introduction: An Evening with NASA Scientists and Engineers is an outreach program for senior living communities, where participants learn from and interact with a scientist or engineer in a virtual setting. Participants learn about NASA science and engineering through a behind-the-scenes look from the people who work at NASA. The program focuses on both the stories behind the discoveries and the stories behind the people. The audience tunes in to the events via the NASA Zoom Webinar platform, where they have the opportunity to ask questions throughout the approximately 30-minute program. By bringing the audience into the conversation, we build rapport and thus improve their connection with NASA. Overview: An Evening with NASA Scientists and Engineers began in September 2020 when we identified a need for outreach to this particular demographic, as senior living communities had been hit especially hard by the COVID-19 pandemic. The program covers a wide range of topics, including heliophysics, astrophysics, planetary science, Earth science, planetary defense, and more, depending on what is topically appropriate at the time, and occurs on a roughly monthly basis. Each interactive presentation is between 20-25 minutes with 5-10 minutes of dedicated Q&A. Future dates and topics may change depending on new developments to NASA missions and stories. Audience: As of December 2021, we have four regularly attending senior living communities, spanning the East Coast from New Hampshire to Florida, with each joining the overall program at various stages of its development. The ability to reach many different senior living communities is crucial so that a diversity of people may benefit from this program. The audience consists of seniors with varying experience and comprehension levels – some are very familiar with the sciences while others are simply curious to learn more. Residents tune in to each event from their individual rooms or from their larger community rooms. RiverWoods Exeter. The RiverWoods Exeter community was our initial audience who acted as our “guinea pig” to see how this program might be implemented and to work out any major issues. They are located in Exeter, NH but also have two additional campuses in Durham, NH and Manchester, NH, that joined us a few months into the program. Culpepper Garden. Our second community to join the program was Culpepper Garden, a senior living community in Arlington, VA that provides both independent and assisted living housing to low-income seniors. Edinburgh Square. Our third community, Edinburgh Square, connected with us after hearing about the program through Culpepper Garden. Edinburgh Square is an HUD-subsidized retirement community in Roanoke, VA that houses both seniors and those living with disabilities. Moonstruck Astronomy Club. The Moonstruck Astronomy Club consists of residents from the On Top of the World retirement community in Ocala, FL and was the latest senior living community to join us. NASA Zoom Webinar: An Evening with NASA Scientists and Engineers reaches numerous senior living communities through live presentations that we host using the NASA Zoom Webinar virtual platform. Participants are typically already familiar with the Zoom platform which enables a lower barrier to entry. A recording of each talk is added to a designated video playlist on the NASA STEM YouTube channel so that audiences worldwide may view them [1]. These recordings began with our April 1, 2021 presentation, as this was when NASA Zoom Webinar was implemented, thus enabling us to record each talk. Metrics: We record attendance numbers from the senior living communities for each event as well as those from YouTube views after the presentation recording is posted online. Depending on which communities tune in, typical attendance numbers are between 60-100 people. RiverWoods Exeter has the most regularly attending residents, with an average of 55 attendees per event. As of December 2021, we have hosted fourteen events, nine of which were recorded and posted to our designated NASA STEM YouTube Channel playlist. The nine recordings combined have roughly 4,000 YouTube views thus far, with specific videos seeing higher view counts around launch dates (e.g. NASA’s DART mission) and trending topics (e.g. JWST). A list of speakers, topics, and links to presentation recordings is shown in Table 1. Future Program Expansion: Thus far, we have been adding communities on an individual basis. To make this process more streamlined, we are looking into working with senior living community networks and organizations such as LeadingAge [2]. In this manner, we will be able to reach more communities while also making it easier to send and receive relevant information.

S L Tiedeken↗
DOE OSTI2022

ACES: Infrastructure As Code. Model Optimization and Performance Capability

Infrastructure as Code (IaC) refers to managing infrastructure (networks, physical/virtual machines, storage, and connection topology) in a descriptive model/language, rather than configuring it manually or using interactive configuration tools. Just like source code can be compiled to generate the same binary code, IaC enables generating the same environment every time it is applied. IaC is a key DevOps practice and is generally used in conjunction with continuous integration (CI) and continuous delivery (CD). In CI, all code changes are merged into a mainline branch and validated multiple times a day as developers check in their changes to the source code. In CD on the other hand, code changes are automatically packaged for a new release-to-production on a regular basis. This typically enables teams to deliver software changes much more quickly and often. Developing and managing the ACES platform using (IaC) is vital for the robust deployment and continued sustainment of this foundational computing capability. IaC and DevOps practices will help us solve many of the common challenges often encountered in developing and maintaining compute infrastructure. First, it will make the provisioning, deployment, and maintenance of the compute infrastructure across multiple environments much more efficient. Second, these processes help make the overall system much more stable by continuously testing new changes as they are introduced to the system. Third, it allows us to be much more confident of the security controls in place since they can be tested as part of the CI process and all new changes can be audited and tracked. Finally, IaC enables the ACES Platform to be adaptable to the emerging technologies due to its ability to spin up different test beds to evaluate and incorporate these technologies. This document addresses common infrastructure-management challenges, describes what happens if they are not addressed, and highlights the value of utilizing IaC to tackle them. Finally, we will provide a high-level overview of the IaC and DevOps practices being utilized by the ACES Platform team.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1992

Remote Earth Sciences data collection using ACTS

Given the focus on global change and the attendant scope of such research, we anticipate significant growth of requirements for investigator interaction, processing system capabilities, and availability of data sets. The increased complexity of global processes requires interdisciplinary teams to address them; the investigators will need to interact on a regular basis; however, it is unlikely that a single institution will house sufficient investigators with the required breadth of skills. The complexity of the computations may also require resources beyond those located within a single institution; this lack of sufficient computational resources leads to a distributed system located at geographically dispersed institutions. Finally the combination of long term data sets like the Pathfinder datasets and the data to be gathered by new generations of satellites such as SeaWiFS and MODIS-N yield extra-ordinarily large amounts of data. All of these factors combine to increase demands on the communications facilities available; the demands are generating requirements for highly flexible, high capacity networks. We have been examining the applicability of the Advanced Communications Technology Satellite (ACTS) to address the scientific, computational, and, primarily, communications questions resulting from global change research. As part of this effort three scenarios for oceanographic use of ACTS have been developed; a full discussion of this is contained in Appendix B.

Evans, Robert H.↗
NASA NTRSDate not supplied

Evaluation of single-footprint AIRS CH4 Profile Retrieval Uncertainties Using Aircraft Profile Measurements

We evaluate the uncertainties of methane optimal estimation retrievals from single footprint thermal infrared observations from the Atmospheric Infrared Sounder (AIRS). These retrievals are primarily sensitive to atmospheric methane in the mid-troposphere through the lower stratosphere (~2 to ~17 km). We compare to in situ observations made from aircraft during the Hiaper Pole to Pole Observations (HIPPO), the NASA Atmospheric Tomography Mission (ATom) campaigns, and from the NOAA ESRL aircraft network, between the surface and 5-13 km, across a range of years, latitudes between 60 S to 80 N, and over land and ocean. After a global, pressure dependent bias correction, we find that the land and ocean have similar biases and that the reported observation error (combined measurement and interference errors) of ~27 ppb is consistent with the standard deviation between aircraft and individual AIRS observations. A single measurement has measurement (noise related) uncertainty of ~17 ppb, a ~20 ppb uncertainty from radiative interferences (e.g. from water, temperature, etc.), and ~ 30 ppb due to “smoothing error”, which is partially removed when making comparisons to in situ measurements or models in a way that account for this regularization. We estimate a 16 ppb validation error because the aircraft typically did not measure methane at altitudes where the AIRS measurements have some sensitivity, e.g. the stratosphere. Daily averaged AIRS measurements of at least 9 observations over spatio-temporal domains of < 1 degree and 1 hour have a standard deviation of ~17 ppb versus aircraft, likely because the observation errors from temperature and water vapor (for example) are only partly reduced through averaging. Seasonal averages can reduce this ~17 ppb uncertainty further to ~10 ppb, as determined through comparison with NOAA aircraft, likely because uncertainties related to radiative effects of temperature and water vapor can be reduced when averaged over a season.

Susan Kulawik↗
DOE OSTI2021

Adaptive machine learning for time-varying systems: low dimensional latent space tuning

Machine learning (ML) tools such as encoder-decoder convolutional neural networks (CNN) can represent incredibly complex nonlinear functions which map between combinations of images and scalars. For example, CNNs can be used to map combinations of accelerator parameters and images which are 2D projections of the 6D phase space distributions of charged particle beams as they are transported between various particle accelerator locations. Despite their strengths, applying ML to time-varying systems, or systems with shifting distributions, is an open problem, especially for large systems for which collecting new data for re-training is impractical or interrupts operations. Particle accelerators are one example of large time-varying systems for which collecting detailed training data requires lengthy dedicated beam measurements which may no longer be available during regular operations. We present a novel method of adaptive ML for time-varying systems. Our approach is to map very high (N ≈ 100k) dimensional inputs (a combination of scalar parameters and images) into the low dimensional (N ≈ 2) latent space at the output of the encoder section of an encoder-decoder CNN. We then actively tune the low dimensional latent space-based representation of complex system dynamics by the addition of an adaptively tuned feedback vector directly before the decoder sections builds back up to our image-based high-dimensional phase space density representations. This method allows us to learn correlations within and to quickly tune the characteristics of incredibly large parameter space systems and to track their evolution in real time based on feedback without massive new data sets for re-training. We demonstrate that our method can accurately predict and track the phase space of charged particle beams at various locations in a particle accelerator by adaptively adjusting in real-time while the unknown input beam distribution of the accelerator is changing in shape, charge, and offset and while the RF system of the accelerator itself is also changing in an unpredictable way. For FACET-II we demonstrate that such an approach has the potential to use transverse deflecting cavity and energy spread spectrum beam measurements to accurately predict 2D projections of the 6D phase space of the electron beam at the plasma wakefield acceleration interaction point where such diagnostics are unavailable.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Deep learning-enabled probing of irradiation-induced defects in time-series micrographs

Modeling time-series data with convolutional neural networks (CNNs) requires building a model to learn in batches as opposed to training sequentially. Coupling CNNs with in situ or operando techniques opens the possibility of accurately segmenting dynamic reactions and mass transport phenomena to understand how materials behave under the conditions in which they are used. In this article, in situ ion irradiation transmission electron microscopy (TEM) images are used as inputs into the CNN to assess the defect generation rate, defect cluster density, and saturation of defects. We then use the output segmentation maps to correlate with conventional TEM micrographs to assess the model’s ability to detail nanoscale interactions. Next, we discuss the implications of preprocessing and hyperparameters on model variability, accuracy when expanded to other datasets, and the role of regularization when controlling model variance. Ultimately, we eliminate human bias when extrapolating physical metrics, speed up analysis time, decouple reactions that happen at 100 ms intervals, and deploy models that are both accurate and transferable to similar experiments.

Burns, Kory (ORCID:0000000158019909)↗
DOE OSTI2024

A dynamic solvent chamber propagation estimation framework using RNN for warm solvent injection in heterogeneous reservoirs

Warm solvent injection (WSI), injecting low-temperature solvent into formations to reduce the viscosity of heavy oil, is a clean technology for heavy oil production through reducing greenhouse gas emissions and water usage. The success of WSI operation depends on the uniform development and propagation of solvent chambers in reservoirs. However, reservoir heterogeneity stemming from shale barriers plays a detrimental role in the conformance of solvent chamber development and oil production rate. In this work, we developed a novel recurrent neural network (RNN)-based framework with the capability of efficiently tracking and estimating the solvent chamber positions in heterogeneous reservoirs based on only production time-series data. The developed estimation model utilizes the “sequence-to-sequence" mapping methodology to correlate observed production time-series sequence and solvent chamber edge sequence via a long short-term memory (LSTM) algorithm. The trained RNN models exhibit high accuracy, evidenced by the predicted dynamic solvent chamber locations match the corresponding true locations from numerical simulation, with a high coefficient of determination (R 2 ) and a low mean squared error. Specifically, the achieved R 2 values exceed 0.98 on both the training and testing data. The developed RNN-based workflow was tested via several cases from both regularly- and irregularly-shaped shale barriers, and the results were promising. The predicted solvent chambers showed strong agreement with those obtained from numerical simulations. The major benefits of this workflow include reducing computational time and saving overall monitoring and tracking costs for conventional techniques. In conclusion, the present work would provide a good demonstration of the capability of practical integration of machine learning methods in solving engineering problems.

58 GEOSCIENCES↗
DOE OSTI2021

Machine-learning predictions of the shale wells’ performance

The ultra-low permeability nature of shale reservoirs leads to an extended linear flow and necessitates horizontal wells with multi-stage engineered fractures to efficiently extract hydrocarbons resources. These artificially-generated and naturally-occurring fractures form complex networks that create complex flow regimes which control oil production. These fractures are neither identical nor equally-spaced, which leads to a production profile with a masked onset of the boundary-dominated flow. The combination of the extended linear flow with the indeterminate onset of the boundary-dominated flow challenges the current deterministic analytic approaches to forecast the estimated ultimate recovery (EUR). In this work, we propose a novel machine-learning approach which overcomes these challenges and provides reliable EUR estimates based on field-wide analyses. We implement a novel unsupervised machine learning (ML) methodology, which allows for automatic identification of the optimal number of features (signals) present in the data based on non-negative matrix/tensor factorization coupled with k-means clustering incorporating regularization and physics constraints. In the presented analyses, the input data to the ML algorithm is the available (public) production history from the field collected at existing unconventional reservoirs. We validate our approach through hindcasting of the production data, where we achieved an excellent agreement. In addition, our approach is able to identify the poorly-performing wells, which could benefit from early refracing. Our approach provides fast and accurate estimations of the well performance without presumptions about the state of the well or the flow regime.

03 NATURAL GAS↗
DOE OSTI2023

Enterprise Risks for Scientific Software in the Post Exascale Era

The Department of Energy’s Office of Science’s Advanced Scientific Computing Research (ASCR) Office hosts three high performance computing Facilities and one high performance networking Facility. ASCR’s Facilities Division and these four Facilities established a joint working group to address the most severe threats to the software capabilities that can prevent the Facilities from supporting a diverse array of mission critical scientific research carried out by thousands of researchers from national labs, academia, and industry. This report outlines the risk categories, threat matrix calculations, and number of risks in each of the categories along with the threat levels. Two categories—programming environment/tools and system software—account for 13 out of the 20 risks encountered in the risk register. A significant risk to ASCR’s software ecosystem also arises from the possible loss of personnel and expertise past the end of the exascale computing project. The working group recommends that the software enterprise risks are reevaluated regularly, and are considered in future decision making regarding system acquisition, knowledge sharing, partnership development, and strategic planning

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Physics-guided dual implicit neural representations for source separation

Significant challenges exist in efficient data analysis of most advanced experimental and observational techniques because the collected signals often include unwanted contributions, such as background and signal distortions, that can obscure the physically relevant information of interest. To address this, we have developed a self-supervised machine-learning approach for source separation using a dual implicit neural representation framework that jointly trains two neural networks: one for approximating distortions of the physical signal of interest and the other for learning the effective background contribution. Our method learns directly from the raw data by minimizing a reconstruction-based loss function without requiring labeled data or pre-defined dictionaries. We demonstrate the effectiveness of our framework by considering a challenging case study involving large-scale simulated, as well as experimental, momentum-energy-dependent inelastic neutron scattering data in a four-dimensional parameter space, characterized by heterogeneous background contributions and unknown distortions to the target signal. The method is found to successfully separate physically meaningful signals from a complex or structured background even when the signal characteristics vary across all four dimensions of the parameter space. An analytical approach that informs the choice of the regularization parameter is presented. Our method offers a versatile framework for addressing source separation problems across diverse domains, ranging from superimposed signals in astronomical measurements to structural features in biomedical image reconstructions.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

The Energy and Operational Impacts of Using 0-10V Control for LED Streetlights

LED lighting is becoming widely adopted and displacing most traditional lighting technologies. However, the traditional methods used to control light sources have not seen similar displacement. Lighting systems have historically utilized either a proprietary control method, or one of a handful of standardized methods (e.g., 0-10V, DALI, DMX512). The utility and market success of the standardized methods has been limited for a variety of reasons. Analog 0-10V methods have long been popular due to their simplicity and low cost of implementation and are presently the most commonly available control interface for indoor and outdoor LED products in North America. The emergence of “connected lighting systems” with more modern network interfaces and luminaire-level sensors and intelligence was anticipated by many to mark the beginning of the end of analog control. However, 0-10V interfaces continue to be prevalent with these more “digital” systems. The use of 0-10V methods has significant tradeoffs. 0-10V standards have historically not explicitly defined the relationship between the luminaire input control signal and output luminous flux for the full control signal range. As a result, it is difficult to predict relative luminaire light output and input power at any particular control voltage, and in practice the performance across LED drivers and the luminaires power is inconsistent. While this inconsistency has long been acknowledged by experts in the field, it is not accounted for in standard practice deployment, and end-users continue to regularly see unexpected and undesirable performance. It is hoped that the results from this study will help the lighting industry and standards developing organizations better understand and possibly resolve the shortcomings of 0-10V products, and consider what is best for the industry – additional incremental improvements to this fundamentally limited analog technology, or fully moving on to existing digital approaches, such as DALI D4i, that deliver accurate and consistent dimming performance across all luminaires in the system and thus guarantee the delivery of expected light levels, and energy and cost savings. Recommendations consistent with these goals are made to lighting and driver manufacturers, lighting software developers, standard developing organizations, and system designers and specifiers.

0-10V↗
DOE OSTI2025

GRUMDN: A Multi-Task Model for Predicting Human Patterns-of-Life from Stay Transition Data

Understanding human patterns-of-life (PoL) is essential towards ensuring safe and secure indoor facility environment as well as outdoor urban environment. Prediction of human movement in between places of interest is vital in understanding human PoL. Movement between spaces maybe represented and detected in one of the two forms: 1) trajectories: locations measured at regular time intervals by mobile sensors, bluetooth or GPS sensors; or 2) stay transitions: semantic PoI (points of interest) and stay duration data measurable by eventbased sensors that collect data when a check-in or check-out event is detected. Stay transition data provides a more compressed data format compared to trajectories data, especially in situations with longer stay durations, while preserving the information necessary for PoL analysis. Now as introduced briefly in the paper, our deployed end application (Digital Twin of a facility with non-player characters, besides the interactive user in virtual reality) needed a well-performing and validated AI/ML model for simulating high quality stay transitions behavior. In this study we thus primarily present our findings with developing and validating that model, which is a multi-task neural network for stay transition prediction. The neural network consists of two heads, for corresponding two tasks of stay category prediction and stay duration prediction. We evaluated gated recurrent units and multi-layer perceptrons of varying network sizes for stay category prediction; while mixture density networks, noisy generator-only networks, and generative adversarial networks of varying network sizes for stay duration prediction. We have then evaluated four multi-task models, constructed by combining these specialized models, on their ability to predict stay transition data. We tested our models on datasets from two different cases: 1) a simulation-generated dataset of indoor movement within the HFIR (high flux isotope reactor) nuclear reactor facility at Oak Ridge National Laboratory (ORNL); and 2) the GeoLife human mobility dataset of outdoor urban movement available in literature. Our results indicate that GRUMDN, which combines gated recurrent units (GRU) for stay category prediction task, and mixture density networks (MDN) for stay duration prediction task, did overall outperform other multitask models and the current state-of-the-art.

Gunaratne, Chathika [ORNL] (ORCID:0000000225088745↗
NASA NTRS2009

An Intelligent Archive Testbed Incorporating Data Mining

Many significant advances have occurred during the last two decades in remote sensing instrumentation, computation, storage, and communication technology. A series of Earth observing satellites have been launched by U.S. and international agencies and have been operating and collecting global data on a regular basis. These advances have created a data rich environment for scientific research and applications. NASA s Earth Observing System (EOS) Data and Information System (EOSDIS) has been operational since August 1994 with support for pre-EOS data. Currently, EOSDIS supports all the EOS missions including Terra (1999), Aqua (2002), ICESat (2002) and Aura (2004). EOSDIS has been effectively capturing, processing and archiving several terabytes of standard data products each day. It has also been distributing these data products at a rate of several terabytes per day to a diverse and globally distributed user community (Ramapriyan et al. 2009). There are other NASA-sponsored data system activities including measurement-based systems such as the Ocean Data Processing System and the Precipitation Processing system, and several projects under the Research, Education and Applications Solutions Network (REASoN), Making Earth Science Data Records for Use in Research Environments (MEaSUREs), and the Advancing Collaborative Connections for Earth-Sun System Science (ACCESS) programs. Together, these activities provide a rich set of resources constituting a value chain for users to obtain data at various levels ranging from raw radiances to interdisciplinary model outputs. The result has been a significant leap in our understanding of the Earth systems that all humans depend on for their enjoyment, livelihood, and survival. The trend in the community today is towards many distributed sets of providers of data and services. Despite this, visions for the future include users being able to locate, fuse and utilize data with location transparency and high degree of interoperability, and being able to convert data to information and usable knowledge in an efficient, convenient manner, aided significantly by automation (Ramapriyan et al. 2004; NASA 2005). We can look upon the distributed provider environment with capabilities to convert data to information and to knowledge as an Intelligent Archive in the Context of a Knowledge Building system (IA-KBS). Some of the key capabilities of an IA-KBS are: Virtual Product Generation, Significant Event Detection, Automated Data Quality Assessment, Large-Scale Data Mining, Dynamic Feedback Loop, and Data Discovery and Efficient Requesting (Ramapriyan et al. 2004).

Ramapriyan, H.↗
DOE OSTI2025

Bridging the Gap Between Modern UX Design and Particle Accelerator Control Room Interfaces

Accelerator control systems often represent relatively complex and safety-sensitive human-machine interfaces within process control industries. These systems are technically robust and reflect the cumulative integration of solutions built and adapted across decades. One of the regular, unfortunate casualties of provisional accelerator control system updates is their human-system interfaces (HSIs) which often lag behind modern usability and design standards. An additional challenge is that although there is a multitude of established human factors (HF), and user experience (UX) principles for everyday digital applications, there are very few (if any) established principles for complex and safety-critical applications for an accelerator. This paper argues for the importance of established HF and UX principles (herein referred to as human-centered design principles) into the development of accelerator HSIs, emphasizing the need for clarity, consistency, responsiveness, and cognitive accessibility. Drawing from HF/UX best practices and human-centered design, this paper discusses how these approaches can enhance operator performance, reduce human error, and improve accelerator personnel collaboration. Case studies from Accelerator Control Operations Research Network (ACORN) at Fermilab are explored to demonstrate how interfaces built with human-centered design principles can scale with system complexity while remaining intuitive and efficient for diverse user roles including operators, machine experts, and engineers. By bridging the gap between traditional control system design and modern human-centered design methods, this paper provides a roadmap for evolving accelerator HSIs into more usable, maintainable, and effective tools.

Hill, Rachael [Idaho Natl. Lab.]↗
DOE OSTI2022

Background-Aware 3-D Point Cloud Segmentation With Dynamic Point Feature Aggregation

With the proliferation of LiDAR sensors and 3-D vision cameras, 3-D point cloud analysis has attracted significant attention in recent years. In this article, we propose a novel 3-D point cloud learning network, referred to as dynamic point feature aggregation network (DPFA-Net), by selectively performing the neighborhood feature aggregation (FA) with dynamic pooling and an attention mechanism. DPFA-Net has two variants for semantic segmentation and classification of 3-D point clouds. As the core module of the DPFA-Net, we propose an FA layer, in which features of the dynamic neighborhood of each point are aggregated via a self-attention mechanism. In contrast to other segmentation models, which aggregate features from fixed neighborhoods, our approach can aggregate features from different neighbors in different layers providing a more selective and broader view to the query points and focusing more on the relevant features in a local neighborhood. In addition, to further improve the performance of semantic segmentation, we exploit the background–foreground (BF) information and present two novel approaches, namely, two-stage BF-Net and BF regularization. Experimental results show that the proposed DPFA-Net achieves the state-of-the-art overall accuracy score of 89.22% for semantic segmentation on the Stanford large-scale 3-D Indoor Spaces (S3DIS) dataset and provides consistently satisfactory performance across different tasks of semantic segmentation, part segmentation, and 3-D object classification. Furthermore, our model achieves 93.1% accuracy on the ModelNet40 dataset and provides a mean shape intersection-over-union (IoU) value of 85.5% for part segmentation on the ShapeNet-Part dataset. It is a also computationally more efficient compared to other methods.

3-D↗
DOE OSTI2023

Student Travel Support for the Inaugural Gordon Research Seminar on Multiphoton Processes (Final Technical Report)

This project provided financial support for early-career participants of the 2022 Gordon Research Seminar (GRS) on Multiphoton Processes, which was held on June 11 & 12, 2022 in Smithfield, Rhode Island, in conjunction with the Gordon Research Conference (GRC) on the same topic, held on June 12-17, 2022 in the same location. The GRC on Multiphoton Processes is an established conference series in the field of Atomic, Molecular and Optical (AMO) Physics with intense lasers. It regularly attracts around one hundred fifty researchers from around the world to present and discuss their forefront research featuring light-matter interaction in a variety of systems, ranging from atoms and molecules to nanosystems. In order to increase the attendance of early-career researchers at the GRC, in particular graduate students, post-docs, and other scientists with comparable levels of experience and education, the general assembly of the GRC on Multiphoton Processes decided during their last session in 2018 to organize a Gordon Research Seminar in conjunction with the next conference and organized and attended by early-career researchers. The GRS's primary intent is to provide a forum to graduate students and post-docs working in the field of intense and ultrafast AMO physics to present and exchange new data and cutting-edge ideas and to network with their peers at other research institutions around the U.S. and the world.

74 ATOMIC AND MOLECULAR PHYSICS↗