Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Model classification”

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 1,261 records · Page 70
All sourcesNASA NTRSDOE OSTI
NASA NTRS2012

VERITAS Observations of Six Bright, Hard-Spectrum Fermi-LAT Blazars

We report on VERITAS very-high-energy (VHE; E >= 100 GeV) observations of six blazars selected from the Fermi Large Area Telescope First Source Catalog (1FGL). The gamma-ray emission from 1FGL sources was extrapolated up to the VHE band, taking gamma-ray absorption by the extragalactic background light into account. This allowed the selection of six bright, hard-spectrum blazars that were good candidate TeV emitters. Spectroscopic redshift measurements were attempted with the Keck Telescope for the targets without Sloan Digital Sky Survey (SDSS) spectroscopic data. No VHE emission is detected during the observations of the six sources described here. Corresponding TeV upper limits are presented, along with contemporaneous Fermi observations and non-concurrent Swift UVOT and XRT data. The blazar broadband spectral energy distributions (SEDs) are assembled and modeled with a single-zone synchrotron self-Compton model. The SED built for each of the six blazars show a synchrotron peak bordering between the intermediate- and high-spectrum-peak classifications, with four of the six resulting in particle-dominated emission region.

RGB J0316+090↗
NASA NTRS2021

Deep Domain Adaptation based Cloud Type Detection using Active and Passive Satellite Data

Domain adaptation techniques have been developed to handle data from multiple sources or domains. Most existing domain adaptation models assume that source and target domains are homogeneous, i.e., they have the same feature space. Nevertheless, many real world applications often deal with data from heterogeneous domains that come from completely different feature spaces. In our remote sensing application, data in source domain (from an active spaceborne Lidar sensor CALIOP onboard CALIPSO satellite) contain 25 attributes, while data in target domain (from a passive spectroradiometer sensor VIIRS onboard Suomi-NPP satellite) contain 20 different attributes. CALIOP has better representation capability and sensitivity to aerosol types and cloud phase, while VIIRS has wide swaths and better spatial coverage but has inherent weakness in differentiating atmospheric objects on different vertical levels. To address this mismatch of features across the domains/sensors, we propose a novel end-to-end deep domain adaptation with domain mapping and correlation alignment (DAMA) to align the heterogeneous source and target domains in active and passive satellite remote sensing data. It can learn domain invariant representation from source and target domains by transferring knowledge across these domains, and achieve additional performance improvement by incorporating weak label information into the model (DAMA-WL). Our experiments on a collocated CALIOP and VIIRS dataset show that DAMA and DAMA-WL can achieve higher classification accuracy in predicting cloud types.

domain adaptation↗
NASA NTRS1995

Using dark current data to estimate AVIRIS noise covariance and improve spectral analyses

Starting in 1994, all AVIRIS data distributions include a new product useful for quantification and modeling of the noise in the reported radiance data. The 'postcal' file contains approximately 100 lines of dark current data collected at the end of each data acquisition run. In essence this is a regular spectral-image cube, with 614 samples, 100 lines and 224 channels, collected with a closed shutter. Since there is no incident radiance signal, the recorded DN measure only the DC signal level and the noise in the system. Similar dark current measurements, made at the end of each line are used, with a 100 line moving average, to remove the DC signal offset. Therefore, the pixel-by-pixel fluctuations about the mean of this dark current image provide an excellent model for the additive noise that is present in AVIRIS reported radiance data. The 61,400 dark current spectra can be used to calculate the noise levels in each channel and the noise covariance matrix. Both of these noise parameters should be used to improve spectral processing techniques. Some processing techniques, such as spectral curve fitting, will benefit from a robust estimate of the channel-dependent noise levels. Other techniques, such as automated unmixing and classification, will be improved by the stable and scene-independence noise covariance estimate. Future imaging spectrometry systems should have a similar ability to record dark current data, permitting this noise characterization and modeling.

Boardman, Joseph W.↗
DOE OSTI2026

Genomic Language model for Annotation of Repetitive Elements (GLARE) v1.0

GLARE (Genomic Language model for Annotation of Repetitive Elements) is a tool that classifies transposable elements (TEs)—the mobile, repetitive DNA sequences that make up large fractions of eukaryotic genomes. GLARE fine-tunes the NTv3-650M genomic language model on a harmonized collection of curated TE sequences from the PanTEon and Repbase reference databases, assigning each input sequence to one of 11 orders and 32 superfamilies in a Wicker-compatible taxonomy. Features. From nucleotide FASTA input, GLARE outputs per-sequence predictions, class summaries, composition figures, and an annotated FASTA. It provides calibrated confidence scores with optional abstention and runs on CPU or GPU. Uses. GLARE serves as a classification component in genome-annotation pipelines, downstream of TE discovery, supporting genome annotation and comparative and evolutionary genomics. Advantages. GLARE is the first repeat-element classifier to leverage a pretrained genomic language model. Combined with multi-database training, this approach outperformed all nine classifiers in the PanTEon benchmark, generalized better to unseen taxonomic clades, and remained robust to sequence orientation—a common failure mode of existing tools.

Bruna, Tomas [Lawrence Berkeley National Laborator↗
DOE OSTI2021

X-Ray Spectra and Multiwavelength Machine Learning Classification for Likely Counterparts to Fermi 3FGL Unassociated Sources

We conduct X-ray spectral fits on 184 likely counterparts to Fermi-LAT 3FGL unassociated sources. Characterization and classification of these sources allows for more complete population studies of the high-energy sky. Most of these X-ray spectra are well fit by an absorbed power-law model, as expected for a population dominated by blazars and pulsars. A small subset of seven X-ray sources have spectra unlike the power law expected from a blazar or pulsar and may be linked to coincident stars or background emission. We develop a multiwavelength machine learning classifier to categorize unassociated sources into pulsars and blazars using gamma-ray and X-ray observations. Training a random forest (RF) procedure with known pulsars and blazars, we achieve a cross-validated classification accuracy of 98.6%. Applying the RF routine to the unassociated sources returned 126 likely blazar candidates (defined as P {sub bzr} ≥ 90%) and five likely pulsar candidates (P {sub bzr} ≤ 10%). Our new X-ray spectral analysis does not drastically alter the RF classifications of these sources compared to previous works, but it builds a more robust classification scheme and highlights the importance of X-ray spectral fitting. Our procedure can be further expanded with UV, visual, or radio spectral parameters or by measuring flux variability.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1991

Classification of multifrequency multilook synthetic aperture radar data

A technique for segmentation of multifrequency multilook intensity synthetic aperture radar (SAR) data into regions of homogeneous and similar backscatter characteristics is presented. Two statistical models, one for the multifrequency multilook SAR intensities and the other for the distribution of the region labels, are combined to obtain the a posteriori probability distribution function of the region labels given the multifrequency speckled intensities. As the maximization of the posterior distribution is computationally intensive, a suboptimal technique for region labeling is proposed. Several examples using both simulated and real multifrequency multilook imagery are given to illustrate the performance of the algorithm.

Rignot, Eric↗
NASA NTRS2019

Feature Learning for Multispectral Satellite Imagery Classification Using Neural Architecture Search

Automated classification of remote sensing data is an integral tool for earth scientists, and deep learning has proven very successful at solving such problems. However, building deep learning models to process the data requires expert knowledge of machine learning. We introduce DELTA, a software toolkit to bridge this technical gap and make deep learning easily accessible to earth scientists. Visual feature engineering is a critical part of the machine learning lifecycle, and hence is a key area that will be automated by DELTA. Hand-engineered features can perform well, but require a cross functional team with expertise in both machine learning and the specific problem domain, which is costly in both researcher time and labor. The problem is more acute with multispectral satellite imagery, which requires considerable computational resources to process. In order to automate the feature learning process, a neural architecture search samples the space of asymmetric and symmetric autoencoders using evolutionary algorithms. Since denoising autoencoders have been shown to perform well for feature learning, the autoencoders are trained on various levels of noise and the features generated by the best performing autoencoders evaluated according to their performance on image classification tasks. The resulting features are demonstrated to be effective for Landsat-8 flood mapping, as well as benchmark datasets CIFAR10 and SVHN.

Robert Campbell↗
NASA NTRS2009

Land-Use and Land-Cover Change around Mobile Bay, Alabama from 1974-2008

This document summarizes the major findings of a Gulf of Mexico Application Pilot project led by NASA Stennis Space Center (SSC) in conjunction with a regional collaboration network of the Gulf of Mexico Alliance (GOMA). NASA researchers processed and analyzed multi-temporal Landsat data to assess land-use and land-cover (LULC) changes in the coastal counties of Mobile and Baldwin, AL between 1974 and 2008. Our goal was to create satellite-based LULC data products using methods that could be transferable to other coastal areas of concern within the Gulf of Mexico. The Mobile Bay National Estuary Program (MBNEP) is the primary end-user, however, several other state and local groups may benefit from the project s data products that will be available through NOAA-NCDDC s Regional Ecosystem Data Management program. Mobile Bay is a critical ecologic and economic region in the Gulf of Mexico and to the entire country. Mobile Bay was designated as an estuary of national significance in 1996. This estuary receives the fourth largest freshwater inflow in the United States. It provides vital nursery habitat for commercially and recreationally important fish species. It has exceptional aquatic and terrestrial bio-diversity, however, its estuary health is influenced by changing LULC patterns, such as urbanization. Mobile and Baldwin counties have experienced a population growth of 1.1% and 20.5% from 2000-2006. Urban expansion and population growth are likely to accelerate with the construction and operation of the ThyssenKrupp steel mill in the northeast portion of Mobile County. Land-use and land-cover change can negatively impact Gulf coast water quality and ecological resources. The conversion of forest to urban cover types impacts the carbon cycle and increases the freshwater and sediment in coastal waters. Increased freshwater runoff decreases salinity and increases the turbidity of coastal waters, thus impacting the growth potential of submerged aquatic vegetation (SAV), which is critical nursing ground for many Gulf fish species. A survey of Mobile Bay SAV showed widespread decreases since the 1940s. Prior to our project, coastal environmental managers in Baldwin and Mobile counties needed more understanding of the historical LULC for properly assessing the impacts of urbanization. In particular, more information on the location and extent of changing urbanization LULC patterns was needed to aid LULC planning and to assess predictions of future LULC patterns. Our products will assist the coastal environmental managers and land-use planners in making better community growth planning decisions. Our project also will help to establish a historical baseline of LULC distributions, which is a fundamental need in any stewardship plan. The primary research objective of our project was to produce historic and current geospatial LULC change products across a 34-year time frame. A multi-decadal coastal LULC change product was the major project deliverable. The geographic extent and nature of change was quantified and assessed for the upland herbaceous, barren, open water, urban, upland forest, woody wetland, and non-woody wetlanddominated land cover types. We focused on regional analyses of decadal-scale urban expansion and watershed-scaled analyses of LULC change for multiple areas of concern to the Mobile Bay NEP (Figure A). We used the following dates to derive LULC classification products from Landsat data: 1974, 1979, 1984, 1988, 1991, 1996, 2001, 2005, and 2008. We assessed the accuracy of our products using randomly sampled locations and digital geospatial reference data including field survey data, high resolution orthorectified aerial photography, high resolution multispectral and panchromatic satellite data displays (from QuickBird and Corona sensors), digital elevation model data, and National Wetlands Inventory wetland cover type data. NOAA s Coastal Change Assessment Program s (C-CAP) and National Land Cover Database (NLCD) procts were used for qualitative comparison in assessing map accuracy. We calculated an average overall classification accuracy of 87% with similar overall accuracies for the older (MSS) and newer (TM and ETM) Landsat LULC products.

Ellis, Jean↗
DOE OSTI2026

Leveraging machine learning to enhance aerosol classification using Single-Particle Mass Spectrometry

Advancing automated classification of atmospheric aerosols from Single-Particle Mass Spectrometry (SPMS) data remains challenging due to overlapping ion signatures, compositional diversity, and limited labeled data. This study evaluates supervised and semi-supervised learning frameworks to enhance aerosol identification by jointly leveraging labeled and unlabeled spectra. Four models were compared: a supervised Support Vector Machine (SVM), a self-training SVM, a stacked autoencoder classifier, and a stacked autoencoder trained using a temporal-ensembling Mean Teacher approach. All models achieved high and stable accuracies (90.0 %–91.1 %), surpassing previous results on the same dataset (87 %) and matching the performance of state-of-the-art deep learning methods. Despite small global metric differences (≤ 1 %), semi-supervised variants yielded up to 5 %–10 % improvements for compositionally rare particle types – such as soot (0.77 % of spectra, F1-score: 0.93–0.97) and hazelnut pollen (0.98 % of spectra, F1-score: 0.97–1.00) – equating to roughly ∼ 187 additional correctly classified spectra. These gains are scientifically significant, as such rare particles exert disproportionate influence on radiative absorption and ice nucleation processes; their improved detection reduces modeled uncertainties in aerosol absorption optical depth and mixed-phase cloud ice nucleation rates. The models' residual misclassifications (≈ 9 %) largely arise from true spectral overlap among chemically adjacent species (e.g., Na- vs. K-feldspar, coated vs. uncoated feldspars), reflecting physical compositional continuity rather than algorithmic error. Collectively, these findings demonstrate that leveraging unlabeled data to learn robust spectral representations and refine classification enhances both fidelity and interpretability, bridging data-driven analysis with aerosol–climate process understanding.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2011

CCSDS Advanced Orbiting Systems Virtual Channel Access Service for QoS MACHETE Model

To support various communications requirements imposed by different missions, interplanetary communication protocols need to be designed, validated, and evaluated carefully. Multimission Advanced Communications Hybrid Environment for Test and Evaluation (MACHETE), described in "Simulator of Space Communication Networks" (NPO-41373), NASA Tech Briefs, Vol. 29, No. 8 (August 2005), p. 44, combines various tools for simulation and performance analysis of space networks. The MACHETE environment supports orbital analysis, link budget analysis, communications network simulations, and hardware-in-the-loop testing. By building abstract behavioral models of network protocols, one can validate performance after identifying the appropriate metrics of interest. The innovators have extended the MACHETE model library to include a generic link-layer Virtual Channel (VC) model supporting quality-of-service (QoS) controls based on IP streams. The main purpose of this generic Virtual Channel model addition was to interface fine-grain flow-based QoS (quality of service) between the network and MAC layers of the QualNet simulator, a commercial component of MACHETE. This software model adds the capability of mapping IP streams, based on header fields, to virtual channel numbers, allowing extended QoS handling at link layer. This feature further refines the QoS v existing at the network layer. QoS at the network layer (e.g. diffserv) supports few QoS classes, so data from one class will be aggregated together; differentiating between flows internal to a class/priority is not supported. By adding QoS classification capability between network and MAC layers through VC, one maps multiple VCs onto the same physical link. Users then specify different VC weights, and different queuing and scheduling policies at the link layer. This VC model supports system performance analysis of various virtual channel link-layer QoS queuing schemes independent of the network-layer QoS systems.

Jennings, Esther H.↗
DOE OSTI2021

Novel usage of deep learning and high-performance computing in long-baseline neutrino oscillation experiments

Mención Internacional en el título de doctorDeep-learning methods are playing a crucial role in numerous scientific and industrialapplications. Over the past two decades, these techniques have helped in the collection,reconstruction, and analysis of large data samples in particle physics experiments. Themain topic of this PhD research is the study of deep-learning techniques in long-baselineneutrino oscillation experiments. Neutrinos are mysterious light elementary particles,and their investigation is essential to shed light on some of the remaining open questionsin physics. The work presented here describes an algorithm based on a convolutionalneural network developed to provide highly accurate and efficient selections of electronneutrino and muon neutrino interactions in the Deep Underground Neutrino Experiment(DUNE). With this algorithm, the electron neutrino (antineutrino) selection efficiencypeaks at 90% (94%) and exceeds 85% (90%) for reconstructed neutrino energies between2-5 GeV. The selection efficiency for muon neutrino (antineutrino) interactions is foundto have a maximum of 96% (97%) and exceeds 90% (95%) efficiency for reconstructedneutrino energies above 2 GeV. When considering all electron neutrino and antineutrinointeractions as signal (both those appearing from oscillations and those intrinsic tothe beam), a selection purity of 90% is achieved. These event selections are criticalto maximise the sensitivity of the experiment to CP-violating effects, key to furtherunderstand the matter-antimatter asymmetry of the Universe.In high-energy physics experiments, deep learning has also been explored for producingfast simulations and physically-motivated manipulations of simulated images. Some ofthose simulations, such as the light production and detection, are very computationallyexpensive and require novel methods to produce the necessary samples while controllingthe varied underlying physics model parameters. To do so, we invented the model-assistedgenerative adversarial network (MAGAN), first validated on simple generic case studiesand then successfully applied to the DUNE photon-detector simulation.Moreover, we also developed graph neural networks for 3D-voxel classification ofambiguities and optical crosstalk for a different particle physics experiment, most preciselyfor the proposed SuperFGD. This novel 3D-granular plastic-scintillator neutrino detectorwill be used to upgrade the near detector of the T2K neutrino oscillation experiment, and our method reports efficiencies and purities of 94-96% per event in the classificationof particle track voxels.Due to the growth and complexity of deep neural networks, researchers have beeninvestigating techniques to train those networks in a more computationally-efficient way.Many efforts have been made by the community to optimise deep-learning models byparallelising or distributing their training computation across multiple devices. In thisthesis, we study an approach based on data locality for those neural networks that cannotbenefit from scaling their computation due to a significant bottleneck in the data I/O.The research also includes a detailed study on the performance of deep neural networkson hardware accelerator boards.Los métodos de aprendizaje profundo son cada vez más utilizados en numerosas aplicacionescientíficas e industriales hoy en día. Durante las dos últimas décadas, estastécnicas se han empleado en la recolección, reconstrucción y análisis de la gran cantidadde datos generados por experimentos de física de partículas. El tema principal de estatesis doctoral es el uso de estos modelos de aprendizaje profundo en experimentos defísica de neutrinos, en concreto en los experimentos de larga distancia DUNE y T2K. Losneutrinos, partículas fundamentales neutras, de las más ligeras del Universo, pueden serclave para explicar algunas de las cuestiones todavía sin resolver en física fundamental.Entre las diferentes contribuciones que esta tesis ha hecho a su estudio, cabe destacar eldesarrollo de un algoritmo basado en una red de neuronas convolucional para seleccionarcon gran eficiencia y precisión las interacciones de neutrinos electrónicos y muónicos enel Deep Underground Neutrino Experiment (DUNE). La eficiencia de selección obtenidapara neutrinos (antineutrinos) electrónicos alcanza un máximo del 90% (94%) y supera el85% (90%) para neutrinos con energías reconstruidas en el rango 2-5 GeV. La selección deneutrinos (antineutrinos) muónicos tiene una eficiencia máxima del 96% (97%) y excedeel 90% (95%) para neutrinos con energías reconstruidas de más de 2 GeV. Considerandocomo señal todas las interacciones de neutrinos y antineutrinos electrónicos (procedentestanto de oscilaciones como intrínsecos en el haz inicial), se logra una pureza en la seleccióndel 90%. Dichas selecciones de eventos son fundamentales para maximizar la sensibilidaddel experimento a los efectos de violació...

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Identifying Climate Patterns Using Clustering Autoencoder Techniques

Abstract The complexity of growing spatiotemporal resolution of climate simulations produces a variety of climate patterns under different projection scenarios. This paper proposes a new data-driven climate classification workflow via an unsupervised deep learning technique that can dimensionally reduce the vast volume of spatiotemporal numerical climate projection data into a compact representation. We aim to identify distinct zones that capture multiple climate variables as well as their future changes under different climate change scenarios. Our approach leverages convolutional autoencoders combined with k -means clustering (standard autoencoder) and online clustering based on the Sinkhorn–Knopp algorithm (clustering autoencoder) across the conterminous United States (CONUS) to capture unique climate patterns in a data-driven fashion from the Geophysical Fluid Dynamics Laboratory Earth System Model with GOLD component (GFDL-ESM2G). The developed approach compresses 70 years of GFDL-ESM2G simulation at 0.125° spatial resolution across the CONUS under multiple warming scenarios to a lower-dimensional space by a factor of 660 000 and then tested on 150 years of GFDL-ESM2G simulation data. The results show that five climate clusters capture physically reasonable and spatially stable climatological patterns matched to known climate classes defined by human experts. Results also show that using a clustering autoencoder can reduce the computational time for clustering by up to 9.2 times when compared to using a standard autoencoder. Our five unique climate patterns resulting from the deep learning–based clustering of the lower-dimensional space thereby enable us to provide insights on hydrometeorology and its spatial heterogeneity across the conterminous United States immediately without downloading large climate datasets. Significance Statement This paper presents a data-driven climate classification approach using unsupervised deep learning to dimensionally reduce climate model outputs and to identify distinct climate regions for their future changes. Our approach compresses climate information for 70 years of Geophysical Fluid Dynamics Laboratory Earth System Model data across the conterminous United States (CONUS) at 0.125° spatial resolution. The results reveal that five climate clusters capture reasonable and stable climatological patterns matched to known climate patterns. The embedded clustering process in deep learning provides ×9.2 times faster execution than the k -means clustering technique. These results give us insight about climate spatial patterns and heterogeneity of hydrological patterns across the conterminous United States without downloading large climate datasets.

Kurihana, Takuya↗
DOE OSTI2023

2022 Prentice Award Lecture: Advancing Retinal Imaging and Visual Function in Patient Management and Disease Mechanisms

Patient-based research plays a key role in probing basic visual mechanisms. Less-well recognized is the role of patient-based retinal imaging and visual function studies in elucidating disease mechanisms, which are accelerated by advances in imaging and function techniques and are most powerful when combined with the results from histology and animal models. A patient's visual complaints can be one key to patient management, but human data are also key to understanding disease mechanisms. Unfortunately, pathological changes can be difficult to detect. Before advanced retinal imaging, the measurement of visual function indicated the presence of pathological changes that were undetectable with existing clinical examination. Over the past few decades, advances in retinal imaging have increasingly revealed the unseen. This has led to great strides in the management of many diseases, particularly diabetic retinopathy and macular edema, and age-related macular degeneration. It is likely widely accepted that patient-based research, as in clinical trials, led to such positive outcomes. Both visual function measures and advanced retinal imaging have clearly demonstrated differences among retinal diseases. Contrary to initial thinking, sight-threatening damage in diabetes occurs to the outer retina and not only to the inner retina. This has been clearly indicated in patient results but has only gradually entered the clinical classifications and understanding of disease etiology. There is strikingly different pathophysiology for age-related macular degeneration compared with photoreceptor and retinal pigment epithelial genetic defects, yet research models and even some treatments confuse these. It is important to recognize the role that patient-based research plays in probing basic visual mechanisms and elucidating disease mechanisms, combining these findings with the concepts from histology and animal models. Thus, this article combines sample instrumentation from my laboratory and progress in the fields of retinal imaging and visual function.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Deep learning models for interpretation of point of care ultrasound in military working dogs

Introduction: Military working dogs (MWDs) are essential for military operations in a wide range of missions. With this pivotal role, MWDs can become casualties requiring specialized veterinary care that may not always be available far forward on the battlefield. Some injuries such as pneumothorax, hemothorax, or abdominal hemorrhage can be diagnosed using point of care ultrasound (POCUS) such as the Global FAST® exam. This presents a unique opportunity for artificial intelligence (AI) to aid in the interpretation of ultrasound images. In this article, deep learning classification neural networks were developed for POCUS assessment in MWDs. Methods: Images were collected in five MWDs under general anesthesia or deep sedation for all scan points in the Global FAST® exam. For representative injuries, a cadaver model was used from which positive and negative injury images were captured. A total of 327 ultrasound clips were captured and split across scan points for training three different AI network architectures: MobileNetV2, DarkNet-19, and ShrapML. Gradient class activation mapping (GradCAM) overlays were generated for representative images to better explain AI predictions. Results: Performance of AI models reached over 82% accuracy for all scan points. The model with the highest performance was trained with the MobileNetV2 network for the cystocolic scan point achieving 99.8% accuracy. Across all trained networks the diaphragmatic hepatorenal scan point had the best overall performance. However, GradCAM overlays showed that the models with highest accuracy, like MobileNetV2, were not always identifying relevant features. Conversely, the GradCAM heatmaps for ShrapML show general agreement with regions most indicative of fluid accumulation. Discussion: Overall, the AI models developed can automate POCUS predictions in MWDs. Preliminarily, ShrapML had the strongest performance and prediction rate paired with accurately tracking fluid accumulation sites, making it the most suitable option for eventual real-time deployment with ultrasound systems. Further integration of this technology with imaging technologies will expand use of POCUS-based triage of MWDs.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

A novel machine learning based identification of potential adopter of rooftop solar photovoltaics

With the proliferation of rooftop solar photovoltaic installations, there is a need to proactively predict consumer potential for solar photovoltaic adoption, for improved electric utility planning and operation. Traditional analytical modeling approaches are limited to a few survey features and a larger part of the survey would remain untouched by the decision model. This article presents a novel, data-driven modeling approach that strategically prunes a large set of consumer profile features using a machine learning framework to train a model for predicting potential solar adoption. The approach utilizes the Gradient Boosting Decision Tree model through a Light Gradient Boosting framework that improves significantly over the poor prediction accuracy of the existing approaches. Model training using focal-loss based supervision is used to overcome the difficulty in identifying the potential adopters that is inherent in conventional data-driven models. In addition, to overcome possible data sparsity in a limited survey sample, a Generative Adversarial Network is presented to create synthetic user samples and its effectiveness on model performance is assessed. A Bayesian optimization approach is used to systematically arrive at the hyperparameters of the proposed model. Validation of the presented approach on a survey data collected by the National Rural Electric Cooperative Association in Virginia in 2018 demonstrates the excellent predictive capability of the machine learning based approach to modeling solar adoption reliably.

14 SOLAR ENERGY↗
DOE OSTI2022

Hybrid Quantum-Classical Neural Networks

Deep learning is one of the most successful and far-reaching strategies used in machine learning today. However, the scale and utility of neural networks is still greatly limited by the current hardware used to train them. These concerns have become increasingly pressing as conventional computers are soon expected to approach the physical limitations that will slow their performance improvements in the near future. For these reasons, scientists have begun to explore alternative computing platforms, like quantum computers, for training neural networks. In recent years, variational quantum circuits have emerged as one of the most successful approaches to quantum deep learning on noisy intermediate scale quantum devices. We propose a hybrid quantum-classical neural network architecture where each neuron is a variational quantum circuit. We empirically analyze the performance of this hybrid neural network on a series of binary classification data sets using a simulated IBM universal quantum computer and a state-of-the-art IBM universal quantum computer. On the simulated hardware, we observe that the hybrid neural network achieves around 10% higher classification accuracy and 20% better minimization of the cost function than an individual variational quantum circuit. On the quantum hardware, we observe that each model only performs well when the qubit and gate count is sufficiently small.

Arthur, Davis↗
DOE OSTI2022

Probabilistic Nanomagnetic Memories for Uncertain and Robust Machine Learning

This project evaluated the use of emerging spintronic memory devices for robust and efficient variational inference schemes. Variational inference (VI) schemes, which constrain the distribution for each weight to be a Gaussian distribution with a mean and standard deviation, are a tractable method for calculating posterior distributions of weights in a Bayesian neural network such that this neural network can also be trained using the powerful backpropagation algorithm. Our project focuses on domain-wall magnetic tunnel junctions (DW-MTJs), a powerful multi-functional spintronic synapse design that can achieve low power switching while also opening the pathway towards repeatable, analog operation using fabricated notches. Our initial efforts to employ DW-MTJs as an all-in-one stochastic synapse with both a mean and standard deviation didn’t end up meeting the quality metrics for hardware-friendly VI. In the future, new device stacks and methods for expressive anisotropy modification may make this idea still possible. However, as a fall back that immediately satisfies our requirements, we invented and detailed how the combination of a DW-MTJ synapse encoding the mean and a probabilistic Bayes-MTJ device, programmed via a ferroelectric or ionically modifiable layer, can robustly and expressively implement VI. This design includes a physics-informed small circuit model, that was scaled up to perform and demonstrate rigorous uncertainty quantification applications, up to and including small convolutional networks on a grayscale image classification task, and larger (Residual) networks implementing multi-channel image classification. Lastly, as these results and ideas all depend upon the idea of an inference application where weights (spintronic memory states) remain non-volatile, the retention of these synapses for the notched case was further interrogated. These investigations revealed and emphasized the importance of both notch geometry and anisotropy modification in order to further enhance the endurance of written spintronic states. In the near future, these results will be mapped to effective predictions for room temperature and elevated operation DW-MTJ memory retention, and experimentally verified when devices become available.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2026

Opportunities in AI/ML for the Rubin LSST Dark Energy Science Collaboration

The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) will produce unprecedented volumes of heterogeneous astronomical data (images, catalogs, and alerts) that challenge traditional analysis pipelines. The LSST Dark Energy Science Collaboration (DESC) aims to derive robust constraints on dark energy and dark matter from these data, requiring methods that are statistically powerful, scalable, and operationally reliable. Artificial intelligence and machine learning (AI/ML) are already embedded across DESC science workflows, from photometric redshifts and transient classification to weak lensing inference and cosmological simulations. Yet their utility for precision cosmology hinges on trustworthy uncertainty quantification, robustness to covariate shift and model misspecification, and reproducible integration within scientific pipelines. This white paper surveys the current landscape of AI/ML across DESC's primary cosmological probes and cross-cutting analyses, revealing that the same core methodologies and fundamental challenges recur across disparate science cases. Since progress on these cross-cutting challenges would benefit multiple probes simultaneously, we identify key methodological research priorities, including Bayesian inference at scale, physics-informed methods, validation frameworks, and active learning for discovery. With an eye on emerging techniques, we also explore the potential of the latest foundation model methodologies and LLM-driven agentic AI systems to reshape DESC workflows, provided their deployment is coupled with rigorous evaluation and governance. Finally, we discuss critical software, computing, data infrastructure, and human capital requirements for the successful deployment of these new methodologies, and consider associated risks and opportunities for broader coordination with external actors.

Aubourg, Eric [APC, Paris] (ORCID:000000025592023X↗