Results for “machine learning classification” — Page 6

DOE OSTI2024

Improving Text Classification with Large Language Model-Based Data Augmentation

Large Language Models (LLMs) such as ChatGPT possess advanced capabilities in understanding and generating text. These capabilities enable ChatGPT to create text based on specific instructions, which can serve as augmented data for text classification tasks. Previous studies have approached data augmentation (DA) by either rewriting the existing dataset with ChatGPT or generating entirely new data from scratch. However, it is unclear which method is better without comparing their effectiveness. This study investigates the application of both methods to two datasets: a general-topic dataset (Reuters news data) and a domain-specific dataset (Mitigation dataset). Our findings indicate that: 1. ChatGPT generated new data consistently enhanced model’s classification results for both datasets. 2. Generating new data generally outperforms rewriting existing data, though crafting the prompts carefully is crucial to extract the most valuable information from ChatGPT, particularly for domain-specific data. 3. The augmentation data size affects the effectiveness of DA; however, we observed a plateau after incorporating 10 samples. 4. Combining the rewritten sample with new generated sample can potentially further improve the model’s performance.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

A Semi-supervised Hybrid Machine Learning Framework for the Qualification of Resistance Spot Welds

• Industries requiring high structural integrity, including automotive, aerospace, and construction, place considerable significance on weld quality classification. • The inspection normally involves human expertise through predefined quality metrics that are subjective, error-prone, and time-intensive • The challenge to classification model development is the scarcity of labeled data and imbalanced distributions in the data that are labeled. • This work develops a new hybrid methodology that achieves clustering using KMeans++ together with supervised classification to overcome these challenges. • The ensemble-based classifiers were identified as optimal, with accuracy enhancements of up to 8% using the pseudo-labeled dataset. • The work provides practical insight into feature engineering and machine learning integration in industrial quality assurance applications.

Rogers, Jeremy K. [Savannah River National Laborat↗

DOE OSTI2025

A Morphological Model to Separate Resolved–Unresolved Sources in the DESI Legacy Surveys: Application in the LS4 Alert Stream

Separating resolved and unresolved sources in large imaging surveys is a fundamental step to enable downstream science, such as searching for extragalactic transients in wide-field time-domain surveys. Here we present our method to effectively separate point sources from the resolved, extended sources in the Dark Energy Spectroscopic Instrument (DESI) Legacy Surveys (LS). We develop a supervised machine learning model based on the Gradient Boosting algorithm XGBoost. The features input to the model are purely morphological and are derived from the tabulated LS data products. We train the model using ∼2 × 10 5 LS sources in the COSMOS field with HST morphological labels and evaluate the model performance on LS sources with spectroscopic classification from the DESI Data Release 1 (∼2 × 10 7 objects) and the Sloan Digital Sky Survey Data Release 17 (∼3 × 10 6 objects), as well as on ∼2 × 10 8 Gaia stars. A significant fraction of LS sources are not observed in every LS filter, and we therefore build a “Hybrid” model as a linear combination of two XGBoost models, each containing features combining aperture flux measurements from the “blue” (gr) and “red” (iz) filters. The Hybrid model shows a reasonable balance between sensitivity and robustness, and achieves higher accuracy and flexibility compared to the LS morphological typing. With the Hybrid model, we provide classification scores for ∼3 × 10 9 LS sources, making this the largest ever machine learning catalog separating resolved and unresolved sources. The catalog has been incorporated into the real-time pipeline of the La Silla Schmidt Southern Survey (LS4), enabling the identification of extragalactic transients within the LS4 alert stream.

astrostatistics↗

DOE OSTI2026

Hybrid Quantum–Classical Graph Transformers for Efficient Sentiment Analysis

Quantum Machine Learning (QML) offers a promising paradigm that leverages quantum computing principles to develop efficient and expressive models for learning from complex and structured data. Recent advances in natural language processing (NLP) and artificial intelligence (AI) have demonstrated capabilities in understanding, generating, and reasoning over linguistic and multimodal information. In this work, we present the Quantum Graph Transformer (QGT), a hybrid quantum–classical architecture that extends graph transformer capabilities through quantum self-attention. The QGT models variable-length sentences as token graphs, where both the embedding encoding and the self-attention mechanisms are implemented using parameterized quantum circuits (PQCs), enabling efficient contextual learning with significantly fewer trainable parameters. We train QGT using both fully connected and 𝑘 -nearest-neighbor graph structures and evaluate it on five benchmark sentiment-classification datasets. Experimental results show that QGT consistently achieves higher or comparable accuracy to existing quantum NLP models and outperforms a Classical Graph Transformer (CGT) baseline with identical architecture, achieving 29.4 × fewer parameters while requiring 3–5 × fewer samples to reach comparable performance. These findings highlight the potential of graph-based quantum models as scalable and data-efficient architectures for natural language understanding.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2024

Evaluating Material Design Principles for Calcium-Ion Mobility in Intercalation Cathodes

Multivalent-ion batteries offer an alternative to Li-based technologies, with the potential for greater sustainability, improved safety, and higher energy density, primarily due to their rechargeable system featuring a passivating metal anode. Although a system based on the Ca 2+ /Ca couple is particularly attractive given the low electrochemical plating potential of Ca 2+ , the remaining challenge for a viable rechargeable Ca battery is to identify Ca cathodes with fast ion transport. In this work, a high-throughput computational pipeline is adapted to (1) discover novel Ca cathodes in a largely unexplored space of empty intercalation hosts and (2) develop material design rules for Ca-ion mobility. One candidate from the screening, W 2 O 3 (PO 4 ) 2 , is confirmed to have a low Nudged Elastic Band (NEB) barrier of 168 meV within a one-dimensional (1D) ion percolation topology. This candidate is subsequently synthesized and electrochemically tested, achieving reversible Ca cycling with a capacity of 25 mA h/g. To further accelerate the screening for promising Ca intercalation electrodes, machine learning (ML) Random Forest (RF) and Extreme Gradient Boosting (XGB) classification models are created with local environment descriptors based on a large, structurally and chemically diverse dataset of minimum energy pathways, spanning over 5,000 density functional theory (DFT) site energy calculations. Accuracies of 92% are achieved, material design metrics are quantified, ML force-fields are leveraged in an accelerated iteration of the screening, and a total of 27 novel Ca cathode materials are highlighted for further investigation.

25 ENERGY STORAGE↗

DOE OSTI2026

Simultaneous Probe of the Charm and Bottom Quark Yukawa Couplings Using $t\bar{t}$𝐻 Events

A search for the standard model Higgs boson decaying to a charm quark-antiquark pair, 𝐻→$c\bar{c}$, produced in association with a top quark-antiquark pair ($t\bar{t}$𝐻) is presented. The search is performed with data from proton-proton collisions at √𝑠 =13 TeV, corresponding to an integrated luminosity of 138 fb−1. Advanced machine learning techniques are employed for jet flavor identification and event classification. The Higgs boson decay to a bottom quark-antiquark pair is measured simultaneously and the observed $t\bar{t}$𝐻(𝐻→$b\bar{b}$) event rate relative to the standard model expectation is 0.91$^{+0.26}_{−0.22}$. The observed (expected) upper limit on the product of production cross section and branching fraction 𝜎⁡($t\bar{t}$𝐻)⁢ℬ⁡(𝐻→$c\bar{c}$) is 0.11 (0.13) pb at 95% confidence level, corresponding to 7.8 (8.7) times the standard model prediction. When combined with the previous search for 𝐻 →$c\bar{c}$ via associated production with a 𝑊 or 𝑍 boson, the observed (expected) 95% confidence interval on the Higgs-charm Yukawa coupling modifier, 𝜅 𝑐 , is |𝜅 𝑐 | < 3.5 (2.7), the most stringent constraint to date.

Bottom quark↗

DOE OSTI2025

PhotonIDs: ML-Powered Photon Identification System for Dark Count Elimination

Reliable single photon detection is the foundation for practical quantum communication and networking. However, today's superconducting nanowire single photon detector(SNSPD) inherently fails to distinguish between genuine photon events and dark counts, leading to degraded fidelity in long-distance quantum communication. In this work, we introduce PhotonIDs, a machine learning-powered photon identification system that is the first end-to-end solution for real-time discrimination between photons and dark count based on full SNSPD readout signal waveform analysis. PhotonIDs ~demonstrates: 1) an FPGA-based high-speed data acquisition platform that selectively captures the full waveform of signal only while filtering out the background data in real time; 2) an efficient signal preprocessing pipeline, and a novel pseudo-position metric that is derived from the physical temporal-spatial features of each detected event; 3) a hybrid machine learning model with near 98% accuracy achieved on photon/dark count classification. Additionally, proposed PhotonIDs ~ is evaluated on the dark count elimination performance with two real-world case studies: (1) 20 km quantum link, and (2) Erbium ion-based photon emission system. Our result demonstrates that PhotonIDs ~could improve more than 31.2 times of signal-noise-ratio~(SNR) on dark count elimination. PhotonIDs ~ marks a step forward in noise-resilient quantum communication infrastructure.

Linne, Karl C. [Chicago U.] (ORCID:000900091870358↗

DOE OSTI2024

Rapid, antibiotic incubation-free determination of tuberculosis drug resistance using machine learning and Raman spectroscopy

Tuberculosis (TB) is the world’s deadliest infectious disease, with over 1.5 million deaths and 10 million new cases reported anually. The causative organism Mycobacterium tuberculosis (Mtb) can take nearly 40 d to culture, a required step to determine the pathogen’s antibiotic susceptibility. Both rapid identification and rapid antibiotic susceptibility testing of Mtb are essential for effective patient treatment and combating antimicrobial resistance. Here, we demonstrate a rapid, culture-free, and antibiotic incubation-free drug susceptibility test for TB using Raman spectroscopy and machine learning. We collect few-to-single-cell Raman spectra from over 25,000 cells of the Mtb complex strain Bacillus Calmette-Guérin (BCG) resistant to one of the four mainstay anti-TB drugs, isoniazid, rifampicin, moxifloxacin, and amikacin, as well as a pan-susceptible wildtype strain. By training a neural network on this data, we classify the antibiotic resistance profile of each strain, both on dried samples and on patient sputum samples. On dried samples, we achieve >98% resistant versus susceptible classification accuracy across all five BCG strains. In patient sputum samples, we achieve ~79% average classification accuracy. We develop a feature recognition algorithm in order to verify that our machine learning model is using biologically relevant spectral features to assess the resistance profiles of our mycobacterial strains. Finally, we demonstrate how this approach can be deployed in resource-limited settings by developing a low-cost, portable Raman microscope that costs <$5,000. We show how this instrument and our machine learning model enable combined microscopy and spectroscopy for accurate few-to-single-cell drug susceptibility testing of BCG.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2026

Optimizing Neutrino Flavor Conversion Measurements through Machine Learning

The phenomenon of neutrino flavor conversion whereby the flavor of a neutrino particle can change between its time of production and later detection was the first definitive evidence of physics beyond the Standard Model. Some of the oscillation parameters used to describe this conversion are not yet well measured, leaving important questions still open regarding flavor conversion both in vacuum and as neutrinos travel through matter. NOvA is a long-baseline neutrino oscillation experiment that uses Fermilab's predominantly $\nu_\mu$ NuMI beam. A 14 kton oil-based liquid scintillator far detector 810 km away is used to measure neutrino oscillation through the $\nu_\mu$ disappearance and $\nu_e$ appearance channels. Super-K is a 50 kton water Cherenkov detector, which measures the disappearance of $\nu_e$ produced during solar fusion. The high density environment of the sun decreases the $\nu_e$ survival probability at higher energies observable in Super-K compared to the vacuum-dominated oscillations at lower energies. However, the transition region is overshadowed by radioactive background in the detector. In both of these experiments, the separation of neutrino detection events from background and classification of neutrino flavor are crucial tasks that benefit from the introduction of machine learning. Chapter 1 gives an overview of neutrinos and the context under which flavor conversion is measured in this dissertation. Chapters 2-7 present the results of a Bayesian sampling approach for the latest NOvA 3-flavor oscillation analysis with $26.6 \times 10^{20}$ protons on target in neutrino mode and $12.5 \times 10^{20}$ in antineutrino mode collected over 10 years. Chapters 8-13 present the results of extending the Super-K solar analysis to lower energies during its fourth phase with 2970 days of livetime.

Yankelevich, Alejandro Jaime [UC, Irvine]↗

DOE OSTI2026

Optimizing Neutrino Flavor Conversion Measurements through Machine Learning

The phenomenon of neutrino flavor conversion whereby the flavor of a neutrino particle can change between its time of production and later detection was the first definitive evidence of physics beyond the Standard Model. Some of the oscillation parameters used to describe this conversion are not yet well measured, leaving important questions still open regarding flavor conversion both in vacuum and as neutrinos travel through matter. NOvA is a long-baseline neutrino oscillation experiment that uses Fermilab's predominantly $\nu_\mu$ NuMI beam. A 14 kton oil-based liquid scintillator far detector 810 km away is used to measure neutrino oscillation through the $\nu_\mu$ disappearance and $\nu_e$ appearance channels. Super-K is a 50 kton water Cherenkov detector, which measures the disappearance of $\nu_e$ produced during solar fusion. The high density environment of the sun decreases the $\nu_e$ survival probability at higher energies observable in Super-K compared to the vacuum-dominated oscillations at lower energies. However, the transition region is overshadowed by radioactive background in the detector. In both of these experiments, the separation of neutrino detection events from background and classification of neutrino flavor are crucial tasks that benefit from the introduction of machine learning. Chapter 1 gives an overview of neutrinos and the context under which flavor conversion is measured in this dissertation. Chapters 2-7 present the results of a Bayesian sampling approach for the latest NOvA 3-flavor oscillation analysis with $26.6 \times 10^{20}$ protons on target in neutrino mode and $12.5 \times 10^{20}$ in antineutrino mode collected over 10 years. Chapters 8-13 present the results of extending the Super-K solar analysis to lower energies during its fourth phase with 2970 days of livetime.

Yankelevich, Alejandro Jaime [UC, Irvine]↗

DOE OSTI2026

Optimizing Neutrino Flavor Conversion Measurements through Machine Learning

The phenomenon of neutrino flavor conversion whereby the flavor of a neutrino particle can change between its time of production and later detection was the first definitive evidence of physics beyond the Standard Model. Some of the oscillation parameters used to describe this conversion are not yet well measured, leaving important questions still open regarding flavor conversion both in vacuum and as neutrinos travel through matter. NOvA is a long-baseline neutrino oscillation experiment that uses Fermilab's predominantly $\nu_\mu$ NuMI beam. A 14 kton oil-based liquid scintillator far detector 810 km away is used to measure neutrino oscillation through the $\nu_\mu$ disappearance and $\nu_e$ appearance channels. Super-K is a 50 kton water Cherenkov detector, which measures the disappearance of $\nu_e$ produced during solar fusion. The high density environment of the sun decreases the $\nu_e$ survival probability at higher energies observable in Super-K compared to the vacuum-dominated oscillations at lower energies. However, the transition region is overshadowed by radioactive background in the detector. In both of these experiments, the separation of neutrino detection events from background and classification of neutrino flavor are crucial tasks that benefit from the introduction of machine learning. Chapter 1 gives an overview of neutrinos and the context under which flavor conversion is measured in this dissertation. Chapters 2-7 present the results of a Bayesian sampling approach for the latest NOvA 3-flavor oscillation analysis with $26.6 \times 10^{20}$ protons on target in neutrino mode and $12.5 \times 10^{20}$ in antineutrino mode collected over 10 years. Chapters 8-13 present the results of extending the Super-K solar analysis to lower energies during its fourth phase with 2970 days of livetime.

Yankelevich, Alejandro Jaime [UC, Irvine] (ORCID:0↗

DOE OSTI2024

Behavioral Segmentation and Clustering of Geospatial Trajectories

The rapid growth of global positioning system (GPS) devices has led to a corresponding increase in the size of GPS datasets. While these large GPS datasets contain a wealth of information about the behaviors of the moving objects in them, manual classification and anomaly detection are prohibitively time consuming. We utilize unsupervised machine learning techniques to first identify the behaviors for individual moving objects and then cluster those objects by their behavioral sequences. In this way, trajectories behaving unusually as well as common patterns of behavior are both detectable in large datasets without requiring an a priori definition of "unusual" or "common."

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Investigating resource-efficient neutron/gamma classification ML models targeting eFPGAs

There has been considerable interest and resulting progress in implementing machine learning (ML) models in hardware over the last several years from the particle and nuclear physics communities. A big driver has been the release of the Python package, hls4ml, which has enabled porting models specified and trained using Python ML libraries to register transfer level (RTL) code. So far, the primary end targets have been commercial field-programmable gate arrays (FPGAs) or synthesized custom blocks on application specific integrated circuits (ASICs). However, recent developments in open-source embedded FPGA (eFPGA) frameworks now provide an alternate, more flexible pathway for implementing ML models in hardware. These customized eFPGA fabrics can be integrated as part of an overall chip design. In general, the decision between a fully custom, eFPGA, or commercial FPGA ML implementation will depend on the details of the end-use application. In this work, we explored the parameter space for eFPGA implementations of fully-connected neural network (fcNN) and boosted decision tree (BDT) models using the task of neutron/gamma classification with a specific focus on resource efficiency. We used data collected using an AmBe sealed source incident on Stilbene, which was optically coupled to an OnSemi J-series silicon photomultiplier (SiPM) to generate training and test data for this study. We investigated relevant input features and the effects of bit-resolution and sampling rate as well as trade-offs in hyperparameters for both ML architectures while tracking total resource usage. The performance metric used to track model performance was the calculated neutron efficiency at a gamma leakage of 10 -3 . The results of the study will be used to aid the specification of an eFPGA fabric, which will be integrated as part of a test chip.

47 OTHER INSTRUMENTATION↗

DOE OSTI2024

Improved enzyme functional annotation prediction using contrastive learning with structural inference

Not Available

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2025

Defect Complexes in CrSBr Revealed Through Electron Microscopy and Deep Learning

Atomic defects underpin the properties of van der Waals materials, and their understanding is essential for advancing quantum and energy technologies. Scanning transmission electron microscopy is a powerful tool for defect identification in atomically thin materials, and extending it to multilayer and beam-sensitive materials would accelerate their exploration. Here, we establish a comprehensive defect library in a bilayer of the magnetic quasi-1D semiconductor CrSBr by combining atomic-resolution imaging, deep learning, and calculations. We apply a custom-developed machine learning work flow to detect, classify, and average point vacancy defects. This classification enables us to uncover several distinct Cr interstitial defect complexes, combined Cr and Br vacancy defect complexes, and lines of vacancy defects that extend over many unit cells. We show that their occurrence is in agreement with our computed structures and binding energy densities, reflecting the intriguing layer interlocked crystal structure of CrSBr. Our ab initio calculations show that the interstitial defect complexes give rise to highly localized electronic states. These states are of particular interest due to the reduced electronic dimensionality and magnetic properties of CrSBr and are, furthermore, predicted to be optically active. Our results broaden the scope of defect studies in challenging materials and reveal new defect types in bilayer CrSBr that can be extrapolated to the bulk and to over 20 materials belonging to the same FeOCl structural family.

deep learning↗

DOE OSTI2025

Reference Shapefiles and Pre-trained Random Forest Classification Models for Detecting Aufeis on the North Slope of Alaska in Landsat Imagery

This dataset provides shapefiles and trained machine learning models used for aufeis detection at four sites on the North Slope of Alaska. It includes reference data for evaluating Landsat-based detection methods, supporting research on remote sensing approaches for identifying aufeis. The ReferenceData folder contains ArcGIS shapefiles of semi-automated land cover classifications for 217 Landsat Collection 2 images, categorizing pixels into six classes: aufeis, snow, ground, none, water, and cloud. The SiteBuffers.zip file includes 10-kilometer buffer shapefiles defining regions of interest around four aufeis fields (Canning21, FH1, Firth, and Kuparuk), used to test three detection techniques. Additionally, the TrainedRFModels folder contains six pre-trained Scikit-Learn Random Forest classifiers (100 trees, max depth = 30) designed to predict aufeis presence in Landsat Collection 2 Surface Reflectance images using Red, Blue, SWIR2, NDVI, and NDWI bands. This dataset supports the development and validation of remote sensing methods for mapping aufeis in Arctic environments.The Next-Generation Ecosystem Experiments: Arctic (NGEE Arctic), was a research effort to reduce uncertainty in Earth System Models by developing a predictive understanding of carbon-rich Arctic ecosystems and feedbacks to climate. NGEE Arctic was supported by the Department of Energy's Office of Biological and Environmental Research.The NGEE Arctic project had two field research sites: 1) located within the Arctic polygonal tundra coastal region on the Barrow Environmental Observatory (BEO) and the North Slope near Utqiagvik (Barrow), Alaska and 2) multiple areas on the discontinuous permafrost region of the Seward Peninsula north of Nome, Alaska.Through observations, experiments, and synthesis with existing datasets, NGEE Arctic provided an enhanced knowledge base for multi-scale modeling and contributed to improved process representation at global pan-Arctic scales within the Department of Energy's Earth system Model (the Energy Exascale Earth System Model, or E3SM), and specifically within the E3SM Land Model component (ELM).

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

Automated RF Phase Adjustment for Beam Stabilization in the Fermilab Linac

The Fermilab Linac experiences longitudinal beam phase drift, leading to increased particle loss, conventionally corrected through labor-intensive manual RF adjustments. This project explores machine learning-based automation for drift correction, employing a prototype-based classification approach. Our model utilizes a 34-dimensional feature set (RF settings and BPM readings) and leverages a 7x27 response matrix for system modeling. To overcome limited real-world data, we generate synthetic data, enhancing model training and generalizability. Custom loss functions, including a surrogate energy-consistent loss and a temporal smoothness constraint, ensure physically plausible drift predictions. The goal is a robust system for autonomous phase adjustments, ensuring stable beam acceleration and reduced manual intervention.

Chichili, R. R. [Illinois U., Chicago]↗

DOE OSTI2025

Automated RF Phase Adjustment for Beam Stabilization in the Fermilab Linac

The Fermilab Linac experiences longitudinal beam phase drift, leading to increased particle loss, conventionally cor- rected through labor-intensive manual RF adjustments. This project explores machine learning-based automation for drift correction, employing a prototype-based classification approach. Our model utilizes a 34-dimensional feature set (RF settings and BPM readings) and leverages a 7x27 response matrix for system modeling. To overcome limited real-world data, we generate synthetic data, enhancing model training and generalizability. Custom loss functions, including a sur- rogate energy-consistent loss and a temporal smoothness constraint, ensure physically plausible drift predictions. The goal is a robust system for autonomous phase adjustments, ensuring stable beam acceleration and reduced manual intervention.

Chichili, R. R. [U. Illinois, Chicago]↗