Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data 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 1,099 records · Page 61
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Integrating Overhead Camera Imagery with Reinforcement Learning to Improve Fuel Economy Through Adaptive Traffic Control

Overhead cameras have been deployed for some time as a sensor for traffic control, with many advantages over conventional inductive loop sensors in terms of robustness, ease of installation, and simplicity with respect to maintenance. We explore the utility of such imagery (in particular, fisheye lens cameras) for intelligent traffic control in real-time using reinforcement learning, with a goal of improving fuel economy for the overall intersection and grid of intersections. We summarize our initial work in data collection and approach to ascertain the ability to visually sense vehicular fuel consumption using real-world data. We then describe our deep reinforcement learning topology to test adaptive control informed by the camera capabilities. Next, we tested the proof-of-concept through a variety of simulation scenarios using the Simulation of Urban Mobility (SUMO) traffic simulator, which included different estimates on vehicle classifications, different traffic distributions, and different traffic densities. Six different control policies were tested ranging from simple timing, to heuristic visual-based methods, to actual policies learned via the reinforcement learning approach. Our results demonstrate the feasibility of the approach for controlling traffic lights for better fuel efficiency based on visual vehicle estimates from commercial, fisheye lens cameras.

Karnowski, Thomas↗
DOE OSTI2021

Herbig Ae/Be Stars toward the Dark Cloud LDN 1667

We report the discovery of a new emission-line object, named SPH 4-South = (GAIA EDR3 5616553300192230272), toward the dark cloud LDN 1667. This object came to our attention after inspecting public images that show a faint diffuse nebula a few arcseconds south of SPH 4, an emission-line object previously classified as a T Tauri star. We present high-resolution spectra and analyzed JHK photometry of SPH 4 and SPH 4-South and new narrowband and archival broadband images of these objects. A comparison of the spectra of SPH 4 and SPH 4-South with high-resolution ones of DG Cir and R Mon strongly suggests that SPH 4 and SPH 4-South are Herbig Ae/Be stars. The classification of SPH 4-South is further supported by using a k-NN algorithm to its position in an H–K versus J–H color–color diagram. Both stars are detected in the four WISE bands and the WISE colors allow us to classify SPH 4 as a Class I and SPH 4-South as a Class II source. We also show that the faint nebula is most probably associated with SPH 4-South. Using published results on LDN 1667 and the Gaia Early Data Release 3, we conclude that SPH 4 is a member of LDN 1667. The case of SPH 4-South is not clear because the determination of its distance and proper motion could be affected by the nebulosity around the star, although membership of SPH 4-South to LDN 1667 cannot be ruled out.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Efficient distributed continual learning for steering experiments in real-time

Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training suffers from catastrophic forgetting (i.e., new patterns are reinforced at the expense of previously acquired knowledge). Training from scratch each time new training data becomes available would result in extremely long training times and massive data accumulation. Rehearsal-based continual learning has shown promise for addressing the catastrophic forgetting challenge, but research to date has not addressed performance and scalability. To fill this gap, we propose an approach based on a distributed rehearsal buffer that efficiently complements data-parallel training on multiple GPUs to achieve high accuracy, short runtime, and scalability. It leverages a set of buffers (local to each GPU) and uses several asynchronous techniques for updating these local buffers in an embarrassingly parallel fashion, all while handling the communication overheads necessary to augment input minibatches using unbiased, global sampling. We further propose a generalization of rehearsal buffers to support both classification and generative learning tasks, as well as more advanced rehearsal strategies (notably Dark Experience Replay, leveraging knowledge distillation). We illustrate this approach with a real-life HPC streaming application from the domain of ptychographic image reconstruction. Furthermore, we run extensive experiments on up to 128 GPUs of the ThetaGPU supercomputer to compare our approach with baselines representative of training-from-scratch (the upper bound in terms of accuracy) and incremental training (the lower bound). Results show that rehearsal-based continual learning achieves a top-5 validation accuracy close to the upper bound, while simultaneously exhibiting a runtime close to the lower bound.

Asynchronous data management↗
DOE OSTI2023

Towards POI-based large-scale land use modeling: spatial scale, semantic granularity, and geographic context

The combination of spatial distribution, semantic characteristics, and sometimes temporal dynamics of POIs inside a geographic region can capture its unique land use characteristics. Most previous studies on POI-based land use modeling research focused on one geographic region and select one spatial scale and semantic granularity for land use characterization. There is a lack of understanding on the impact of spatial scale, semantic granularity, and geographic context on POI-based land use modeling, particularly large-scale land use modeling. In this study, we developed a scalable POI-based land use modeling framework and examined the impact of these three factors on POI-based land use characterization using data from three geographic regions. We developed a unified semantic representation framework for POI semantics that can help fuse heterogeneous POI data sources. Then, by combining POIs with a neural network language model, we developed a spatially explicit approach to learn the embedding representation of POIs and AOIs. We trained multiple supervised classifiers using AOI embeddings as input features to predict AOI land use at different semantic granularities. The classification performance of different land use classes was analyzed and compared across three geographic regions to identify the semantic representativeness of POI-based AOI embedding and the impact of geographic context.

58 GEOSCIENCES↗
DOE OSTI2020

The incommensurately modulated structures of low-temperature labradorite feldspars: a single-crystal X-ray and neutron diffraction study

Labradorite feldspars of the plagioclase solid solution series have been known for their complicated subsolidus phase relations and enigmatic incommensurately modulated structures. Characterized by the irrationally indexed e -reflections in the diffraction pattern, e -labradorite shows the largest variation in the incommensurate ordering states among the e -plagioclase structures. The strongly ordered low-temperature e -labradorite is one of the last missing pieces of the e -plagioclase puzzle. Nine plutonic and metamorphic labradorite feldspar samples from Canada, Ukraine, Minnesota (USA), Tanzania and Greenland with compositions ranging from An 52.5 to An 68 were studied with single-crystal X-ray diffraction. Two crystals from Labrador, Canada, and Duluth, MN, USA, with wide enough twin lamellae were analyzed with single-crystal neutron diffraction. The incommensurately modulated structures of e -plagioclase are refined for the first time with neutron diffraction data, which confirmed that the T—O distance modulation in the low-temperature e -plagioclase results from the Al–Si ordering in the framework. Detailed configurations of the M site are also observed in the structures refined from neutron diffraction data, which were not possible to see with X-ray diffraction data. The relation between the q -vectors and the mole% An composition is revealed for the entire compositional range of e -plagioclase, from An 25 to An 75 . The previously proposed two-trend relation depending on the cooling rate and phase transition path is confirmed. A new classification of e -plagioclase ( e α , e β and e γ ) is proposed based on the q -vector of the structure, which makes it an independent character from the presence/absence of density modulation. New parameters are proposed to quantify the ordering states of these complicated aperiodic structures of e -plagioclases, such as the difference between $\langle$T 1 o—O$\rangle$ and $\langle$T 1 m—O$\rangle$ at phase t = 0.2 or the normalized intensity of the (071\bar 1) reflection.

36 MATERIALS SCIENCE↗
DOE OSTI2025

DOE Repository Metadata Profile (DRMP): A Metadata Framework for Advancing Interoperability and AI Readiness Across Scientific Repositories

The Department of Energy (DOE) funds a diverse and distributed ecosystem of repositories that steward scientific data, publications, and software across its research programs, user facilities, and national laboratories. While significant progress has been made in standardizing dataset-level metadata, the metadata describing repositories themselves (their identity, governance, access interfaces, policies, and technical capabilities) remains inconsistent and fragmented across DOE-funded systems. This variability limits discoverability, interoperability, automated validation, and AI-driven analysis, all of which are increasingly essential for modern scientific workflows. To address this gap, the DOE Data Curation Working Group (DCWG) developed the DOE Repository Metadata Profile (DRMP). The DRMP is a practical, community-driven framework that defines how repositories can describe themselves in a consistent, machine-actionable, and scalable manner. The DRMP is not a new metadata schema. Instead, it is a mapping profile and structured element set capturing the essential characteristics of DOE repositories. It harmonizes repository-level metadata across six widely adopted community schemas: RE3Data; DCAT-US v3; Schema.org; Dublin Core; DataCite 4.6; and PREMIS 3.0. This harmonization eliminates reinvention and enables interoperability within DOE and across the broader scientific ecosystem. A core objective of the DRMP is to reduce burden on repositories by allowing them to reuse their existing metadata through a Rosetta-style crosswalk rather than redesigning local implementations. The profile introduces a three-level conformance model that supports incremental adoption: • Level 1 – Minimum Viable Record (MVR): foundational identification elements required for workflows, project registration, and basic repository presence. • Level 2 – Interoperable: structured metadata enabling alignment with national and international discovery systems. • Level 3 – AI-Ready: enhanced provenance, policy transparency, fixity, semantic context, and capabilities that support automated reasoning, model training governance, and machine-assisted curation. To support implementation, the DRMP includes JSON Schema definitions, OpenAPI patterns, and MCP templates that allow repositories to publish machine-readable metadata directly within existing platforms. These resources are modular and lightweight, enabling adoption without major architectural change. Adopting the DRMP enables repositories to: • Enhance discoverability and interoperability by aligning identifiers, classifications, and descriptive elements across widely used schema standards. • Support federated discovery and cross-registration across DOE systems, Data.gov, and international catalogs. • Enable AI agents and workflow orchestration systems to interpret repository-level metadata within the American Science Cloud (AmSC) through Model Context Protocol (MCP)-based context publication. • Demonstrate alignment with DOE’s open science, stewardship, and FAIR data priorities. This guidance represents a community-driven step forward. Through voluntary adoption and continued feedback, the DRMP advances a cohesive, machine-actionable description of DOE repositories that supports FAIR data practices, preparing the infrastructure for AI-enabled research, and strengthening the discoverability and reuse of DOE’s scientific outputs.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2021

Uranium Oxide Synthetic Pathway Discernment through Unsupervised Morphological Analysis

We present a novel unsupervised machine learning method for quantitative representation of scanning electron micrographs and its applications and performance for nuclear forensic analysis of uranium ore concentrates. The method uses a vector quantizing variational autoencoder followed by a histogram operation to encode a micrograph into a single dimensional representation, called the latent vector. The method requires no extant labeling of the data and can be applied over large datasets of micrographs with minimal human interaction. The representations generated are broadly descriptive of each micrograph and the microstructure of the material imaged. In the case of uranium ore concentrate analysis, the representations were amenable to processing reagent and ore concentrate species classification with accuracy of 81:8%, which is competitive with state-of-the-art supervised networks. The representations were also used to classify previously unseen processing routes, were able to classify imaging parameters such as magnification (to 76:0% accuracy), were able to classify fine grained process parameters such as calcining temperature (to 74:4% accuracy), and their informatic properties indicate that they are generally descriptive of the image represented. This method can be applied across microstructure analysis fields to perform quantitative analysis without the need for labor intensive and possibly biased human analysis.

Scanning Electron Microscopy, Vector Quantizing Va↗
DOE OSTI2022

InClass nets: independent classifier networks for nonparametric estimation of conditional independence mixture models and unsupervised classification

Abstract Conditional independence mixture models (CIMMs) are an important class of statistical models used in many fields of science. We introduce a novel unsupervised machine learning technique called the independent classifier networks (InClass nets) technique for the nonparameteric estimation of CIMMs. InClass nets consist of multiple independent classifier neural networks (NNs), which are trained simultaneously using suitable cost functions. Leveraging the ability of NNs to handle high-dimensional data, the conditionally independent variates of the model are allowed to be individually high-dimensional, which is the main advantage of the proposed technique over existing non-machine-learning-based approaches. Two new theorems on the nonparametric identifiability of bivariate CIMMs are derived in the form of a necessary and a (different) sufficient condition for a bivariate CIMM to be identifiable. We use the InClass nets technique to perform CIMM estimation successfully for several examples. We provide a public implementation as a Python package called RainDancesVI.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Integrating Machine Learning into a Methodology for Early Detection of Wellbore Failure [Slides]

Approximately 93% of US total energy supply is dependent on wellbores in some form. The industry will drill more wells in next ten years than in the last 100 years (King, 2014). Global well population is around 1.8 million of which approximately 35% has some signs of leakage (i.e. sustained casing pressure). Around 5% of offshore oil and gas wells “fail” early, more with age and most with maturity. 8.9% of “shale gas” wells in the Marcellus play have experienced failure (120 out of 1,346 wells drilled in 2012) (Ingraffea et al., 2014). Current methods for identifying wells that are at highest priority for increased monitoring and/or at highest risk for failure consists of “hand” analysis of multi-arm caliper (MAC) well logging data and geomechanical models. Machine learning (ML) methods are of interest to explore feasibility for increasing analysis efficiency and/or enhanced detection of precursors to failure (e.g. deformations). MAC datasets used to train ML algorithms and preliminary tests were run for “predicting” casing collar locations and performed above 90% in classification and identifying of casing collar locations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Integrating Machine Learning into a Methodology for Early Detection of Wellbore Failure [Slides]

Approximately 93% of US total energy supply is dependent on wellbores in some form. The industry will drill more wells in next ten years than in the last 100 years (King, 2014). Global well population is around 1.8 million of which approximately 35% has some signs of leakage (i.e. sustained casing pressure). Around 5% of offshore oil and gas wells “fail” early, more with age and most with maturity. 8.9% of “shale gas” wells in the Marcellus play have experienced failure (120 out of 1,346 wells drilled in 2012) (Ingraffea et al., 2014). Current methods for identifying wells that are at highest priority for increased monitoring and/or at highest risk for failure consists of “hand” analysis of multi-arm caliper (MAC) well logging data and geomechanical models. Machine learning (ML) methods are of interest to explore feasibility for increasing analysis efficiency and/or enhanced detection of precursors to failure (e.g. deformations). MAC datasets used to train ML algorithms and preliminary tests were run for “predicting” casing collar locations and performed above 90% in classification and identifying of casing collar locations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Mycorrhiza better predict soil fungal community composition and function than aboveground traits in temperate forest ecosystems

We sampled soil in the organic and mineral horizons beneath two AM-associated (Fraxinus americana, Thuja occidentalis) and two ECM-associated tree species (Betula alleghaniensis, and Tsuga canadensis), with an evergreen and deciduous species in each mycorrhizal group. To characterize fungal communities and organic matter decomposition beneath each tree species, we sequenced the ITS1 region of fungal DNA and measured the potential activity of carbon and nitrogen-targeting extracellular enzymes. Each tree species harbored distinct fungal communities, supporting the need to consider both mycorrhizal type and leaf habit. However, between tree characteristics, mycorrhizal type better predicted fungal communities. Across fungal guilds, saprotrophic fungi were the most important group in shaping fungal community differences in soils beneath all tree species. The effect of leaf habit on carbon and nitrogen-targeting hydrolytic enzymes depended on tree mycorrhizal association in the organic horizon, while oxidative enzyme activities were higher beneath EcM-associated trees across both soil horizons and leaf habits. These data include extracellular hydrolytic and oxidative enzyme activities, ITS sequencing fungal community data, soil carbon to nitrogen, and soil pH. Site level data include climate (mean annual temperature, precipitation), elevation, and soil series and order information.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Linking Extragalactic Transients and Their Host Galaxy Properties: Transient Sample, Multiwavelength Host Identification, and Database Construction

Understanding the preferences of transient types for host galaxies with certain characteristics is key to studies of transient physics and galaxy evolution, as well as to transient identification and classification in the LSST era. Here we describe a value-added database of extragalactic transients—supernovae, tidal disruption events, gamma-ray bursts, and other rare events—and their host galaxy properties. Based on reported coordinates, redshifts, and host galaxies (if known) of events, we cross-identify their host galaxies or most likely host candidates in various value-added or survey catalogs, and compile the existing photometric, spectroscopic, and derived physical properties of the host galaxies in these catalogs. This new database covers photometric measurements from the far-ultraviolet to mid-infrared. Spectroscopic measurements and derived physical properties are also available for a smaller subset of hosts. For our 36,333 unique events, we have cross-identified 13,753 host galaxies using host names, plus 4480 using host coordinates. Besides those with known hosts, there are 18,100 transients with newly identified host candidates. This large database will allow explorations of the connections of transients to their hosts, including a path toward transient alert filtering and probabilistic classification based on host properties.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Global Geo-processed Data of Aquifer Properties by 0.5° Grid, Country and Water Basins

This repository of global hydrogeologic datasets contains aquifer properties on 0.5° scale, including depth to groundwater (Fan et al., 2013), aquifer thickness (de Graaf et al., 2015), WHYMap aquifer classes (Richts et al., 2011), recharge (Döll and Fiedler, 2008; Gleeson et al., 2016), lakes (Messager et al., 2016), porosity and permeability (Gleeson et al., 2014), digitized and geo-processed from their respective sources. Globally gridded aquifer properties could be used independently to estimate global groundwater availability or used as critical inputs to the superwell model to simulate groundwater extraction and provide estimates of pumped volumes and unit costs under user-specific scenarios. Key resources related to this data are: Niazi, H., Ferencz, S. B., Graham, N. T., Yoon, J., Wild, T. B., Hejazi, M., Watson, D. J., & Vernon, C. R. (2025). Long-term hydro-economic analysis tool for evaluating global groundwater cost and supply: Superwell v1.1. Geoscientific Model Development, 18(5), 1737-1767. https://doi.org/10.5194/gmd-18-1737-2025 superwell model repository which uses this data to simulate groundwater extraction and provides estimates of the global extractable volumes and unit-costs ($/km3) of accessible groundwater production under user-specified extraction scenarios. Repository Overview Main output: aquifer_properties_rec.csv contains all processed outputs, including aquifer properties like porosity, permeability, recharge, lake areas, aquifer thickness, and depth to groundwater. shapefiles.zip: contains all digitized GIS databases and shapefile for all aquifer properties prep_inputs.R and prep_inputs_recharge_lakes.R: R scripts that process the shapefiles to produce the aquifer_properties_rec.csv file plot_inputs.R: R script for plotting the maps and conducting preliminary analysis on the available groundwater volume basin_to_country_mapping.csv, basin_country_region_mapping.csv and continent_county_mapping.csv provide the mapping between continents, 32 energy-economic macro regions, countries, and water basins for post-processing aquifer_properties_rec.csv Maps: Each map visualizes the spatial distribution of one of the aquifer properties across the globe map_in_Porosity.png map_in_Permeability.png map_in_Aquifer_thickness.png map_in_Depth_to_water.png map_in_Recharge.png map_in_Grid_area_km.png map_in_Lake_area_km.png map_in_WHYClass.png Sample inputs sample_inputs.py: this script samples inputs from the aquifer_properties_rec dataset, ensuring the sampled and original inputs maintain the same distributions sampled_data_100.csv contains 100 sampled data points and sampled_data_100.png compares their distributions Dataset Overview The main outputs are consolidated in a comprehensive aquifer_properties_rec.csv file and include the following fields: GridCellID: Unique identifier for each (roughly 0.5°) grid cell Continent: Continent name Country: Country name GCAM_basin_ID: Identifier for GCAM hydrologic basin Basin_long_name: Full name of the basin WHYClass: Hydrogeologic classification based on WHYMap aquifer classes (Richts et al., 2011) Porosity: Soil porosity (%) (Gleeson et al., 2014) Permeability: Soil permeability (in square meters; Gleeson et al., 2014) Aquifer_thickness: Thickness of the aquifer (in meters; de Graaf et al., 2015) Depth_to_water: Depth to groundwater (in meters; Fan et al., 2013) Recharge: long-term annual averaged recharge rates (in m/yr; Döll and Fiedler, 2008; Gleeson et al., 2016) Grid_area: Area of the grid cell (in square meters) Lakes_area: Area of inland lakes (in square meters; Messager et al., 2016) Key References The datasets are digitized versions of global hydrogeologic properties from the following key literature sources: Depth to Groundwater: Fan, Y., Li, H., & Miguez-Macho, G. (2013). Global Patterns of Groundwater Table Depth. Science, 339(6122), 940-943. https://doi.org/10.1126/science.1229881 Aquifer Thickness: de Graaf, I. E. M., Sutanudjaja, E. H., van Beek, L. P. H., & Bierkens, M. F. P. (2015). A high-resolution global-scale groundwater model. Hydrol. Earth Syst. Sci., 19(2), 823-837. https://doi.org/10.5194/hess-19-823-2015 Porosity and Permeability: Gleeson, T., Moosdorf, N., Hartmann, J., & van Beek, L. P. H. (2014). A glimpse beneath earth's surface: GLobal HYdrogeology MaPS (GLHYMPS) of permeability and porosity. Geophysical Research Letters, 41(11), 3891-3898. https://doi.org/10.1002/2014GL059856 Aquifer classes: Richts, A., Struckmeier, W. F., & Zaepke, M. (2011). WHYMAP and the Groundwater Resources Map of the World 1:25,000,000. In J. A. A. Jones (Ed.), Sustaining Groundwater Resources: A Critical Element in the Global Water Crisis (pp. 159-173). Springer Netherlands. https://doi.org/10.1007/978-90-481-3426-7_10 Recharge: Döll, P., & Fiedler, K. (2008). Global-scale modeling of groundwater recharge. Hydrol. Earth Syst. Sci., 12(3), 863-885. https://doi.org/10.5194/hess-12-863-2008; Gleeson, T., Befus, K. M., Jasechko, S., Luijendijk, E., & Cardenas, M. B. (2016). The global volume and distribution of modern groundwater. Nature Geoscience, 9(2), 161-167. https://doi.org/10.1038/ngeo2590 Inland Lakes: Messager, M. L., Lehner, B., Grill, G., Nedeva, I., & Schmitt, O. (2016). Estimating the volume and age of water stored in global lakes using a geo-statistical approach. Nature Communications, 7(1), 13603. https://doi.org/10.1038/ncomms13603 Cite as Niazi, H., Watson, D., Hejazi, M., Yonkofski, C., Ferencz, S., Vernon, C., Graham, N., Wild, T., & Yoon, J. (2024). Global Geo-processed Data of Aquifer Properties by 0.5° Grid, Country and Water Basins. MultiSector Dynamics-Living, Intuitive, Value-adding, Environment. https://doi.org/10.57931/2484226 Contact Reach out to Hassan Niazi or open an issue in the superwell repository for questions or suggestions.

aquifer thickness↗
DOE OSTI2021

Subaru Hyper Suprime-Cam revisits the large-scale environmental dependence on galaxy morphology over 360 deg2 at z = 0.3–0.6

This study investigates the role of large-scale environments on the fraction of spiral galaxies at z = 0.3–0.6 sliced to three redshift bins of Δz = 0.1. Here, we sample 276220 massive galaxies in a limited stellar mass of 5 × 1010 solar mass (~M*) over 360 deg2, as obtained from the Second Public Data Release of the Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP). By combining projected two-dimensional density information (Shimakawa et al. 2021, MNRAS, 503, 3896) and the CAMIRA cluster catalog (Oguri et al. 2018, PASJ, 70, S20), we investigate the spiral fraction across large-scale overdensities and in the vicinity of red sequence clusters. We adopt transfer learning to reduce the cost of labeling spiral galaxies significantly and then perform stacking analysis across the entire field to overcome the limitations of sample size. Here we employ a morphological classification catalog by the Galaxy Zoo Hubble (Willett et al., 2017, MNRAS, 464, 4176) to train the deep learning model. Based on 74103 sources classified as spirals, we find moderate morphology–density relations on a 10 comoving Mpc scale, thanks to the wide-field coverage of HSC-SSP. Clear deficits of spiral galaxies have also been confirmed, in and around 1136 red sequence clusters. Furthermore, we verify whether there is a large-scale environmental dependence on rest-frame u - r colors of spiral galaxies; such a tendency was not observed in our sample.

Astronomy & Astrophysics↗
DOE OSTI2020

Towards a classification of rank r $\mathscr{N}$ = 2 SCFTs. Part II. Special Kahler stratification of the Coulomb branch

We study the stratification of the singular locus of four dimensional $\mathscr{N}$ = 2 Coulomb branches. We present a set of self-consistency conditions on this stratification which can be used to extend the classification of scale-invariant rank 1 Coulomb branch geometries to two complex dimensions, and beyond. The calculational simplicity of the arguments presented here stems from the fact that the main ingredients needed - the rank 1 deformation patterns and the pattern of inclusions of rank 2 strata - are discrete topological data which satisfy strong self-consistency conditions through their relationship to the central charges of the SCFT. This relationship of the stratification data to the central charges is used here, but is derived and explained in a companion paper by one of the authors. We illustrate the use of these conditions by re-analyzing many previously-known examples of rank 2 SCFTs, and also by finding examples of new theories. The power of these conditions stems from the fact that for Coulomb branch stratifications a conjecturally complete list of physically allowed “elementary slices” is known. By contrast, constraining the possible elementary slices of symplectic singularities relevant for Higgs branch stratifications remains an open problem.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

SERS-based ssDNA composition analysis with inhomogeneous peak broadening and reservoir computing

Surface-enhanced Raman spectroscopy employed in conjunction with post-processing machine learning methods is a promising technique for effective data analysis, allowing one to enhance the molecular and chemical composition analysis of information rich DNA molecules. In this work, we report on a room temperature inhomogeneous broadening as a function of the increased adenine concentration and employ this feature to develop one-dimensional and two dimensional chemical composition classification models of 200 long single stranded DNA sequences. Afterwards, we develop a reservoir computing chemical composition classification scheme of the same molecules and demonstrate enhanced performance that does not rely on manual feature identification.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

“Understanding Robustness Lottery”: A Geometric Visual Comparative Analysis of Neural Network Pruning Approaches

Deep learning approaches have provided state-of-the-art performance in many applications by relying on large and overparameterized neural networks. However, such networks are very brittle and are difficult to deploy on resource-limited platforms. Model pruning, i.e., reducing the size of the network, is a widely adopted strategy that can lead to a more robust and compact model. Many heuristics exist for model pruning, but our understanding of the pruning process remains limited due to the black-box nature of a neural network model. Empirical studies show that some heuristics improve performance whereas others can make models more brittle. Here, this work aims to shed light on how different pruning methods alter the network’s internal feature representation and the corresponding impact on model performance. To facilitate a comprehensive comparison and characterization of the high-dimensional model feature space, we introduce a visual geometric analysis of feature representations. We evaluated a set of critical geometric concepts decomposed from the commonly adopted classification loss and used them to design a visualization system to compare and highlight the impact of pruning on model performance and feature representation. The proposed tool provides an environment for an in-depth comparison of pruning methods and a comprehensive understanding of how the model responds to common data corruption. By leveraging the proposed visualization, machine learning researchers can reveal the similarities between pruning methods and redundancy in robustness evaluation benchmarks, obtain geometric insights about the differences between pruned models that achieve superior robustness performance, and identify samples that are robust or fragile to model pruning and common data corruption.

Li, Zhimin [Univ. of Utah, Salt Lake City, UT (Uni↗
DOE OSTI2022

Exploring the universality of hadronic jet classification

The modeling of jet substructure significantly differs between Parton Shower Monte Carlo (PSMC) programs. Despite this, we observe that machine learning classifiers trained on different PSMCs learn nearly the same function. This means that when these classifiers are applied to the same PSMC for testing, they result in nearly the same performance. This classifier universality indicates that a machine learning model trained on one simulation and tested on another simulation (or data) will likely be optimal. Our observations are based on detailed studies of shallow and deep neural networks applied to simulated Lorentz boosted Higgs jet tagging at the LHC.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗