Search NASA⌕ Search

SEARCH · Search NASA

Results for “Bounding boxes”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

YOLO11 to SAM2 pipeline for feature extraction from nuclear test films

The response to the effects of nuclear detonations is supported by models that describe the evolution of the nuclear fireball and cloud and the associated transport of active debris. Validation of those descriptions relies on data from the nuclear test operations. Video records of those events offer a rich source of information that was exploited to a limited extent in historic analyses. Computer vision and machine learning techniques are powerful tools that can be used to increase the number of measurements that can be obtained from those films. In this work, we apply computer vision techniques to automatically track the temporal evolution of the nuclear fireball. In particular, we apply You Only Look Once 11 (YOLO11) and Segment Anything Model 2 (SAM2) in combination with minimal human intervention to digitized versions of the original nuclear test films. As part of the proposed workflow, the YOLO11 model is applied to films to determine bounding boxes for the fireball within each frame. These are then used as inputs to SAM2, which uses image segmentation to determine the fireball boundaries and their temporal evolution. We assess the accuracy of our approach by using it to determine the energy released during the Trinity nuclear test and comparing the results with previous analyses based on manual measurements.

Van Exel, Kimberly [ORNL] (ORCID:0009000877463894)↗
DOE OSTI2020

Separation of overlapping sources in bioacoustic mixtures

Source separation is an important step to study signals that are not easy or possible to record individually. Common methods such as deep clustering, however, cannot be applied to signals of an unknown number of sources and/or signals that overlap in time and/or frequency—a common problem in bioacoustic recordings. This work presents an approach, using a supervised learning framework, to parse individual sources from a spectrogram of a mixture that contains a variable number of overlapping sources. This method isolates individual sources in the time-frequency domain using only one function but in two separate steps, one for the detection of the number of sources and corresponding bounding boxes, and a second step for the segmentation in which masks of individual sounds are extracted. This approach handles the full separation of overlapping sources in both time and frequency using deep neural networks in an applicable manner to other tasks such as bird audio detection. This paper presents method and reports on its performance to parse individual bat signals from recordings containing hundreds of overlapping bat echolocation signals. This method can be extended to other bioacoustic recordings with a variable number of sources and signals that overlap in time and/or frequency.

Izadi, Mohammad Rasool↗
DOE OSTI2020

Panel-Segmentation [SWR-21-18]

Panel-Segmentation contains the scripts for automated metadata extraction of solar PV installations, using satellite imagery coupled with computer vision techniques. In this package, the user can perform the following actions: *Automatically generate a satellite image using a set of lat-long coordinates, and a Google Maps API key. Users would need to set up a Google Cloud account and get a Maps Static API key. Please refer to Setting Up Google Maps Static API Key section for this process. *Perform image segmentation on the satellite image, to locate the solar array(s) in the image on a pixel-by-pixel basis, using an image segmentation model (panel_detection_model.pth). Get classification of the installation (rooftop, ground mounted fixed-tilt or tracking, carport, etc). *Perform azimuth estimation on each solar array cluster in the masked image. *Detect solar panels and get its latitude, longitude, and address within a geographic bounding box through the SOL-Searcher Pipeline. *Detect and calculate hurricane damage on solar installations given pre-hurricane and post-hurricane satellite imagery through the Hurricane Detection Pipeline. *Detect and calculate hail damage on solar installations given satellite imagery through the Hail Detection pipeline. *Convert NOAA MESH (Maximum Estimated Size of Hail) grib2 files into kml or geojson files. *Estimate tilt and azimuth of a solar array by processing USGS LiDAR data for the array’s location.

Edun, Ayobami↗
DOE OSTI2021

MenuFramework

The Menu Framework is a reusable Extended Reality multi-level menu system for the Unity Development Platform. The menu structure is architected for reusability to suit whatever need the developer may have for a multi-level, reusable menu framework. Menu Framework's architecture, GUI, and functionality are based on the paper "Extended Reality for Enhanced Training and Knowledge Capture" (SAND2020-2361C). This tool uses the Microsoft Mixed Reality ToolKit (MRTK) built in functionality to provide a suite of functionalities including bounding box, follow me, minimize, maximize, settings, and help commands. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525. SAND2021-1507 O

Klein, BrandonThorin↗
DOE OSTI2026

NLR Data Processing Pipeline for MADIS [SWR-26-050]

The NLR Data Processing Pipeline for MADIS software package is for downloading, processing, and performing QA/QC on MADIS data. Designed to handle the following steps: 1) Download all MADIS data as compressed netcdf files for a given time period. 2) Unpack netcdf files into timeseries csvs for each coordinate within the given bounding box. 3) Process the csvs to filter according to quality control checks and convert variables to correct units. 4) Write processed csvs to a single nc file.

Benton, Brandon [National Laboratory of the Rockie↗
DOE OSTI2024

Effects of machine learning errors on human decision-making: manipulations of model accuracy, error types, and error importance

Abstract This study addressed the cognitive impacts of providing correct and incorrect machine learning (ML) outputs in support of an object detection task. The study consisted of five experiments that manipulated the accuracy and importance of mock ML outputs. In each of the experiments, participants were given the T and L task with T-shaped targets and L-shaped distractors. They were tasked with categorizing each image as target present or target absent. In Experiment 1, they performed this task without the aid of ML outputs. In Experiments 2–5, they were shown images with bounding boxes, representing the output of an ML model. The outputs could be correct (hits and correct rejections), or they could be erroneous (false alarms and misses). Experiment 2 manipulated the overall accuracy of these mock ML outputs. Experiment 3 manipulated the proportion of different types of errors. Experiments 4 and 5 manipulated the importance of specific types of stimuli or model errors, as well as the framing of the task in terms of human or model performance. These experiments showed that model misses were consistently harder for participants to detect than model false alarms. In general, as the model’s performance increased, human performance increased as well, but in many cases the participants were more likely to overlook model errors when the model had high accuracy overall. Warning participants to be on the lookout for specific types of model errors had very little impact on their performance. Overall, our results emphasize the importance of considering human cognition when determining what level of model performance and types of model errors are acceptable for a given task.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Data from: "Warming and the dependence of limber pine (Pinus flexilis) establishment on summer soil moisture within and above its current elevation range"

This data package contains data that were used for analysis in “Warming and the dependence of limber pine (Pinus flexilis) establishment on summer soil moisture within and above its current elevation range”, by Moyes et al. 2013. All data collection and field research were completed on Niwot Ridge, Colorado, USA.This data package contains nine comma-separated-values (.csv) files, one text (.txt) file, and two zipped seedling folders that were used for leaf area analysis. One zipped folder contains 468 .jpg photographs of seedlings, and the second contains 468 corresponding Image J-processed .jpg images that include silhouette leaf area values. .csv and .txt files can be opened using any compatible simple text-editor software such as TextEdit (Mac) and Notepad (Windows); .csv’s can also be opened using R and Microsoft Excel. Image files can be opened using Preview (Mac) and Photos (Windows). In addition, there are a total of 31 Microsoft Excel files: three .xlsx files, and 28 raw Li-Cor output .xls files. This data user’s guide is available in .pdf format, and can be opened using Adobe Acrobat Reader, or any other compatible file viewing software. Geospatial data showing field site locations are also included in the archive for use and reference. There are two geospatial formats in this archive: ESRI shapefiles (.shp) and keyhole markup-language (.kml) files. Both file types contain bounding box information, with the former being polygons, and the latter containing corner coordinates for each site. ESRI shapefiles can be opened using any geospatial software compatible with the file type (such as ESRI’s ArcGIS suite and QGIS), and .kml files are compatible with Google Earth and Google Maps.--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------Continued changes in climate are projected to alter the geographic distributions of plant species, in part by affecting where individuals can establish from seed. We tested the hypothesis that warming promotes uphill redistribution of subalpine tree populations by reducing cold limitation at high elevation and enhancing drought stress at low elevation. We seeded limber pine (Pinus flexilis) into plots with combinations of infrared heating and water addition treatments, at sites positioned in lower subalpine forest, the treeline ecotone, and alpine tundra. In 2010, first-year seedlings were assessed for physiological performance and survival over the snow-free growing season. Seedlings emerged in midsummer, about 5–8 weeks after snowmelt. Low temperature was not observed to limit seedling photosynthesis or respiration between emergence and October, and thus experimental warming did not appear to reduce cold limitation at high elevation. Instead, gas exchange and water potential from all sites indicated a prevailing effect of summer moisture stress on photosynthesis and carbon balance. Infrared heaters raised soil growing degree days (base 5 °C, p < 0.001) and August–September mean soil temperature (p < 0.001). Despite marked differences in vegetation cover and meteorological conditions across sites, volumetric soil moisture content (θ) at 5–10 cm below 0.16 and 0.08 m^3 m^(−3) consistently corresponded with moderate and severe indications of drought stress in midday stem water potential, stomatal conductance, photosynthesis, and respiration. Seedling survival was greater in watered plots than in heated plots (p = 0.01), and negatively related to soil growing degree days and duration of exposure to θ < 0.08 m^3 m^(−3) in a stepwise linear regression model (p < 0.0001). We concluded that seasonal moisture stress and high soil surface temperature imposed a strong limitation to limber pine seedling establishment across a broad elevation gradient, including at treeline, and that these limitations are likely to be enhanced by further climate warming.--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------Maintenance log:Amended file name error in Data User's Guide May 19 2022

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Metagenome-assembled genomes measured at 3 depths during snowmelt period in East River, CO (March, May, and June, September 2017)

Snowmelt is a critical biogeochemical period that accounts for large nitrogen (N) export events from high-elevation watersheds. Soil microbial populations bloom and immobilize N during snowmelt, yet the population size crashes in spring, which releases a pulse of soil N. We sought to discover the N sources fueling this microbial bloom and determine the fate of N following microbial die-off. Here, focusing on the snowmelt period within a headwater catchment of the Upper Colorado River Basin (East River, CO), we deployed strain-resolved metagenomics to identify the metabolic pathways and processes that mobilize soil N during and after snowmelt. Soil metagenome samples were taken from 6 snowpits from 3 depths (0-5cm, 5-15cm, >15cm) at 4 time points during snowmelt period (March 2017, May 2017, and June 2017, September 2017) generating 48 metagenomes. We reconstructed 474 metagenome-assembled genomes (MAGs) across all metagenomes.All 48 metagenomes were sequenced at JGI and raw data can be found under JGI (Joint Genome Institute) GOLD Study Gs0135149. Metagenome assemblies from IMG under the same study were used for genome binning. This dataset (1) a zip file of 474 MAGs (as fasta files, Gs0135149_bins_tar.gz), (2) sample metadata file with sample IGSNs (International Generic Sample Numbers) (samples.csv), (3) bounding box coordinates for the sampled locations (Gs0135149.kml), (4) metagenome metadata file listing IMG/M (Integrated Microbial Genomes/Metagenomes) metagenome accessions linking samples to metagenomes (metagenomes.csv), (5) location metadata file (locations.csv), (6) file-level metadata file (flmd.csv) and (7) data dictionary (dd.csv) file.This work was supported by the Watershed Function Science Focus Area at Lawrence Berkeley National Laboratory funded by the US Department of Energy, Office of Science, Biological and Environmental Research under Contract No. DE-AC02-05CH11231.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Metagenome-assembled genomes from topsoils along a hillslope water gradient across early snowmelt to late summer in East River, CO

Drought is changing the American Mountain West at unprecedented rates with unknown consequences to soil microbiome composition and function. As a part of LBNL Watershed Science Focus Area (SFA), we investigated shifts in microbial community and transcriptional activity on a subalpine conifer-meadow transition zone throughout the summer of 2023 as soil dried down. This work took place in Crested Butte, CO on Snodgrass mountain, using a proxy for drought conditions.Here we present metagenome assembled genomes (MAGs) for the bacterial and archaeal community at 0-10cm from three sites along a hillslope water gradient across five timepoints from early snowmelt to late summer. 42 metagenomes were sequenced at Joint Genome Institute (JGI) and can be found under the JGI GOLD (Genomes Online Database) sequencing project Gs0166660. Metagenomes were assembled through an inhouse pipeline (see methods), binned using four autobinners (concoct, maxbin2, metabat2, and vamb) and consolidated using dastool. The consolidated bins from all metagenomes were pooled, filtered by completeness (>70%) and contamination (<10%), and dereplicated at 95% ANI using drep. This dataset (1) a zip file of 157 MAGs (as fasta files, Gs0166660_bins_tar.gz), (2) sample metadata file with sample IGSNs (International Generic Sample Numbers) (samples.csv), (3) bounding box coordinates for the sampled locations (Gs0166660.kml), (4) metagenome assembly and coassembly metadata file listing IMG/M (Integrated Microbial Genomes/Metagenomes) metagenome accessions linking samples to metagenomes (EastRiver_Drought_ESSDive_Metadata.csv), (5) location metadata file (locations.csv), (6) file-level metadata file (flmd.csv) and (7) data dictionary (dd.csv) file.This work was supported by the Watershed Function Science Focus Area at Lawrence Berkeley National Laboratory funded by the US Department of Energy, Office of Science, Biological and Environmental Research under Contract No. DE-AC02-05CH11231.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Metagenome-assembled genomes from topsoils collected during NEON campaign in East River, CO (06/14/2018-06/28/2018)

The Watershed Function Science Focus Area (WF SFA) at Lawrence Berkeley National Lab is working to build a mechanistic understanding of the distribution and dynamics of biogeochemical processes in mountainous watersheds and their response to perturbation. In June 2018, the NEON (National Ecological Observatory Network) Airborne Observatory Platform (AOP) performed a taskable airborne imaging campaign to collect visible to shortwave infrared (VSWIR) imaging spectroscopy and LiDAR data across 330 km2 in the Upper East River at Crested Butte, CO. We conducted a parallel ground sampling campaign to sample vegetation traits, as well as soil physical, chemical, and microbiological characteristics. We collected these samples from 438 sites across 12 locations spanning much of the elevation, topographic, and geologic variability across the study area. A subset of 250 samples were used for soil metagenomics which is presented here. In addition, at each site, vegetation samples were collected to measure species-specific leaf water content and leaf mass area, foliar elemental composition and foliar CN stable isotope ratios. Soil samples were collected to measure soil physical properties which include bulk density and soil texture analysis. A suite of soil chemical properties was measured from the samples collected at each site, including pH, organic matter, concentrations exchangeable cations, total elemental composition, and the concentrations of extractable N pools (e.g. total free amino acids, ammonium, nitrate, dissolved organic N, and total dissolved N). Additionally, we have measured soil microbial biomass CN stoichiometry. Here, we present 1982 metagenome-assembled genomes (MAGs) for the bacterial and archaeal community from topsoil collected from during NEON 2018 campaign. All metagenomes were sequenced at JGI (Joint Genome Institute) (GOLD Study ID: Gs0149986). Metagenomes were assembled using JGI Metagenome Workflow (10.1128/mSystems.00804-20). The dataset includes (1) zip files for 1982 MAG fasta files (neon_genomes1-5.tar.gz, split into 5 tarballs to keep tarballs under 0.5 GB), (2) neon_Gs0149986_samples_soilproperties_metagenomes.csv: the sample information together with the accession numbers for the underlying metagenomes and the associated soil physical and chemical measurements in NMDC (National Microbiome Data Collaborative) compliant format, (3) neon_Gs0149986.kml: location bounding box file for the sampled locations, (4) samples.csv: sample metadata file used to register Internationall Generic Sample Numbers (IGSNs), (5) flmd.csv: file level metadata file, and (6) dd.csv: data dictionary file. This work was supported by the Watershed Function Science Focus Area at Lawrence Berkeley National Laboratory funded by the US Department of Energy, Office of Science, Biological and Environmental Research under Contract No. DE-AC02-05CH11231.

2018 NEON and 2025 CHESS Campaigns↗
DOE OSTI2020

HFIRCON Version 1.0.5 User Guide

The High Flux Isotope Reactor (HFIR) Controller (HFIRCON) code is a collection of python routines and C plugins that automate the workflow for fuel and single- or multicycle target depletion analyses for HFIR at Oak Ridge National Laboratory (ORNL). This code calls the LAVAMINT (LAVA Model Interrogator) parallel (MCNP) Monte Carlo N-Particle model interrogator to stochastically calculate cell volumes and bounding boxes, the ADVANTG (Automatic Variance Reduction Generation) code package for all variance reduction and source biasing calculations, the ORNL-Transformative Neutronics/MCNP5 transport solver for all transport solutions, and the MSX_DEPLETE module to perform all depletion calculations via the ORIGEN (Oak Ridge Isotope Generation) application programming interface. It also performs a robust set of postprocessing functions to automatically provide summaries of several key metrics that are common to a wide variety of typical HFIR design and safety-basis analyses.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2024

AEPF: Attention-Enabled Point Fusion for 3D Object Detection

Current state-of-the-art (SOTA) LiDAR-only detectors perform well for 3D object detection tasks, but point cloud data are typically sparse and lacks semantic information. Detailed semantic information obtained from camera images can be added with existing LiDAR-based detectors to create a robust 3D detection pipeline. With two different data types, a major challenge in developing multi-modal sensor fusion networks is to achieve effective data fusion while managing computational resources. With separate 2D and 3D feature extraction backbones, feature fusion can become more challenging as these modes generate different gradients, leading to gradient conflicts and suboptimal convergence during network optimization. To this end, we propose a 3D object detection method, Attention-Enabled Point Fusion (AEPF). AEPF uses images and voxelized point cloud data as inputs and estimates the 3D bounding boxes of object locations as outputs. An attention mechanism is introduced to an existing feature fusion strategy to improve 3D detection accuracy and two variants are proposed. These two variants, AEPF-Small and AEPF-Large, address different needs. AEPF-Small, with a lightweight attention module and fewer parameters, offers fast inference. AEPF-Large, with a more complex attention module and increased parameters, provides higher accuracy than baseline models. Experimental results on the KITTI validation set show that AEPF-Small maintains SOTA 3D detection accuracy while inferencing at higher speeds. AEPF-Large achieves mean average precision scores of 91.13, 79.06, and 76.15 for the car class’s easy, medium, and hard targets, respectively, in the KITTI validation set. Results from ablation experiments are also presented to support the choice of model architecture.

Chemistry↗
DOE OSTI2025

Edge ML for CAN bus intrusion detection in AVs

Autonomous Vehicles (AVs) are revolutionizing transportation, but their reliance on interconnected cyber-physical systems exposes them to unprecedented cybersecurity risks. This study addresses the critical challenge of detecting real-time cyber intrusions in self-driving vehicles by leveraging a dataset from the Udacity self-driving car project. We simulate four high-impact attack vectors, Denial of Service (DoS), spoofing, replay, and fuzzy attacks, by injecting noise into spatial features (e.g., bounding box coordinates) to replicate adversarial scenarios. We develop and evaluate two lightweight neural network architectures (NN-1 and NN-2) alongside a logistic regression baseline (LG-1) for intrusion detection. The models achieve exceptional performance, with NN-2 attaining an AUC score of 93.15% and 93.15% accuracy, demonstrating their suitability for edge deployment in AV environments. Through explainable AI techniques, we uncover unique forensic fingerprints of each attack type, such as spatial corruption in fuzzy attacks and temporal anomalies in replay attacks, offering actionable insights for feature engineering and proactive defense. Visual analytics, including confusion matrices, ROC curves, and feature importance plots, validate the models' robustness and interpretability. This research sets a new benchmark for AV cybersecurity, delivering a scalable, field-ready toolkit for Original Equipment Manufacturers (OEMs) and policymakers. By aligning intrusion fingerprints with SAE J3061 automotive security standards, we provide a pathway for integrating machine learning into safety-critical AV systems. Our findings underscore the urgent need for security-by-design AI, ensuring that AVs not only drive autonomously but also defend autonomously. This work bridges the gap between theoretical cybersecurity and life-preserving engineering, offering a leap toward safer, more secure autonomous transportation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Automated Classification of Vehicle Movements at Signalized Intersections Using Vehicle Trajectories

Accurate vehicle movement classification through signalized intersections is of paramount importance to the analysis of intersection performance and the optimization of traffic control strategies. Conventional techniques for tracking vehicle turning movements depend on infrastructure-based strategies like human counts, loop detectors, and video analytics, all of which are costly, prone to errors, and spatially constrained. High-frequency trajectory data can be utilized to determine vehicle movement patterns in a scalable and infrastructure-independent method due to the adoption of connected vehicles (CVs). In recent years, several studies have utilized connected vehicle data to generate performance measures. Most of the trajectory-based performance measures approaches, however, require map matching-i.e., extracting geospatial references from maps to identify the movements that individual vehicles make at a signalized intersection. These approaches are often time-consuming and hinder scalability since geographic features need to be provided for an analysis to be conducted. Map matching methods are prone to errors as different map versions change these geographic features. This research presents a novel automatic classification pipeline that uses CV trajectory data to classify vehicle movements at signalized crossings, specifically pass-through left-turn and right-turn maneuvers. The process starts by filtering trips that cross a spatial bounding box that has been defined at the target intersection. Approach and departure headings for each trajectory crossing the boundary are computed and are clustered together to identify dominant movements. The proposed algorithm is used to classify the movement of vehicles at 10 intersections in the state of California, and the results indicate that the algorithm can classify movements at these intersections with varying traffic volumes and road network configurations, all in a map-less framework with no need for conflation of vehicle trajectories to a digital base map.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Transparent Object Tracking Benchmark

Visual tracking has achieved considerable progress in recent years. However, current research in the field mainly focuses on tracking of opaque objects, while little attention is paid to transparent object tracking. In this paper, we make the first attempt in exploring this problem by proposing a Transparent Object Tracking Benchmark (TOTB). Specifically, TOTB consists of 225 videos (86K frames) from 15 diverse transparent object categories. Each sequence is manually labeled with axis-aligned bounding boxes. To the best of our knowledge, TOTB is the first benchmark dedicated to transparent object tracking. In order to understand how existing trackers perform and to provide comparison for future research on TOTB, we extensively evaluate 25 state-of-the-art tracking algorithms. The evaluation results exhibit that more efforts are needed to improve transparent object tracking. Besides, we observe some nontrivial findings from the evaluation that are discrepant with some common beliefs in opaque object tracking. For example, we find that deeper features are not always good for improvements. Moreover, to encourage future research, we introduce a novel tracker, named TransATOM, which leverages transparency features for tracking and surpasses all 25 evaluated approaches by a large margin. By releasing TOTB, we expect to facilitate future research and application of transparent object tracking in both the academia and industry.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Neutrino Interaction Identification for the DUNE Trigger

The DUNE will be a long baseline neutrino oscillation experiment using a high purity muon neutrino beam and near detector, both located at the FNAL, and a far detector hosted 1300 km downstream at the SURF. The 10 kt fiducial mass of LAr will allow DUNE to have a rich off-beam neutrino physics programme, including the study of neutrino signals from core collapse supernovae. The SP DUNE FD module will read out ionisation data at a rate of 1.2 TB\textsuperscript{-1} whilst only a total data volume of 30 PB per year can be permanently stored. DUNE will make use of FPGA resources in the front-end of the DAQ as part of the necessitated triggering system. This thesis presents a validation study of the FPGA-based TPG in the front-end DAQ using data collected by the ProtoDUNE experiment hosted at the CERN. The FPGA-based TPG was utilised as the first stage of a baseline SNB trigger whose performance was evaluated using simulated neutrino interactions for a $11.2 m_\odot$ progenitor star. The efficiency of the baseline SNB trigger was determined to have a lower limit of $97.7\substack{+ 0.2\\ -0.3}\%$ for supernovae at a distance of 20kpc, achieving the technical requirements set out for DUNE. To improve the performance of the SNB trigger at greater SNB distances, the use of a bounding box proposal network, YOLOv3, was explored. This was found to improve the efficiency of the SNB trigger to 100\% up to the far side of the Milky Way galaxy and to $92.5\substack{+ 0.5\\ -0.5}\%$ at the Large Magellanic Cloud.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

A Review on the State of the Art of Machine Learning and Satellite Imaging: Detecting Scene Changes in Selected Nuclear Fuel Cycle Datasets

The timely detection of clandestine nuclear facilities is one of the greatest challenges faced by the International Atomic Energy Agency’s (IAEA). Idaho National Laboratory is currently applying machine learning (ML) to existing satellite imagery (SI) datasets to find facilities within the nuclear fuel life cycle, with primary focus placed on identifying critical predecessor (i.e., fuel fabrication and fuel enrichment) and successor (i.e., nuclear power plants) facilities. This could provide a satellite image methodology that the IAEA could leverage to discover clandestine facilities. The work presented in this paper describes the evolution of a workflow developed by this team for object detection related to critical infrastructure by expanding that workflow for the purpose of identifying nuclear fuel cycle components and automating dependency assessments. This will be done using two methods housed within a single pipeline. The first method involves implementing a DenseNet161 convolutional neural network to classify the images and explain the results using Local Interpretable Model-Agnostic Explanations (LIME). The second method implements You Only Look Once version 5 (YoloV5), to detect objects within images, provide a probability for the detection, and provide a bounding box that corresponds to the object of interest. The results of this work are anticipated to provide a clear picture of this portion of the nuclear fuel cycle and perform as a stand-alone tool for image assessment that can be expanded to additional fuel cycle components and implemented in international safeguards and national security domains. This capability addresses the IAEA’s need to detect undeclared nuclear materials and activities within a state while encompassing the entire nuclear fuel cycle.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Interactive Rotated Object Detection for Novel Class Detection in Remotely Sensed Imagery

In this paper we propose IRTR-DETR an Interactive and Real-Time Rotated DEtection TRansformer that extends IRTDETR to predict rotated bounding boxes. IRTR-DETR maintains the Human-In-The-Loop (HIL) workflow of IRTDETR but introduces rotation-aware heads for improved detection of objects with arbitrary orientations. Similarly to IRTDETR IRTR-DETR can be trained with a small labeled sample set in an interactive setting but we show that it can also be pretrained on related but not identical data--such as a building damage dataset--before being applied to tasks like identifying buildings under construction. We demonstrate the efficacy of our approach on the publicly available Tiny-DOTA and xBD dataset as well as two study-cases on proprietary datasets of greenhouses and houses under construction ("waffle homes"). Detecting greenhouses is highly relevant in the context of damage assessment while "waffle homes" aid understanding typical floorplans and building codes in different areas both thereby supporting population modeling emergency response and policy planning. Our method outperforms the state of the art in interactive rotated object detection on the Tiny-DOTA dataset by 5.7 percent and improves upon the non interactive RTDETR by 7.85 to 19.39 percent (depending on the number of provided samples) while maintaining its real-time efficiency.

Burges, Marvin [ORNL] (ORCID:0000000312690769)↗