Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “classification models”

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 1,009 records · Page 56
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Precision dispersive approaches versus unitarized chiral perturbation theory for the lightest scalar resonances $\sigma /f_0(500) $ and $\kappa /K_0^*(700) $

For several decades, the $\sigma /f_0(500) $ and $\kappa /K_0^*(700) $ resonances have been subject to long-standing debate. Both their existence and properties were controversial until very recently. In this tutorial review, we compare model-independent dispersive and analytic techniques versus unitarized Chiral Perturbation Theory, when applied to the lightest scalar mesons $\sigma /f_0(500) $ and $\kappa /K_0^*(700) $. Here, the former have settled the long-standing controversy about the existence of these states, providing a precise determination of their parameters, whereas unitarization of chiral effective theories allows us to understand their nature, spectroscopic classification and dependence on QCD parameters. Here we review in a pedagogical way their uses, advantages and caveats.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Extracting Material Property Measurement Data from Scientific Articles

Machine learning-based prediction of material properties is often hampered by the lack of sufficiently large training datasets. The majority of such measurement data is embedded in scientific literature and the ability to automatically extract these data is essential to support the development of reliable property prediction methods. In this work, we describe a methodology for an automatic property extraction framework using material solubility as the target property. We create an annotated dataset containing tags for solubility-related entities using a combination of regular expressions and manual tagging. We then compare five entity recognition models leveraging both token-level and span-level architectures on the task of classifying solute names, solubility values, and solubility units. Additionally, we explore a novel pretraining approach that leverages automated chemical name and quantity extraction tools to generate large datasets that do not rely on intensive manual effort. Finally, we perform an analysis to identify the causes of classification errors.

Panapitiya, Gihan U.↗
DOE OSTI2022

Performance of New Near-Real-Time PERSIANN Product (PDIR-Now) for Atmospheric River Events over the Russian River Basin, California

Most heavy precipitation events and extreme flooding over the U.S. Pacific coast can be linked to prevalent atmospheric river (AR) conditions. Thus, reliable quantitative precipitation estimation with a rich spatiotemporal resolution is vital for water management and early warning systems of flooding and landslides over these regions. At the same time, high-quality near-real-time measurements of AR precipitation remain challenging due to the complex topographic features of land surface and meteorological conditions of the region: specifically, orographic features occlude radar measurements while infrared-based algorithms face challenges, differentiating between both cold brightband (BB) precipitation and the warmer nonbrightband (NBB) precipitation. It should be noted that the latter precipitation is characterized by greater orographic enhancement. In this study, we evaluate the performance of a recently developed near-real-time satellite precipitation algorithm: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN) Dynamic Infrared–Rain Rate-Now (PDIR-Now). This model is primarily dependent on infrared information from geostationary satellites as input; consequently, PDIR-Now has the advantage of short data latency, 15–60-min delay between observation to precipitation product delivery. The performance of PDIR-Now is analyzed with a focus on AR-related events for cases dominated by NBB and BB precipitation over the Russian River basin. In our investigations, we utilize S-band (3-GHz) precipitation profilers with Joss/Parsivel disdrometer measurements at the Middletown and Santa Rosa stations to classify BB and NBB precipitation events. In general, our analysis shows that PDIR-Now is more skillful in retrieving precipitation rates over both BB and NBB events across the topologically complex study area as compared to PERSIANN-Cloud Classification System (CCS). Also, we discuss the performance of well-known operational near-real-time precipitation products from 2017 to 2019. Conventional categorical and volumetric categorical indices, as well as continuous statistical metrics, are used to show the differences between various high-resolution precipitation products such as Multi-Radar Multi-Sensor (MRMS).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Classification of Ultrasonic Weld Quality using Acoustic Signatures Acquired During Manufacture

Ultrasonic welding is a process is based on generating a solid-state bond between two metals by applying moderate pressure and high intensity sound waves (20-70 kHz frequencies) at their interface. During the solid-state process numerous material, surface, instrument, and environmental factors contribute to bond formation, strength, and durability. The inherent difficulty of measuring and controlling each of these factors has, to date, made predicting bond quality elusive. In this work, a Sonics model MWB20 ultrasonic spot welder with integral base, was used to produce a variety of welds of different metal foils under varying weld conditions. Acoustic measurements were recorded throughout the measurement process. Subsequent analysis of the signals using metrics that approximate the energy dispersed during the weld proved to successfully predict weld quality. Two metrics based on normalized energy differential and Renyi entropy were developed into Python and C++ scripts for direct analysis of weld acoustic data.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Chemical and genetic characterization of the ungrouped pallasite Lieksa

The meteorite Lieksa was found in 2017 in Löpönvaara, Finland, and later donated to the Finnish Museum of Natural History. Here, we report siderophile element concentrations, genetic isotopic data, and a metal–silicate segregation age for the meteorite. The ~280 g Lieksa is ~80% metal and ~20% silicate and oxide inclusions by volume, with the inclusions consisting primarily of Fe-rich olivine. Due to Lieksa's silicate content, coupled with a texture characterized by metal enclosing the silicates, it has been classified as a pallasite. Lieksa's olivine and bulk chemical characteristics are distinct from those of the known pallasite and iron meteorite groups, consistent with its classification as ungrouped. The meteorite exhibits a flat, chondrite-normalized highly siderophile element pattern, consistent with an origin as an early crystallization product from a metallic melt with chondritic relative abundances. Molybdenum, Ru, and 183 W isotopic data indicate that Lieksa formed in the non-carbonaceous (NC) domain of the solar nebula. Radiogenic 182 W abundances for Lieksa yield a model metal–silicate segregation age of 1.5 ± 0.8 Myr after calcium-aluminum-rich inclusion formation, which is within the range established for other NC-type pallasite and iron meteorite parent bodies.

58 GEOSCIENCES↗
DOE OSTI2024

High-dimensional and permutation invariant anomaly detection

Methods for anomaly detection of new physics processes are often limited to low-dimensional spaces due to the difficulty of learning high-dimensional probability densities. Particularly at the constituent level, incorporating desirable properties such as permutation invariance and variable-length inputs becomes difficult within popular density estimation methods. In this work, we introduce a permutation-invariant density estimator for particle physics data based on diffusion models, specifically designed to handle variable-length inputs. We demonstrate the efficacy of our methodology by utilizing the learned density as a permutation-invariant anomaly detection score, effectively identifying jets with low likelihood under the background-only hypothesis. To validate our density estimation method, we investigate the ratio of learned densities and compare to those obtained by a supervised classification algorithm.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2026

AT2025ulz and S250818k: Zooming in with the Hubble Space Telescope

AT2025ulz is an optical/near-infrared transient discovered during follow-up of the candidate gravitational wave (GW) event S250818k. Its young age (≲1 day), rapid decline, and strong color evolution over the first 48 hr classify it as a potential kilonova candidate. In this work, we present the results of our observing campaign, carried out with the Gran Telescopio Canarias and the Hubble Space Telescope (HST). Although the early time evolution of AT2025ulz resembles some aspects of a kilonova, its rapid onset (∼3 hr after the GW trigger) and luminosity (a factor of ∼5 brighter than AT2017gfo in g band) are difficult to reproduce. Only a small subset of our kilonova models matches its multicolor light curve, and the inferred ejecta mass is uncomfortably large given the low chirp mass (≲0.87 M ⊙ ) of the GW candidate. HST observations place the transient within a nearby (z = 0.08489) spiral galaxy with ongoing star formation and measure a color (F336W − F160W ≈ 1.4 mag) that is too blue to match with a kilonova. Our data support the classification of AT2025ulz as a supernova, initially undergoing a shock-cooling phase and later entering its photospheric phase and spectroscopically identified via its broad absorption features.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Classification of fragile topology enabled by matrix homotopy

Flat bands in twisted materials have attracted considerable attention due to the emergence of correlated phases that can be associated with the non-Wannier-representable nature of its single-particle states. Specifically, these bands can exhibit a class of topology that can be nullified by the addition of trivial bands, termed fragile topology, which has required an expansion of prior classification schemes. However, existing approaches for predicting fragile topology rely on momentum-space methods, e.g., Wilson loops, presenting a fundamental challenge for using fragile topology as a predictor of correlated phases in aperiodic systems, such as incommensurate twist angles in moiré materials. Here, we develop a ℤ 2 energy-resolved topological marker for classifying fragile phases using a system’s position-space description, enabling the direct classification of finite, disordered, and aperiodic materials. By translating the physical symmetries protecting the system’s fragile topological phase into matrix symmetries of the system’s Hamiltonian and position operators, we use matrix homotopy to construct our topological marker while simultaneously yielding a quantitative measure of topological robustness. We demonstrate our framework’s effectiveness in both a low-energy tight-binding model and a continuum photonic crystal model of 𝐶 2 ⁢𝒯-symmetric systems, and find that fragile topology can both persist under strong disorder and even exhibit disorder-induced reentrant phase transitions. Our photonic crystal results also demonstrate the robustness of fragile topology, and the applicability of our approach, to heterostructures lacking a bulk spectral gap. Overall, our framework serves as an efficient tool for elucidating fragile topology, offering guidance for the prediction and discovery of correlated phases in both crystalline and aperiodic materials.

Lee, Ki Young [Sandia National Laboratories (SNL-N↗
DOE OSTI2024

Retrieval Augmented Generation for Robust Cyber Defense

In cybersecurity, the ability to efficiently analyze and respond to vulnerabilities, weaknesses, attack patterns, and threat tactics is critical for effective defense strategies. With the increasing complexity and volume of cybersecurity data, traditional methods of querying and retrieving information are often inadequate. To address this challenge, we implemented Retrieval-Augmented Generation (RAG) systems—CyRAG and GraphCyRAG—that integrate large language models (LLMs) with both structured data from relational databases and knowledge graphs such as Neo4j. CyRAG is designed to handle structured data, focusing on CVE (Common Vulnerabilities and Exposures) and CWE (Common Weakness Enumeration) entities to generate accurate and context-rich responses. In contrast, GraphCyRAG leverages Neo4j knowledge graphs to retrieve interconnected information from CVE, CWE, CAPEC (Common Attack Pattern Enumeration and Classification), and ATT&CK (Adversarial Tactics, Techniques, and Common Knowledge) datasets. By utilizing Neo4j’s graph-based framework, GraphCyRAG enables deeper traversal of relationships between vulnerabilities and attack patterns, providing cybersecurity analysts with more comprehensive insights into potential attack vectors and mitigation strategies. Our preliminary results demonstrate that integrating knowledge graphs with RAG significantly enhances both the accuracy and depth of threat analysis, allowing for the retrieval of dynamic, real-time data and the generation of contextually aware responses. This approach helps analysts uncover hidden relationships between cyber entities, predict exploit paths, and prioritize mitigation efforts effectively. The integration of RAG with cybersecurity knowledge graphs represents a significant advancement in cybersecurity threat intelligence, enabling more informed decision-making and stronger defense strategies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Peri-Net-Pro: the neural processes with quantified uncertainty for crack patterns

Abstract This paper develops a deep learning tool based on neural processes (NPs) called the Peri-Net-Pro, to predict the crack patterns in a moving disk and classifies them according to the classification modes with quantified uncertainties. In particular, image classification and regression studies are conducted by means of convolutional neural networks (CNNs) and NPs. First, the amount and quality of the data are enhanced by using peridynamics to theoretically compensate for the problems of the finite element method (FEM) in generating crack pattern images. Second, case studies are conducted with the prototype microelastic brittle (PMB), linear peridynamic solid (LPS), and viscoelastic solid (VES) models obtained by using the peridynamic theory. The case studies are performed to classify the images by using CNNs and determine the suitability of the PMB, LBS, and VES models. Finally, a regression analysis is performed on the crack pattern images with NPs to predict the crack patterns. The regression analysis results confirm that the variance decreases when the number of epochs increases by using the NPs. The training results gradually improve, and the variance ranges decrease to less than 0.035. The main finding of this study is that the NPs enable accurate predictions, even with missing or insufficient training data. The results demonstrate that if the context points are set to the 10th, 100th, 300th, and 784th, the training information is deliberately omitted for the context points of the 10th, 100th, and 300th, and the predictions are different when the context points are significantly lower. However, the comparison of the results of the 100th and 784th context points shows that the predicted results are similar because of the Gaussian processes in the NPs. Therefore, if the NPs are employed for training, the missing information of the training data can be supplemented to predict the results.

Mathematics↗
DOE OSTI2023

Optimizing training trajectories in variational autoencoders via latent Bayesian optimization approach *

Unsupervised and semi-supervised ML methods such as variational autoencoders (VAE) have become widely adopted across multiple areas of physics, chemistry, and materials sciences due to their capability in disentangling representations and ability to find latent manifolds for classification and/or regression of complex experimental data. Like other ML problems, VAEs require hyperparameter tuning, e.g. balancing the Kullback–Leibler and reconstruction terms. However, the training process and resulting manifold topology and connectivity depend not only on hyperparameters, but also their evolution during training. Because of the inefficiency of exhaustive search in a high-dimensional hyperparameter space for the expensive-to-train models, here we have explored a latent Bayesian optimization (zBO) approach for the hyperparameter trajectory optimization for the unsupervised and semi-supervised ML and demonstrated for joint-VAE with rotational invariances. We have demonstrated an application of this method for finding joint discrete and continuous rotationally invariant representations for modified national institute of standards and technology database (MNIST) and experimental data of a plasmonic nanoparticles material system. The performance of the proposed approach has been discussed extensively, where it allows for any high dimensional hyperparameter trajectory optimization of other ML models.

42 ENGINEERING↗
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 OSTI2026

Microstructure prediction for Ti-22Al-25Nb in laser powder bed fusion

This work presents a physics-informed framework for predicting solidification morphology and defect susceptibility in additively manufactured Ti–22Al–25Nb across a broad processing space. The framework integrates solidification microstructure selection (SMS) analysis with a single-track defect-based printability map to establish a unified methodology linking processing parameters to both interfacial morphology and manufacturability. Thermal gradients G and solidification rates R are first computed using the Thermo-Calc Additive Manufacturing (TC-AM) module, a finite-interface-dissipation (FID) phase-field (PF) model coupled with CALPHAD method is then employed to systematically distinguish planar and dendritic regimes as functions of $G$ and $R$. By superimposing the printability map onto the morphology projections, a comprehensive process–structure framework is obtained. Across most processing conditions, the predicted microstructure is predominantly dendritic, while planar growth emerges only under selected laser power $P$ and scan speed $v$ combinations. In addition to morphology classification, the framework quantifies the dendritic area fraction and introduces a width-based morphology descriptor to characterize the spatial extent of planar/dendritic regions within the melt pool. It provides mechanistic insight into the interplay between solidification physics and defect formation, offering practical guidance for parameter selection and microstructural control in Ti–22Al–25Nb additive manufacturing (AM).

36 MATERIALS SCIENCE↗
DOE OSTI2025

Confidence-weighted integration of human and machine judgments for superior decision-making

Large language models (LLMs) can surpass humans in certain forecasting tasks. What role does this leave for humans in the overall decision process? One possibility is that humans, despite performing worse than LLMs, can still add value when teamed with them. A human and machine team can surpass each individual teammate when team members’ confidence is well calibrated and team members diverge in which tasks they find difficult (i.e., calibration and diversity are needed). We simplified and extended a Bayesian approach to combining judgments using a logistic regression framework that integrates confidence-weighted judgments for any number of team members. Using this straightforward method, we demonstrated its effectiveness in both image classification and neuroscience forecasting tasks. Combining human judgments with one or more machines consistently improved overall team performance. Our hope is that this simple and effective strategy for integrating the judgments of humans and machines will lead to productive collaborations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A high resolution, gridded product for vapor pressure deficit using Daymet

Vapor pressure deficit (VPD) is a critical variable in assessing drought conditions and evaluating plant water stress. Gridded products of global and regional VPD are not freely available from satellite remote sensing, model reanalysis, or ground observation datasets. We present two versions of the first gridded VPD product for the Continental US and parts of Northern Mexico and Southern Canada (CONUS+) at a 1 km spatial resolution and daily time step. We derived VPD from Daymet maximum daily temperature and average daily vapor pressure and scale the estimates based on (1) climate determined by the Köppen-Geiger classifications and (2) land cover determined by the International Geosphere-Biosphere Programme. Ground-based VPD data from 253 AmeriFlux sites representing different climate and land cover classifications were used to improve the Daymet-derived VPD estimates for every pixel in the CONUS+ grid to produce the final datasets. We evaluated the Daymet-derived VPD against independent observations and reanalysis data. The CONUS+ VPD datasets will aid in investigating disturbances including drought and wildfire, and informing land management strategies.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Chemical reaction enhanced graph learning for molecule representation

Abstract Motivation Molecular representation learning (MRL) models molecules with low-dimensional vectors to support biological and chemical applications. Current methods primarily rely on intrinsic molecular information to learn molecular representations, but they often overlook effectively integrating domain knowledge into MRL. Results In this article, we develop a reaction-enhanced graph learning (RXGL) framework for MRL, utilizing chemical reactions as domain knowledge. RXGL introduces dual graph learning modules to model molecule representation. One module employs graph convolutions on molecular graphs to capture molecule structures. The other module constructs a reaction-aware graph from chemical reactions and designs a novel graph attention network on this graph to integrate reaction-level relations into molecular modeling. To refine molecule representations, we design a reaction-based relation learning task, which considers the relations between the reactant and product sides in reactions. In addition, we introduce a cross-view contrastive task to strengthen the cooperative associations between molecular and reaction-aware graph learning. Experiment results show that our RXGL achieves strong performance in various downstream tasks, including product prediction, reaction classification, and molecular property prediction. Availability and implementation The code is publicly available at https://github.com/coder-ACAC/RLM.

Biochemistry & Molecular Biology↗
DOE OSTI2021

Understanding the extreme luminosity of DES14X2fna

We present DES14X2fna, a high-luminosity, fast-declining Type IIb supernova (SN IIb) at redshift z = 0.0453, detected by the Dark Energy Survey (DES). DES14X2fna is an unusual member of its class, with a light curve showing a broad, luminous peak reaching M r ≃ –19.3 mag 20 d after explosion. This object does not show a linear decline tail in the light curve until ≃60 d after explosion, after which it declines very rapidly (4.30 ± 0.10 mag 100 d –1 in the r band). By fitting semi-analytic models to the photometry of DES14X2fna, we find that its light curve cannot be explained by a standard 56 Ni decay model as this is unable to fit the peak and fast tail decline observed. Inclusion of either interaction with surrounding circumstellar material or a rapidly-rotating neutron star (magnetar) significantly increases the quality of the model fit. Furthermore, we also investigate the possibility for an object similar to DES14X2fna to act as a contaminant in photometric samples of SNe Ia for cosmology, finding that a similar simulated object is misclassified by a recurrent neural network (RNN)-based photometric classifier as an SN Ia in ~1.1–2.4 per cent of cases in DES, depending on the probability threshold used for a positive classification.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

Global Explainability of A Deep Abstaining Classifier for Cancer Pathology Reports

We present a global explainability method to characterize sources of errors in a real-world multitask deep abstaining classifier (DAC), in the context of cancer histology prediction. Our multitask classifier, currently deployed for automated annotation of cancer pathology reports from NCI-SEER registries, was trained and evaluated on 1.04 million hand-annotated samples and makes simultaneous predictions of cancer site, subsite, histology, laterality, and behavior for each report. The DAC framework enables the model to abstain on ambiguous reports and confusing classes to achieve the target accuracy on the retained (non-abstained) samples, but at the cost of decreased coverage. Requiring 97% accuracy on the histology task caused our model to retain only 22% of all samples, mostly the less ambiguous and common classes. Local explainability with the GradInp technique provided a computationally efficient way of obtaining contextual reasoning for hundreds of thousands of individual predictions. Our method, involving dimensionality reduction of approximately 13000 aggregated local explanations (ALE), offers a tractable path to true global explainability. It enabled identification of sources of errors in histology classification, globally, as hierarchical complexity among classes, label noise, insufficient information, and conflicting evidence. This suggests several strategies for iterative improvement of our DAC, including well-designed exclusion criteria, focused annotation, and reduced penalties for errors involving hierarchically related classes.

59 BASIC BIOLOGICAL SCIENCES↗