Search NASA⌕ Search

SEARCH · Search NASA

Results for “Bayesian 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.

162 records · Page 9
All sourcesNASA NTRSDOE OSTI
NASA NTRS2024

XLSSC 122 Caught in the Act of Growing Up: Spatially Resolved SZ Observations of a z=1.98 Galaxy Cluster

Context. How protoclusters evolved from sparse galaxy overdensities to mature galaxy clusters is still not well understood. In this context, detecting and characterizing the hot intracluster medium (ICM) at high redshifts (z ∼ 2) is key to understanding how the continuous accretion from the filamentary large-scale structure and the mergers along it impact the first phases of cluster formation. Aims. We study the dynamical state and morphology of the z = 1:98 galaxy cluster XLSSC 122 with high-resolution observations (≈5″) of the ICM through the Sunyaev–Zeldovich (SZ) effect. XLSSC 122 is the highest redshift optically confirmed galaxy cluster found in an unbiased, widefield survey. Methods. Via Bayesian forward modeling, we mapped the ICM on scales from the virial radius down to the core of the cluster. To constrain such a broad range of spatial scales, we employed a new technique that jointly forward-models parametric descriptions of the pressure distribution to interferometric ACA and ALMA observations and multiband imaging data from ACT. Results. We detect the SZ effect with 11σ significance in the ALMA+ACA observations and find a flattened inner pressure profile that is consistent with a noncool core classification with a significance of ≥3σ. In contrast to the previous works, we find better agreement between the SZ effect signal and the X-ray emission as well as the cluster member distribution. Further, XLSSC 122 exhibits an excess of SZ flux in the south of the cluster where no X-ray emission is detected. By reconstructing the interferometric observations and modeling in the uv-plane, we obtain a tentative detection of an infalling group or filamentary-like structure in the southeast that is believed to boost and heat up the ICM while the density of the gas is still low. In addition to characterizing the dynamical state of the cluster, we provide an improved SZ mass estimate M500,c = 1.66−0.20+0.23 × 1014 M⊙ . Conclusions. Altogether, the observations indicate that we see XLSSC 122 in a dynamic phase of cluster formation while a large reservoir of gas is already thermalized.

large-scale structure of Universe↗
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↗
DOE OSTI2015

Bayesian analysis of the dynamic cosmic web in the SDSS galaxy survey

Recent application of the Bayesian algorithm \textsc(borg) to the Sloan Digital Sky Survey (SDSS) main sample galaxies resulted in the physical inference of the formation history of the observed large-scale structure from its origin to the present epoch. In this work, we use these inferences as inputs for a detailed probabilistic cosmic web-type analysis. To do so, we generate a large set of data-constrained realizations of the large-scale structure using a fast, fully non-linear gravitational model. We then perform a dynamic classification of the cosmic web into four distinct components (voids, sheets, filaments, and clusters) on the basis of the tidal field. Our inference framework automatically and self-consistently propagates typical observational uncertainties to web-type classification. As a result, this study produces accurate cosmographic classification of large-scale structure elements in the SDSS volume. By also providing the history of these structure maps, the approach allows an analysis of the origin and growth of the early traces of the cosmic web present in the initial density field and of the evolution of global quantities such as the volume and mass filling fractions of different structures. For the problem of web-type classification, the results described in this work constitute the first connection between theory and observations at non-linear scales including a physical model of structure formation and the demonstrated capability of uncertainty quantification. A connection between cosmology and information theory using real data also naturally emerges from our probabilistic approach. Our results constitute quantitative chrono-cosmography of the complex web-like patterns underlying the observed galaxy distribution.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

A Bayesian approach to strong lens finding in the era of wide-area surveys

ABSTRACT The arrival of the Vera C. Rubin Observatory’s Legacy Survey of Space and Time (LSST), Euclid-Wide and Roman wide-area sensitive surveys will herald a new era in strong lens science in which the number of strong lenses known is expected to rise from $\mathcal {O}(10^3)$ to $\mathcal {O}(10^5)$. However, current lens-finding methods still require time-consuming follow-up visual inspection by strong lens experts to remove false positives which is only set to increase with these surveys. In this work, we demonstrate a range of methods to produce calibrated probabilities to help determine the veracity of any given lens candidate. To do this we use the classifications from citizen science and multiple neural networks for galaxies selected from the Hyper Suprime-Cam survey. Our methodology is not restricted to particular classifier types and could be applied to any strong lens classifier which produces quantitative scores. Using these calibrated probabilities, we generate an ensemble classifier, combining citizen science, and neural network lens finders. We find such an ensemble can provide improved classification over the individual classifiers. We find a false-positive rate of 10−3 can be achieved with a completeness of 46 per cent, compared to 34 per cent for the best individual classifier. Given the large number of galaxy–galaxy strong lenses anticipated in LSST, such improvement would still produce significant numbers of false positives, in which case using calibrated probabilities will be essential for population analysis of large populations of lenses and to help prioritize candidates for follow-up.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Evaluating cosmological biases using photometric redshifts for Type Ia Supernova cosmology with the Dark Energy Survey Supernova Program

Cosmological analyses with Type Ia Supernovae (SNe Ia) have traditionally been reliant on spectroscopy for both classifying the type of supernova and obtaining reliable redshifts to measure the distance–redshift relation. While obtaining a host-galaxy spectroscopic redshift for most SNe is feasible for small-area transient surveys, it will be too resource intensive for upcoming large-area surveys such as the Vera Rubin Observatory Legacy Survey of Space and Time, which will observe on the order of millions of SNe. Here, we use data from the Dark Energy Survey (DES) to address this problem with photometric redshifts (photo-z) inferred directly from the SN light curve in combination with Gaussian and full p(z) priors from host-galaxy photo-z estimates. Using the DES 5-yr photometrically classified SN sample, we consider several photo-z algorithms as host-galaxy photo-z priors, including the Self-Organizing Map redshifts (SOMPZ), Bayesian Photometric Redshifts (BPZ), and Directional-Neighbourhood Fitting (DNF) redshift estimates employed in the DES 3 × 2 point analyses. With detailed catalogue-level simulations of the DES 5-yr sample, we find that the simulated w can be recovered within ±0.02 when using SN+SOMPZ or DNF prior photo-z, smaller than the average statistical uncertainty for these samples of 0.03. With data, we obtain biases in w consistent with simulations within ~1σ for three of the five photo-z variants. We further evaluate how photo-z systematics interplay with photometric classification and find classification introduces a subdominant systematic component. This work lays the foundation for next-generation fully photometric SNe Ia cosmological analyses.

(cosmology:) dark energy↗
DOE OSTI2025

Robustness of Deep Learning Classification to Adversarial Input on GPUs: Asynchronous Parallel Accumulation Is a Source of Vulnerability

The ability of machine learning (ML) classification models to resist small, targeted input perturbations—known as adversarial attacks—is a key measure of their safety and reliability. We show that floating-point non associativity (FPNA) coupled with asynchronous parallel programming on GPUs is sufficient to result in misclassification, without any perturbation to the input. Additionally, we show that this misclassification is particularly significant for inputs close to the decision boundary and that standard adversarial robustness results may be overestimated up to 4.6 when not considering machine-level details. We first study a linear classifier, before focusing on standard Graph Neural Network (GNN) architectures and datasets used in robustness assessments. We develop a novel black-box attack using Bayesian optimization to discover external workloads that can change the instruction scheduling which bias the output of reductions on GPUs and reliably lead to misclassification. Motivated by these results, we present a new learnable permutation (LP) gradient-based approach to learning floating-point operation orderings that lead to misclassifications. The LP approach provides a worst-case estimate in a computationally efficient manner, avoiding the need to run identical experiments tens of thousands of times over a potentially large set of possible GPU states or architectures. Finally, using instrumentation-based testing, we investigate parallel reduction ordering across different GPU architectures under external background workloads, when utilizing multi-GPU virtualization, and when applying power capping. Our results demonstrate that parallel reduction ordering varies significantly across architectures under the first two conditions, substantially increasing the search space required to fully test the effects of this parallel scheduler-based vulnerability. These results and the methods developed here can help to include machine-level considerations into adversarial robustness assessments, which can make a difference in safety and mission critical applications.

Shanmugavelu, Sanjif [Maxeler Technologies, a Groq↗
DOE OSTI2016

AGNfitter: a Bayesian MCMC approach to fitting spectral energy distributions of AGNs

We present AGNfitter, a publicly available open-source algorithm implementing a fully Bayesian Markov Chain Monte Carlo method to fit the spectral energy distributions (SEDs) of active galactic nuclei (AGNs) from the sub-millimeter to the UV, allowing one to robustly disentangle the physical processes responsible for their emission. AGNfitter makes use of a large library of theoretical, empirical, and semi-empirical models to characterize both the nuclear and host galaxy emission simultaneously. The model consists of four physical emission components: an accretion disk, a torus of AGN heated dust, stellar populations, and cold dust in star-forming regions. AGNfitter determines the posterior distributions of numerous parameters that govern the physics of AGNs with a fully Bayesian treatment of errors and parameter degeneracies, allowing one to infer integrated luminosities, dust attenuation parameters, stellar masses, and star-formation rates. We tested AGNfitter’s performance on real data by fitting the SEDs of a sample of 714 X-ray selected AGNs from the XMM-COSMOS survey, spectroscopically classified as Type1 (unobscured) and Type2 (obscured) AGNs by their optical–UV emission lines. We find that two independent model parameters, namely the reddening of the accretion disk and the column density of the dusty torus, are good proxies for AGN obscuration, allowing us to develop a strategy for classifying AGNs as Type1 or Type2, based solely on an SED-fitting analysis. Our classification scheme is in excellent agreement with the spectroscopic classification, giving a completeness fraction of ∼86% and ∼70%, and an efficiency of ∼80% and ∼77%, for Type1 and Type2 AGNs, respectively.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS2004

Putting Priors in Mixture Density Mercer Kernels

This paper presents a new methodology for automatic knowledge driven data mining based on the theory of Mercer Kernels, which are highly nonlinear symmetric positive definite mappings from the original image space to a very high, possibly infinite dimensional feature space. We describe a new method called Mixture Density Mercer Kernels to learn kernel function directly from data, rather than using predefined kernels. These data adaptive kernels can en- code prior knowledge in the kernel using a Bayesian formulation, thus allowing for physical information to be encoded in the model. We compare the results with existing algorithms on data from the Sloan Digital Sky Survey (SDSS). The code for these experiments has been generated with the AUTOBAYES tool, which automatically generates efficient and documented C/C++ code from abstract statistical model specifications. The core of the system is a schema library which contains template for learning and knowledge discovery algorithms like different versions of EM, or numeric optimization methods like conjugate gradient methods. The template instantiation is supported by symbolic- algebraic computations, which allows AUTOBAYES to find closed-form solutions and, where possible, to integrate them into the code. The results show that the Mixture Density Mercer-Kernel described here outperforms tree-based classification in distinguishing high-redshift galaxies from low- redshift galaxies by approximately 16% on test data, bagged trees by approximately 7%, and bagged trees built on a much larger sample of data by approximately 2%.

Srivastava, Ashok N.↗
DOE OSTI2025

Hot Droughts and Forest Tree Dynamics in the Amazon - Statistical Models, Scripts, Data, and Outputs

This package contains data, outputs, equations, and R scripts for analyses for manuscript entitled "Hot droughts in the Amazon: A window to a future hypertropical climate" by J. Chambers et al., in particular it contains statistical models and analyses for the INPA BIONTE tree mortality study. The Models folder contains details for all statistical models in PDF files. The Scripts folder contains the R scripts for Bayesian Hierarchical Models (two text files) and SEMs (one text file) are separate and reasonably annotated. All data associated with these scripts are in the data folder. The Data folder contains two of the three CSV files used for the analyses and are called by the R scripts. Two of them are part of published datasets (`BIONTE_mortality-rates.csv` from Lima et al. 2024, DOI:10.15486/ngt/1898910 and `SPEI.csv` from Pastorello et al. 2023 DOI:10.15486/ngt/1958257) and also provided in this package for convenience (please see the corresponding datasets for usage and citation terms). The third dataset (`BIONTE_gapfilled_wd.csv`) contains sensitive information and can be obtained by contacting the manuscript lead author. The Outputs folder contains the two output files that provide extra information about the analyses. The file `figuresFeb2025d.pdf` contains all the figures from the manuscript - captions are in the manuscript. The file `ChambersMS.pdf` contains primary results from Bayesian statistical models, regression analyses, and validation steps applied to the tree mortality data from the INPA experiments. The document includes visual summaries, model diagnostics, and leave-one-out (LOO) validation results. A breakdown of file contents can be found in the README file that is part of this package.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1990

Topics in inference and decision-making with partial knowledge

Two essential elements needed in the process of inference and decision-making are prior probabilities and likelihood functions. When both of these components are known accurately and precisely, the Bayesian approach provides a consistent and coherent solution to the problems of inference and decision-making. In many situations, however, either one or both of the above components may not be known, or at least may not be known precisely. This problem of partial knowledge about prior probabilities and likelihood functions is addressed. There are at least two ways to cope with this lack of precise knowledge: robust methods, and interval-valued methods. First, ways of modeling imprecision and indeterminacies in prior probabilities and likelihood functions are examined; then how imprecision in the above components carries over to the posterior probabilities is examined. Finally, the problem of decision making with imprecise posterior probabilities and the consequences of such actions are addressed. Application areas where the above problems may occur are in statistical pattern recognition problems, for example, the problem of classification of high-dimensional multispectral remote sensing image data.

Safavian, S. Rasoul↗
DOE OSTI2026

A dendritic strontium river isoscape for fisheries applications in the Sacramento River basin, California, USA

Objective Understanding the origins and movements of fish is fundamental to effective conservation and fisheries management. Strontium isotope ratios ( 87 Sr/ 86 Sr) in otoliths provide a powerful tracer of natal origin and migratory pathways. However, existing 87 Sr/ 86 Sr isoscapes for the Sacramento River basin, an ecosystem that supports ecologically and economically important salmon populations, rely on discrete classification approaches that overlook unsampled habitats and do not incorporate spatial uncertainty. Our objective was to develop a continuous, network-explicit 87 Sr/ 86 Sr isoscape with quantified uncertainty to fill in data gaps and enable probabilistic assignments of fish origin and movement. Methods We used river water 87 Sr/ 86 Sr data from 106 sites (1997–2021) to develop spatial stream network models that use dendritic connectivity and watershed characteristics (lithology, bedrock age, and land cover) to predict river water 87 Sr/ 86 Sr throughout the basin. Models were fitted using maximum and restricted likelihood and were evaluated via Akaike’s information criterion and leave-one-out cross validation. We produced both historical (pre-dam) and present-day (below-dam) isoscapes, delineated uncertainty-informed isotopic ranges using k -means clustering, and applied a proof-of-concept Bayesian assignment to estimate natal origins and early rearing habitats for two endangered winter-run Chinook Salmon Oncorhynchus tshawytscha. Results Cross validation indicated strong performance of the 87 Sr/ 86 Sr model (leave-one-out cross validation: R 2 = 0.91; root mean square error = 0.0005). Uncertainty-informed clustering identified 19 isotopic “suites” (reaches with indistinguishable 87 Sr/ 86 Sr values) in present-day anadromous habitats and 25 suites in the historical network. Example natal and early rearing assignments included predictions that challenged expectations for juvenile salmon migration based on predicted river 87 Sr/ 86 Sr compositions. Conclusions This study developed a continuous, network-explicit 87 Sr/ 86 Sr isoscape that integrates existing river data to predict 87 Sr/ 86 Sr in unsampled reaches and the likely achievable range and resolution of otolith-based origin and life history inference. The resulting river isoscape provides a valuable tool to predict salmon movements and identify habitats supporting their survival and growth that otherwise might remain undetected. Coupling these predictions with complementary approaches that ground-truth juvenile presence (e.g., targeted fish surveys) represents an important step toward science-informed restoration and management of critical habitats throughout the Sacramento River basin.

Environmental sciences↗
DOE OSTI2022

Identification of a new circulating recombinant form of human immunodeficiency virus type 1, CRF124_cpx involving subtypes A, G, H, and CRF27_cpx in Angola

Angola, located in Central Africa, has around 320,000 (270,000–380,000) people living with human immunodeficiency virus (HIV)/AIDS, equivalent to 1% of the country’s population at the end of 2021. A previous study conducted in 2012, using Angolan samples collected between 2008 and 2010 revealed a high prevalence of HIV-1 recombinants, around 42% of sequences, with 21% showing the same UH profile in partial pol region which were grouped into a monophyletic cluster with high bootstrap support. Thus, the objective of the present work was to obtain complete genomes of those sequences and characterize them, aiming at a description of a new circulating recombinant form (CRF). Whole blood from nine HIV-1 UH pol -infected individuals had their genomic DNA extracted, and nested PCR was used to amplify seven overlapping fragments targeting the full-length HIV-1 genome. The final classification was based on maximum likelihood trees, and recombination analyses were performed using a bootscan from the Simplot program. BLAST and Los Alamos Database inspections were used to search other similar H-like pol sequences. Complete genome amplification was possible for three samples, partial genomes were obtained for the other three, and only pol was available for the remaining three sequences. Bootscan analysis of the two whole-genome and three partial genome sequences retrieved from people living with HIV/AIDS (PLHIVA) without epidemiological linkage showed the same complex recombination profile involving HIV-1 subtypes A/G/H/CRF27_cpx, with a total of six recombinant breakpoints, aiming to classify a new HIV-1 CRF124_cpx. We found no other full-length HIV-1 genomes with the same mosaic profile; however, we identified 33 partial pol sequences, mainly sampled from Angola between 2001 to 2019, with the same H-like profile. Bayesian analysis of H and H-like pol sequences indicates that CRF124_cpx probably originated in Angola at mid-1970s, indicating that this CRF has been circulating in the country for a long time. In summary, our study describes a new CRF circulating principally in Angola and highlights the importance of continuing molecular surveillance studies, especially in countries with high molecular diversity of HIV.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

J-PLUS: Spectral evolution of white dwarfs by PDF analysis

We estimated the spectral evolution of white dwarfs with effective temperature using the Javalambre Photometric Local Universe Survey (J-PLUS) second data release (DR2), which provides 12 photometric optical passbands over 2176 deg 2 . We analyzed 5926 white dwarfs with r ≤ 19.5 mag in common between a white dwarf catalog defined from Gaia EDR3 and J-PLUS DR2. We performed a Bayesian analysis by comparing the observed J-PLUS photometry with theoretical models of hydrogen- and helium-dominated atmospheres. We estimated the probability distribution functions for effective temperature (T eff ), surface gravity, parallax, and composition; and the probability of having a H-dominated atmosphere (p H ) for each source. We applied a prior in parallax, using Gaia EDR3 measurements as a reference, and derived a self-consistent prior for the atmospheric composition as a function of T eff . We described the fraction of white dwarfs with a He-dominated atmosphere (f He ) with a linear function of the effective temperature at 5000 < T eff < 30 000 K. We find f He = 0.24 ± 0.01 at T eff = 10 000 K, a change rate along the cooling sequence of 0.14 ± 0.02 per 10 kK, and a minimum He-dominated fraction of 0.08 ± 0.02 at the high-temperature end. We tested the obtained p H by comparison with spectroscopic classifications, finding that it is reliable. We estimated the mass distribution for the 351 sources with distance d < 100 pc, mass M > 0.45 M ⊙ , and T eff > 6000 K. The result for H-dominated white dwarfs agrees with previous studies, with a dominant M = 0.59 M ⊙ peak and the presence of an excess at M ~ 0.8 M ⊙ . This high-mass excess is absent in the He-dominated distribution, which presents a single peak. The J-PLUS optical data provide a reliable statistical classification of white dwarfs into H- and He-dominated atmospheres. We find a 21 ± 3% increase in the fraction of He-dominated white dwarfs from T eff = 20 000 K to T eff = 5000 K.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1992

Signal processing for airborne doppler radar detection of hazardous wind shear as applied to NASA 1991 radar flight experiment data

Radar data collected during the 1991 NASA flight tests have been selectively analyzed to support research directed at developing both improved as well as new algorithms for detecting hazardous low-altitude windshear. Analysis of aircraft attitude data from several flights indicated that platform stability bandwidths were small compared to the data rate bandwidths which should support an assumption that radar returns can be treated as short time stationary. Various approaches at detection of weather returns in the presence of ground clutter are being investigated. Non-coventional clutter rejection through spectrum mode tracking and classification algorithms is a subject of continuing research. Based upon autoregressive modeling of the radar return time sequence, this approach may offer an alternative to overcome errors in conventional pulse-pair estimates. Adaptive filtering is being evaluated as a means of rejecting clutter with emphasis on low signal-to-clutter ratio situations, particularly in the presence of discrete clutter interference. An analysis of out-of-range clutter returns is included to illustrate effects of ground clutter interference due to range aliasing for aircraft on final approach. Data are presented to indicate how aircraft groundspeed might be corrected from the radar data as well as point to an observed problem of groundspeed estimate bias variation with radar antenna scan angle. A description of how recorded clutter return data are mixed with simulated weather returns is included. This enables the researcher to run controlled experiments to test signal processing algorithms. In the summary research efforts involving improved modelling of radar ground clutter returns and a Bayesian approach at hazard factor estimation are mentioned.

Baxa, Ernest G., Jr.↗
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 OSTI2016

A Deep Generative Deconvolutional Image Model

A deep generative model is developed for representation and analysis of images, based on a hierarchical convolutional dictionary-learning framework. Stochastic unpooling is employed to link consecutive layers in the model, yielding top-down image generation. A Bayesian support vector machine is linked to the top-layer features, yielding max-margin discrimination. Deep deconvolutional inference is employed when testing, to infer the latent features, and the top-layer features are connected with the max-margin classifier for discrimination tasks. The model is efficiently trained using a Monte Carlo expectation-maximization (MCEM) algorithm; the algorithm is implemented on graphical processor units (GPU) to enable large-scale learning, and fast testing. Excellent results are obtained on several benchmark datasets, including ImageNet, demonstrating that the proposed model achieves results that are highly competitive with similarly sized convolutional neural networks.

convolutional neural network↗
DOE OSTI2024

Data from "A Bayesian Record Linkage Approach to Applications in Tree Demography Using Overlapping LiDAR Scans"

Processed LiDAR data and environmental covariates from 2015 and 2019 LiDAR scans in the Vicinity of Snodgrass Mountain (Western Colorado, USA), in a geographic subset used in primary analysis for the research paper.This package contains LiDAR-derived canopy height maps for 2015 and 2019, crown polygons derived from the height maps using a segmentation algorithm, and environmental covariates supporting the model of forest growth. Source datasets include August 2015 and August 2019 discrete-return LiDAR point clouds collected by Quantum Geospatial for terrain mapping purposes on behalf of the Colorado Hazard Mapping Program and the Colorado Water Conservation Board. Both datasets adhere to the USGS QL2 quality standard. The point cloud data were processed using the R package lidR to generate a canopy height model representing maximum vegetation height above the ground surface, using a pit-free algorithm.This dataset was compiled to assess how spatial patterns of tree growth in montane and subalpine forests are influenced by water and energy availability. Understanding these growth patterns can provide insight into forest dynamics in the Southern Rocky Mountains under changing climatic conditions.This dataset contains .tif, .csv, and .txt files. This dataset additionally includes a file-level metadata (flmd.csv) file that lists each file contained in the dataset with associated metadata; and a data dictionary (dd.csv) file that contains column/row headers used throughout the files along with a definition, units, and data type.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Deep kernel methods learn better: from cards to process optimization

Abstract The ability of deep learning methods to perform classification and regression tasks relies heavily on their capacity to uncover manifolds in high-dimensional data spaces and project them into low-dimensional representation spaces. In this study, we investigate the structure and character of the manifolds generated by classical variational autoencoder (VAE) approaches and deep kernel learning (DKL). In the former case, the structure of the latent space is determined by the properties of the input data alone, while in the latter, the latent manifold forms as a result of an active learning process that balances the data distribution and target functionalities. We show that DKL with active learning can produce a more compact and smooth latent space which is more conducive to optimization compared to previously reported methods, such as the VAE. We demonstrate this behavior using a simple cards dataset and extend it to the optimization of domain-generated trajectories in physical systems. Our findings suggest that latent manifolds constructed through active learning have a more beneficial structure for optimization problems, especially in feature-rich target-poor scenarios that are common in domain sciences, such as materials synthesis, energy storage, and molecular discovery. The Jupyter Notebooks that encapsulate the complete analysis accompany the article.

97 MATHEMATICS AND COMPUTING↗