Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “intelligent sensors”

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.

719 records · Page 40
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Field Experiments and Model Validation: The EGS Collab Project

Implementing enhanced geothermal systems (EGS) will require improvements in understanding stimulation of crystalline rock to create appropriate flow pathways, and the ability to effectively simulate both the stimulation and the flow and transport processes in the resulting fracture network. The US Department of Energy (DOE) is addressing these and other challenges at multiple scales. The EGS Collab project, addressed here, is performing tests and modeling at the 10 m scale. The FORGE project is performing tests at the full reservoir scale. The EGS Collab team created an underground testbed at the Sanford Underground Research Facility (SURF) in Lead, South Dakota, at a depth of approximately 1.5 km to examine hydraulic fracturing (Experiment 1). We are currently building a second testbed at SURF at a depth of about 1.25 km aimed at investigating shear stimulation (Experiment 2). In Experiment 1, we drilled eight boreholes in a well-characterized phyllite and installed geophysical sensors in six of them to create a well-instrumented testbed to allow careful monitoring of stimulation events and flow tests. Numerical simulation was used to answer key experimental design questions, to forecast fracture propagation trajectories and extents, and to analyze and evaluate results both in near-real-time and in detailed process studies. Stimulations performed in this testbed allowed quantification of processes occurring during stimulation and the examination of dynamic flow occurrences. Long-term ambient temperature and chilled water flow tests were performed in addition to many tracer tests to examine system behavior. Our second testbed, targeted at shear stimulation, is currently being built at the SURF Facility at a depth of about 1.25 km in amphibolite under a different set of stress and fracture conditions than Experiment 1.

artificial intelligence↗
DOE OSTI2022

Intelligent Process Visualization through Nuclear Operation Process Modeling, Reasoning, and Object Detection from Field Videos (Final Report)

This report is a deliverable for the “Final Report” task of DOE NEET Project 19-16790, "Context-Aware Safety Information Display for Nuclear Field Workers." This project's overall goal is to test the hypothesis that integrating computer vision and process reasoning methods will enable proactive visualization of the safe operation and maintenance processes of Nuclear Power Plants (NPP) for field workers. Augmented Reality (AR) glasses adopting such proactive safety information visualization techniques can significantly increase personnel safety and reduce the NPP’s operating costs. The current practice of monitoring NPPs requires workers to switch between digital models, data, and physical workspaces in identifying relevant but potentially occluded objects and in assessing the risks of operation and maintenance processes. On the other hand, frequently changed field conditions require field workers to report to supervisors for real-time guidance. Such guidance is essential to ensure that changing conditions will not invalidate or endanger the work order and other ongoing processes that may jeopardize NPP operations. Additionally, incorrect recognition of equipment objects can result in communication errors and safety problems. AR techniques can assist engineers in viewing the physical workspaces with objects labeled with detailed operation procedures and safety reminders during field operations. The project team developed an “Intelligent Context-Aware Safety Information Display” (ICAD) for supporting Nuclear Power Plant (NPP) field workers in achieving safe and efficient execution of a series of operational tasks in uncertain and changing workspaces of an NPP. Before designing the ICAD-AR prototype, the project team synthesized NPP operational knowledge models through literature review studies, surveys, interviews with domain experts, and knowledge modeling. The project team conducted an extensive study of the operational procedures of various NPPs, and digital technologies that can support the safe and efficient execution of those procedures in different NPP operational contexts. This literature review helped the project team conduct surveys and interviews with nuclear engineers and field workers to identify three categories of information. The NPP knowledge modeling efforts reveal that the three categories of information identified have different levels of importance in a typical procedure of carrying out a series of tasks to achieve a specific NPP operation goal (e.g., shutdown, mode changes). These three categories of information include 1) Workspace dynamics – the changing spatial arrangements of workspaces, tools, protection equipment, and supporting materials, 2) Workflow prognostics – the dynamic dependencies between different parts of an NPP that functionally support and influence each other in terms of safety and efficiency, and 3) Hazards – objects and spaces that contain hazardous materials or physical conditions that can pose risks to workers or mechanical systems. The project team has profiled the importance levels of these categories of information into a knowledge model. This knowledge model specifies what types of information are more critical for a given task in a given workspace so that computers can automatically identify critical objects and sensors in a scene for delivering context-ware safety information to field workers through AR devices. Significant research development of this project results in technical research outcomes and a prototyping system that illustrates the technical feasibility of establishing an ICAD-AR system supporting the proactive safety information display for nuclear field workers. This final report summarizes the project team’s technological achievements in the past three years. Overall, the project team completed the development and integration of five techniques into a prototype ICAD Augmented Reality (ICAD-AR) system and demonstrated the developed system’s real-time execution in a mechanical room. The project team completed the analysis of using this prototype in other types of workspaces based on 3D image data and digital design models collected from two additional workspaces (a water treatment plant and a flow loop training facility). The integrated techniques include 1) Natural Language Processing (NLP) algorithms supporting the generation and updates of nuclear fieldwork process models based on text analysis of work packages and operation manuals; 2) sensor log analysis for predicting control actions in given sensor reading contexts; 3) computer vision algorithms for automatic localization and navigation of workers; 4) object detection algorithms for identifying task-related objects and correlated sensors for safety checking; 5) AR technique as a platform for supporting the integration. The testing results of these five techniques have shown that 1) the sensor log analysis model can predict the next control action with an accuracy of 0.883; 2) the trained natural language processing model can extract more than 80% of the critical information from paper-based procedures (PBPs); 3) the navigation algorithm with the integration of Visual Inertial Odometry (VIO) and Non-Recursive Bayesian Filter methods make operator’s trajectory estimation resilient to drift error; 4) the computer vision algorithm can detect task-specific and safety-critical objects with an average accuracy of 95.3%. The project team used work procedures collected from a flow loop training facility and two datasets collected from two mechanical rooms simulating the workspaces of NPPs to demonstrate the technical capabilities of the developed ICAD-AR prototype. The demonstration validated the technical feasibility of establishing the ICAD-AR system for nuclear field workers and identified the challenges in 1) automatic text analysis of work packages; 2) use of limited samples of sensor logs for predicting the proper timings of control actions; 3) reliably tracking workers and their task progress in mechanical rooms with many similar objects.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRSDate not supplied

Development and Airborne Demonstration of the Concurrent Artificially-Intelligent Spectrometry and Adaptive Lidar System: Advancing Lidar Capabilities for the STV Observing System

We report on the design, build and planned airborne demonstration of a spaceflight-prototype Concurrent Artificially-intelligent Spectrometry and Adaptive Lidar System (CASALS). The CASALS lidar is an Adaptive Wavelength Scanning Lidar (AWSL) operating in push broom mode. The demonstration has three major goals: advance the Technical Readiness Level of the AWSL hardware, validate its measurement performance and mature algorithms and methods needed for the Surface Topography and Vegetation (STV) observing system. AWSL acquires parallel tracks of surface heights by rapidly steering a laser beam across a swath. A 1040nm-centered laser is tuned across 30nm and carved into 2-ns pulses, the pulse energy is fiber amplified and the pulses are dispersed cross-track using a non-mechanical wavelength-to-angle grating. For the spaceflight system the beam will be pointable to 1200 10m footprints across a 7km swath. For the airborne demonstration there will be 256 0.7m footprints across a 110m swath. In both cases the footprints overlap across- and along-track for uniform target illumination. For the airborne demonstration a steering mirror will increase the accessible swath width to 4km. At the receiver, solar radiation is filtered with a narrow-slit grating-spectrometer and the footprints are imaged onto a linear-mode, photon-sensitive HgCdTe APD-array. The received pulses are time-division-multiplexed to a few high-speed analog-to-digital converters to record waveforms. Spaceflight and airborne CASALS are designed to nominally detect 20 photons per pulse and, by averaging 27 overlapping footprints, achieve 2cm flat target range precision and high-quality vegetation structure waveforms The AWSL will be flown in the summer of 2024, along with a Headwall VNIR-SWIR hyperspectral sensor imaging a 4km wide swath, at NEON eddy covariance flux towers in the U.S. mid-Atlantic where high resolution hyperspectral and lidar data, acquired annually, are available for validation.

Guangning Yang↗
NASA NTRS2010

Regional Precipitation Forecast with Atmospheric InfraRed Sounder (AIRS) Profile Assimilation

Advanced technology in hyperspectral sensors such as the Atmospheric InfraRed Sounder (AIRS; Aumann et al. 2003) on NASA's polar orbiting Aqua satellite retrieve higher vertical resolution thermodynamic profiles than their predecessors due to increased spectral resolution. Although these capabilities do not replace the robust vertical resolution provided by radiosondes, they can serve as a complement to radiosondes in both space and time. These retrieved soundings can have a significant impact on weather forecasts if properly assimilated into prediction models. Several recent studies have evaluated the performance of specific operational weather forecast models when AIRS data are included in the assimilation process. LeMarshall et al. (2006) concluded that AIRS radiances significantly improved 500 hPa anomaly correlations in medium-range forecasts of the Global Forecast System (GFS) model. McCarty et al. (2009) demonstrated similar forecast improvement in 0-48 hour forecasts in an offline version of the operational North American Mesoscale (NAM) model when AIRS radiances were assimilated at the regional scale. Reale et al. (2008) showed improvements to Northern Hemisphere 500 hPa height anomaly correlations in NASA's Goddard Earth Observing System Model, Version 5 (GEOS-5) global system with the inclusion of partly cloudy AIRS temperature profiles. Singh et al. (2008) assimilated AIRS temperature and moisture profiles into a regional modeling system for a study of a heavy rainfall event during the summer monsoon season in Mumbai, India. This paper describes an approach to assimilate AIRS temperature and moisture profiles into a regional configuration of the Advanced Research Weather Research and Forecasting (WRF-ARW) model using its three-dimensional variational (3DVAR) assimilation system (WRF-Var; Barker et al. 2004). Section 2 describes the AIRS instrument and how the quality indicators are used to intelligently select the highest-quality data for assimilation. Section 3 presents an overall precipitation improvement with AIRS assimilation during a 37-day case study period, and Section 4 focuses on a single case study to further investigate the meteorological impact of AIRS profiles on synoptic scale models. Finally, Section 5 provides a summary of the paper.

Chou, S.-H.↗
DOE OSTI2022

A Cybersecurity Threat Profile for a Connected Lighting System

In anticipation of improved energy performance and cost savings, cities and building owners are increasingly considering “smart lighting initiatives” that aim to convert their collection of simple luminaires (i.e., lighting fixtures) into an intelligent connected lighting system (CLS) capable of remotely monitoring energy consumption and fault conditions, and possibly implementing adaptive lighting schemes. The U.S. Department of Energy (DOE) has set an national goal of tripling the energy efficiency and demand flexibility of the buildings sector by 2030, relative to 2020 levels 1. It is forecast that connected lighting systems can contribute to that goal by delivering 125 TWh of annual energy savings by 2035 2, equivalent to the annual output of 50 typical (500 MW) power plants. However, these energy savings and the DOE goal are put at significant risk if connected technologies are not adopted due to real or perceived cybersecurity concerns. Connected IoT devices such as these have historically been rife with vulnerabilities which sometimes put security considerations secondary to functionality and operability. What are the cybersecurity threats that will impact these systems, as formerly banal luminaires transition into intelligent connected devices that collect information about themselves, their surrounding environment, and possibly us? In this paper we analyze a threat profile performed on a fault-detection use case for streetlights. A threat profile establishes security requirements, justifies security measures, yields actionable controls, and effectively communicates risk to stakeholders. This effort provides critical information for making threat-based decisions to increase security at a reasonable cost, and can effectively be used by development teams, software architects, and managers to make cybersecurity a part of their ongoing culture of awareness, training, and prevention. This leads to more secure systems and better-understood security. On-premise, cloud, and hybrid architectures with different authentication mechanisms were modeled and later categorized using the Microsoft STRIDE framework. An analysis of the recommended controls for each threat was performed to determine which controls could and should be put in place by manufacturers or third-party suppliers, and which controls need to be left up the end-user to implement. Fifty-seven threats were identified. Among our key findings: (1) 65% (37/57) of the threats did not involve the luminaires, but rather the other components needed to communicate with and manage them; (2) 63% (36/57) of the threats could have been mitigated through manufacturer-implemented defensive techniques or “controls”; and (3) 23% (13/57) of the threats were dependent on the network configuration. Recommendations based on the results of this work are made to key stakeholder groups. Notably, lighting technology developers are advised to address all threats that can be reasonably controlled with baked-in technology solutions (e.g., encryption or authentication controls), and employ some form of secure supply chain management and tracking where other parts (e.g., sensors, microprocessors) of a luminaire must also be built and manufactured with the proper security controls in place. Developers should also review threats involving assets not developed in-house to understand how connectivity with other devices will affect their product during system operation and determine if a compensating control for a defense-in-depth strategy will be needed. Finally, those interested in deploying CLS should compare the differences between cloud and on-premise models to determine which is more suitable for their needs and the abilities of their security team.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

A Reconfigurable Neural Network ASIC for Detector Front-End Data Compression at the HL-LHC

Despite advances in the programmable logic capabilities of modern trigger systems, a significant bottleneck remains in the amount of data to be transported from the detector to off-detector logic where trigger decisions are made. We demonstrate that a neural network (NN) autoencoder model can be implemented in a radiation-tolerant application-specific integrated circuit (ASIC) to perform lossy data compression alleviating the data transmission problem while preserving critical information of the detector energy profile. For our application, we consider the high-granularity calorimeter from the Compact Muon Solenoid (CMS) experiment at the CERN Large Hadron Collider. The advantage of the machine learning approach is in the flexibility and configurability of the algorithm. By changing the NN weights, a unique data compression algorithm can be deployed for each sensor in different detector regions and changing detector or collider conditions. To meet area, performance, and power constraints, we perform quantization-aware training to create an optimized NN hardware implementation. The design is achieved through the use of high-level synthesis tools and the hls4ml framework and was processed through synthesis and physical layout flows based on a low-power (LP)-CMOS 65-nm technology node. The flow anticipates 200 Mrad of ionizing radiation to select gates and reports a total area of 3.6 mm 2 and consumes 95 mW of power. The simulated energy consumption per inference is 2.4 nJ. Furthermore, this is the first radiation-tolerant on-detector ASIC implementation of an NN that has been designed for particle physics applications.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

GraMeR: Gra ph Me ta R einforcement learning for multi-objective influence maximization

Influence maximization (IM) is a combinatorial problem of identifying a subset of seed nodes in a network (graph), which when activated, provide a maximal spread of influence in the network for a given diffusion model and a budget for seed set size. IM has numerous applications such as viral marketing, epidemic control, sensor placement and other network-related tasks. However, its practical uses are limited due to the computational complexity of current algorithms. Recently, deep reinforcement learning has been leveraged to solve IM in order to ease the computational burden. However, there are serious limitations in current approaches, including narrow IM formulation that only consider influence via spread and ignore self-activation, low scalability to large graphs, and lack of generalizability across graph families leading to a large running time for every test network. In this work, we address these limitations through a unique approach that involves: (1) Formulating a generic IM problem as a Markov decision process that handles both intrinsic and influence activations; (2)incorporating generalizability via meta-learning across graph families. There are previous works that combine deep reinforcement learning with graph neural network, but this work solves a more realistic IM problem and incorporates generalizability across graphs via meta reinforcement learning. Extensive experiments are carried out in various standard networks to validate performance of the proposed Graph Meta Reinforcement learning (GraMeR) framework. Finally, the results indicate that GraMeR is multiple orders faster and generic than conventional approaches when applied on small to medium scale graphs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Event-to-Video Conversion for Overhead Object Detection

Collecting overhead imagery using an event camera is desirable due to the energy efficiency of the image sensor compared to standard cameras. However, event cameras complicate downstream image processing, especially for complex tasks such as object detection. In this paper, we investigate the viability of event streams for overhead object detection. We demonstrate that across a number of standard modeling approaches, there is a significant gap in performance between dense event representations and corresponding RGB frames. We establish that this gap is, in part, due to a lack of overlap between the event representations and the pre-training data that the object detectors were initially trained on through a number of experiments. Then, apply an off-the-shelf event-to-video conversion tool that converts event streams into gray-scale video to close this gap. We demonstrate that this approach results in a large performance increase, outperforming even event-specific object detection techniques on our overhead target task. These results suggest that better aligning event representations with existing large pre-trained models may result in greater short-term performance gains compared to end-to-end event-specific architectural improvements.

machine learning (ML), computer vision, Neuromorph↗
DOE OSTI2024

Chemical signature characterization with hyperspectral imagery: novel deep learning model architectures and physically-motivated data augmentation techniques

The high spectral resolution afforded by Hyperspectral Imaging (HSI) sensors is poised to bring unprecedented advancements to signature characterization applications. Thus far, much of the research in the machine learning field devoted to HSI applications has focused on a few specific tasks like land-use land-cover classification. In land classification tasks, spatial information is very important, and model architectures are often designed to leverage spatial contexts. However, it is unclear how well these spatially-tuned models will translate to tasks where spectral information is critical, like the detection and characterization of chemicals. In this work, we compare spectral models (inputs are 1D spectra) and spatial-spectral models (inputs are 3D cubes) in the context of predicting chemical concentration maps. We find that spatial-spectral models perform the best, though we find a wide range in performance across the different architectures tested. Additionally, we find that model performance is impacted by the availability of training data, particularly in scenarios where the training data doesn't fully capture the true variance of real-world conditions. We find that data augmentation can help mitigate sparse coverage of observed parameter space (e.g., seasonal or geographic variability in ground cover), and present augmentation strategies that are tailored to hyperspectral data.

• Artificial intelligence (AI) / machine learning ↗
DOE OSTI2023

Artificial intelligence models, photos, and data associated with the manuscript “Quantifying Streambed Grain Size, Uncertainty, and Hydrobiogeochemical Parameters Using Machine Learning Model YOLO” (v2)

This data package is associated with the manuscript “Quantifying Streambed Grain Size, Uncertainty, and Hydrobiogeochemical Parameters Using Machine Learning Model YOLO” published in Water Resources Research (Chen et al., 2024). This data package includes the training, validation, testing, and prediction data used by the artificial intelligence (AI) model for automated grain size and hydro-biogeochemistry quantification using streambed photos. The grain size data are extracted for each photo using You Look Only Once (YOLO), a pre-trained object detection model. This data package was originally published in October 2023. It was updated August 2025 (v2; new and modified files). File and folder names were not revised to indicate changes. See the change history section in the readme for more details. Please see flmd.csv for a list of all files contained in this data package and descriptions for each. Please see dd.csv for a data dictionary that defines the column headers of .csv files in the data package. This dataset is comprised of one data folder containing (1) file-level metadata; (2) data dictionary; (3) readme; and (4) six subfolders. Subfolders 1 to 4 include the training, validation, testing, and prediction data. Subfolder 5_Summary includes the summary results of different combinations of training, validation, testing, and prediction data. Subfolder 6_SupplementalData includes additional data downloaded from public sources (Kaufman et al., 2023a; Kaufman et al., 2023b; Garefalakis et al., 2023; Mair et al., 2024; https://github.com/river-corridors-sfa/Geospatial_variables). In total, the data package includes 110 folders and 44,283 files. These files include 9,047 .jpg photos, 1 .png photo, 3 .tif photos; 26,639 photo labels and individual grain sizes and probability from AI (.txt); 8,447 grain size distribution data (.dat); and 126 CSV files for results summary, and 14 required metadata files (.xlsx). The summary CSV files contain 68 columns and approximately 2,200 rows that represent photo names, site locations, recording time, GPS coordinates, grains sizes (D10, D50, D60, and D84), number of grains, and additional hydro-biogeochemical data such as water depth, flow velocity, Manning’s coefficient, friction factor, hydraulic conductivity, permeability, streambed interstitial velocity magnitude, mass transfer rate, and nitrate uptake velocity. The photos were obtained from 75 sites in the Yakima River Basin and the Columbia River shorelines, and other associated data from samples and sensors obtained when the photos were taken are publicly available (Fulton et al. 2022; Grieger et al. 2023). All files are .csv, .txt, .dat, .jpg, or .pdf. We acknowledge the Yakama Nation as owners and caretakers of the lands where we collected some of these data. We thank the Confederated Tribes and Bands of the Yakama Nation Tribal Council and Yakama Nation Fisheries for working with us to facilitate sample collection and optimization of data usage according to their values and worldview.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Automated Fire Detection for Industrial Settings with Pretrained Convolutional Networks

Early fire detection in industrial environments is critical to preventing equipment damage, personal injury, and operational disruptions. Traditional smoke detectors, while effective, often experience delays due to the time required for smoke to reach sensors, allowing fires to spread. Manual fire watch operations and human surveillance of camera feeds are resource-intensive and prone to human error. To address these challenges, this paper explores the application of convolutional neural networks for automated fire detection, specifically in industrial settings. By leveraging 11 different pre-trained machine vision models from TensorFlow and enhancing them with transfer learning on a custom-built industrial fire dataset, we optimized fire detection performance. Here, we analyzed each machine vision model architecture in terms of its depth, width, and input image resolution, considering both resource requirements and detection accuracy. We further explored the option of combining multiple models into an ensemble classifier to evaluate whether the performance improvements could justify the much greater computational complexity and other practical impacts. A cost-benefit analysis is presented to evaluate the trade-offs between performance and computational expense. Our findings identify that EfficientNetV2L, specifically tailored for industrial applications, provides the optimal balance between costs involved in training and using the model versus the overall fire detection performance. Additionally, we present a qualitative analysis of model performance using the technique of gradient-based class activation mapping to provide explainability by visualizing model decisions.

artificial intelligence↗
DOE OSTI2025

Even Higher-Level Synthesis: An Exploration of AI Hardware Accelerators using HLS4ML

With the rise of artificial intelligence, the popularization of deep learning, and a constantly evolving industry, the demand for flexible and efficient tools has never been greater. As algorithms grow more complex, their runtime and energy consumption increase exponentially. Customized hardware accelerators, long used for specific mathematical operations, remain essential for managing modern applications' computational and power demands. Hardware accelerators can speed up complex computations by orders of magnitude, but their manual design and verification processes are often challenging and time-consuming. High-Level Synthesis (HLS) provides a solution by transforming high-level algorithm descriptions, typically written in C++ or SystemC, into synthesizable RTL suitable for hardware implementation. This approach reduces development time for RTL engineers while offering flexibility beyond what traditional handwritten RTL can provide. We extended this capability to the machine-learning domain with the open-source framework hls4ml, which allows neural networks trained in Python frameworks like Tensorflow or PyTorch to be synthesized into efficient hardware representations for the traditional FPGA and ASIC flows. This breakthrough addresses the growing need for reduced design turnaround and easy verification of ML hardware accelerators with low latency and power efficiency constraints. During this tutorial, we will demonstrate how Python complements HLS by simplifying the ML design process, bridging the gap between software and hardware development. Attendees will explore how we translate neural networks modeled in Python into fixed-point C++ models suitable for HLS workflows. We will dive into strategies like Value-Range Analysis and Quantization-Aware Training, which optimize these designs for deployment and evaluate their accuracy, power consumption, and energy efficiency. To exemplify these concepts, experts from Fermilab will share their experiences applying this technology to high-energy physics experiments, where real-time, low-latency processing is critical. Over the years, Fermilab engineers have demonstrated how deep neural networks, optimized for hardware using hls4ml, can meet the stringent requirements of trigger systems at the CERN Large Hadron Collider. These systems rely on rapid decision-making to process immense data volumes while retaining only the most relevant events for further analysis. The application of hls4ml has also been extended to innovative technologies like smart pixel arrays. These smart pixels integrate ML inference capabilities directly into sensor devices, enabling localized data processing at the pixel level. This approach drastically reduces the need to transmit raw data to external processing units, significantly decreasing power consumption and latency. By embedding neural networks within the pixel architecture, the smart pixels can identify and prioritize relevant data in real time, providing a highly efficient solution for edge computing in scenarios such as particle detectors and imaging systems. Fermilab's work highlights the potential of hardware-accelerated ML in scenarios where both speed and power efficiency are mission-critical. Through this tutorial, attendees will gain valuable insights into the challenges and solutions of deploying ML in hardware. Understanding how HLS and hls4ml streamline the development of neural network-based hardware accelerators is fundamental for the industry's future. Participants will learn how these technologies are shaping the future of AI and scientific computing.

Di Guglielmo, Giuseppe [Fermilab]↗
DOE OSTI2021

Big Data For Operation and Maintenance Cost Reduction

The purpose of this research is to develop a first-of-a-kind framework for integrating Big Data capability into the daily activities of our current fleet of nuclear power plants. Big Data is traditionally defined as data sets with high volume, velocity, and heterogeneity, and the existing Big Data analytics capabilities are now widely popular in fields such as finance, weather, e-commerce, healthcare and sports. In the nuclear industry, while the volume and velocity of data may present computational challenges for existing analytics capabilities, data heterogeneity are seen to present the major challenge. This research project mainly focuses on incorporating the wide range of data heterogeneities in nuclear power plants into an integrated Big Data Analytics capability. The primary end-product of this project is a Big Data framework that is capable of dealing with the large volume and heterogeneity of the data found in nuclear power plants to extract timely and valuable information on equipment performance. The framework can generate system insights that are actionable relations between measurable impacts and the corresponding maintenance action plans and enable optimization of plant operation and maintenance based on the extracted information. The developed framework is capable of handling heterogeneous data including both image data and time-series sensor data. Specifically, this developed framework includes the following components. The first component is an overarching maintenance ontology which includes system insights required by maintenance optimization. The maintenance ontology interacts with other components in the developed framework. The second component handles Piping & Instrumentation Diagram (P&ID) data. It can be used to extract system components and their relations automatically from the P&IDs. This extracted information is stored in the first component, i.e., maintenance ontology, and is also used as input to the third component, i.e., a tool for generating the fault tree for the corresponding system. The generated fault tree in turn is stored in the ontology for assessing risk that is used as a criterion in maintenance policy optimization. The fourth component is a tool for inferring the parameters in the Markov degradation model for a nuclear system. It uses basic information from the ontology. The fifth component is a tool for assessing the degradation level using sensor measurement data, for example, pressure, flowrate. This tool can be used for determining corrective maintenance actions. The results obtained from components four and five are returned to the ontology. The sixth component of the framework is a tool for optimizing the maintenance policy for a nuclear system of interest. It takes certain basic information from the ontology, e.g., costs of maintenance actions and system failures, as input, and returns the optimal maintenance policy to the ontology. This tool can be used for determining predictive maintenance actions. A set of experiments have also been conducted to verify the algorithms developed in this project for nuclear system degradation monitoring. The experiments are based on four solenoid valves, similar to the ones used in nuclear power plants. The analyses based on the experimental data using two algorithms, i.e., the Randomized Window Decomposition (RWD) algorithm and the particle filtering algorithm, and the results are introduced in the report. The Big Data framework developed in this project can be used as a support tool in daily activities of plant operation and maintenance and will reduce current costs while maintaining or improving safety levels. Overall, the project will not only benefit existing reactors, however it will open new frontiers to realize the long overdue value of Big Data Analytics in the nuclear sphere.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS2022

A Comprehensive Machine Learning Study to Classify Precipitation Type over Land from Global Precipitation Measurement Microwave Imager (GPM-GMI) Measurements

Precipitation type is a key parameter used for better retrieval of precipitation characteristics as well as to understand the cloud–convection–precipitation coupling processes. Ice crystals and water droplets inherently exhibit different characteristics in different precipitation regimes (e.g., convection, stratiform), which reflect on satellite remote sensing measurements that help us distinguish them. The Global Precipitation Measurement (GPM) Core Observatory’s microwave imager (GMI) and dual-frequency precipitation radar (DPR) together provide ample information on global precipitation characteristics. As an active sensor, the DPR provides an accurate precipitation type assignment, while passive sensors such as the GMI are traditionally only used for empirical understanding of precipitation regimes. Using collocated precipitation type flags from the DPR as the “truth”, this paper employs machine learning (ML) models to train and test the predictability and accuracy of using passive GMI-only observations together with ancillary information from a reanalysis and GMI surface emissivity retrieval products. Out of six ML models, four simple ones (support vector machine, neural network, random forest, and gradient boosting) and the 1-D convolutional neural network (CNN) model are identified to produce 90–94% prediction accuracy globally for five types of precipitation (convective, stratiform, mixture, no precipitation, and other precipitation), which is much more robust than previous similar effort. One novelty of this work is to introduce data augmentation (subsampling and bootstrapping) to handle extremely unbalanced samples in each category. A careful evaluation of the impact matrices demonstrates that the polarization difference (PD), brightness temperature (Tc) and surface emissivity at high-frequency channels dominate the decision process, which is consistent with the physical understanding of polarized microwave radiative transfer over different surface types, as well as in snow and liquid clouds with different microphysical properties. Furthermore, the view-angle dependency artifact that the DPR’s precipitation flag bears with does not propagate into the conical-viewing GMI retrievals. This work provides a new and promising way for future physics-based ML retrieval algorithm development.

machine learning/artificial intelligence↗
DOE OSTI2025

Vision Foundation Models in Remote Sensing: A survey

Artificial intelligence (AI) technologies have profoundly transformed the field of remote sensing (RS), revolutionizing data collection, processing, and analysis. Traditionally reliant on manual interpretation and task-specific models, RS research has been significantly enhanced by the advent of foundation models (FMs)—large-scale pretrained AI models capable of performing a wide array of tasks with unprecedented accuracy and efficiency. This article provides a comprehensive survey of FMs in the RS domain. We categorize these models based on their architectures, pretraining datasets, and methodologies. Through detailed performance comparisons, we highlight emerging trends and the significant advancements achieved by those FMs. Additionally, we discuss technical challenges, practical implications, and future research directions, addressing the need for high-quality data, computational resources, and improved model generalization. Our research also finds that pretraining methods, particularly self-supervised learning (SSL) techniques like contrastive learning (CL) and masked autoencoders (MAEs), remarkably enhance the performance and robustness of FMs. This survey aims to serve as a resource for researchers and practitioners by providing a panorama of advances and promising pathways for the continued development and application of FMs in RS.

data models↗
NASA NTRS2000

The Life Cycle Application of Intelligent Software Modeling for the First Materials Science Research Rack

Marshall Space Flight Center (MSFC) has been funding development of intelligent software models to benefit payload ground operations for nearly a decade. Experience gained from simulator development and real-time monitoring and control is being applied to engineering design, testing, and operation of the First Material Science Research Rack (MSRR-1). MSRR-1 is the first rack in a suite of three racks comprising the Materials Science Research Facility (MSRF) which will operate on the International Space Station (ISS). The MSRF will accommodate advanced microgravity investigations in areas such as the fields of solidification of metals and alloys, thermo-physical properties of polymers, crystal growth studies of semiconductor materials, and research in ceramics and glasses. The MSRR-1 is a joint venture between NASA and the European Space Agency (ESA) to study the behavior of different materials during high temperature processing in a low gravity environment. The planned MSRR-1 mission duration is five (5) years on-orbit and the total design life is ten (IO) years. The MSRR-1 launch is scheduled on the third Utilization Flight (UF-3) to ISS, currently in February of 2003). The objective of MSRR-1 is to provide an early capability on the ISS to conduct material science, materials technology, and space product research investigations in microgravity. It will provide a modular, multi-user facility for microgravity research in materials crystal growth and solidification. An intelligent software model of MSRR-1 is under development and will serve multiple purposes to support the engineering analysis, testing, training, and operational phases of the MSRR-1 life cycle development. The G2 real-time expert system software environment developed by Gensym Corporation was selected as the intelligent system shell for this development work based on past experience gained and the effectiveness of the programming environment. Our approach of multi- uses of the simulation model and its intuitive graphics capabilities is providing a concurrent engineering environment for rapid prototyping and development. Operational schematics of the MSRR-1 electrical, thermal control, vacuum access, and gas supply systems, and furnace inserts are represented graphically in the environment. Logic to represent first order engineering calculations is coded into the knowledge base to simulate the operational behavior of the MSRR-1 systems. An example of engineering data provided includes electrical currents, voltages, operational power, temperatures, thermal fluid flow rates. pressures, and component status indications. These type of data are calculated and displayed at appropriate instrumentation points, and the schematics are animated to reflect the simulated operational status of the MSRR-1. The software control functions are also simulated to represent appropriate operational behavior based on automated control and response to commands received by the crew or ground controllers. The first benefit of this simulation environment is being realized in the high fidelity engineering analysis results from the electrical power system G2 model. Secondly, the MSRR-1 simulation model will be embedded with a hardware mock-up of the MSRR-1 to provide crew training on MSRR-1 integrated payload operations. G2 gateway code will output the simulated instrumentation values, termed as telemetry, in a flight-like data stream so that the crew has realistic and accurate simulated MSRR-1 data on the flight displays which will be designed for crew use. The simulation will also respond appropriately to crew or ground initiated commands, which will be part of normal facility operations. A third use of the G2 model is being planned; the MSRR-1 simulation will be integrated with additional software code as part of the test configuration of the primary onboard computer, or Master Controller, for MSRR-1. We will take advantage of the G2 capability to simulate the flight like data stream to test flight software responses and behavior. A fourth use of the G2 model will be to train the Ground Support Personnel that will monitor the MSRR-1 systems and payloads while they are operating aboard the ISS. The intuitive, schematic based environment will provide an excellent foundation for personnel to understand the integrated configuration and operation of the MSRR-1, and the anticipated telemetry feedback based on operational modes of the equipment. Expert monitoring features will be enhanced to provide a smart monitoring environment for the operators. These features include: (1) Animated, intuitive schematic-based displays which reflect telemetry values, (1) Real-time plotting of simulated or incoming sensor values, (3) High/Low exception monitoring for analog data, (4) Expected state monitoring for discrete data, (5) Data trending, (6) Automated malfunction procedure execution to diagnose problems, (7) Look ahead capability to planned MSRR-1 activities in the onboard timeline. And finally, the logic to calculate telemetry values will be deactivated, and the same environment will interface to the incoming data for the real-time telemetry stream to schematically represent the onboard hardware configuration. G2 will be the foundation for the real-time monitoring and control environment. In summary, our MSRR-1 simulation model spans many elements of the life cycle development of this project: Engineering Analysis, Test and Checkout, Training of Crew and Ground Personnel, and Real-time monitoring and control. By utilizing the unique features afforded by an expert system development environment, we have been able to synergize a powerful tool capable of addressing our project needs at every phase of project development.

Rice, Amanda↗
DOE OSTI2026

Two-Stage Wildlife Event Classification for Edge Deployment

Camera-based wildlife monitoring is often overwhelmed by non-target triggers and slowed by manual review or cloud-dependent inference, which can prevent timely intervention for high stakes human–wildlife conflicts. Our key contribution is a deployable, fully offline edge vision sensor that achieves near-real-time, highly accurate wildlife event classification by combining detector-based empty-image suppression with a lightweight classifier trained with a staged transfer-learning curriculum. Specifically, Stage 1 uses a pretrained You Only Look Once (YOLO)-family detector for permissive animal localization and empty-trigger suppression, and Stage 2 uses a lightweight EfficientNet-based binary classifier to confirm puma on detector crops and gate downstream actions. Our design is robust to low-quality nighttime monochrome imagery (motion blur, low contrast, illumination artifacts, and partial-body captures) and operates using commercially available components in connectivity-limited settings. In field deployments running since May 2025, end-to-end latency from camera trigger to action command is approximately 4 s. Ablation studies using a dataset of labeled wildlife images (pumas, not pumas) show that the two-stage approach substantially reduces false alarms in identifying pumas relative to a full-image classifier while maintaining high recall. On the held-out test set (N = 1434 events), the proposed two-stage cascade achieves precision 0.983, recall 0.975, F1 0.979, accuracy 0.986, and balanced accuracy 0.983, with only 8 false positives and 12 false negatives. The system can be easily adapted for other species, as demonstrated by rapid retraining of the second stage to classify ringtails. Downstream responses (e.g., notifications and optional audio/light outputs) provide flexible actuation capabilities that can be configured to support intervention.

58 GEOSCIENCES↗