SEARCH · Engineering Papers

Results for “leverage scores”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Resolving turbulent magnetohydrodynamics: a hybrid operator-diffusion framework

We present a hybrid machine learning framework that combines physics-informed neural operators (PINOs) with score-based generative diffusion models to simulate the full spatio-temporal evolution of two-dimensional, incompressible, resistive magnetohydrodynamic turbulence across a broad range of Reynolds numbers (Re). The framework leverages the equation-constrained generalization capabilities of PINOs to predict coherent, low-frequency dynamics, while a conditional diffusion model stochastically corrects high-frequency residuals, enabling accurate modeling of fully developed turbulence. Trained on a comprehensive ensemble of high-fidelity simulations with Re ϵ {100, 250, 500, 750, 1000, 3000, 10000}, the approach achieves state-of-the-art accuracy in regimes previously inaccessible to deterministic surrogates. At Re = 1000 and 3000, the model faithfully reconstructs the full spectral energy distributions of both velocity and magnetic fields late into the simulation, capturing non-Gaussian statistics, intermittent structures, and cross-field correlations with high fidelity. At extreme turbulence levels (Re = 10 000), it remains the first surrogate capable of recovering the high-wavenumber evolution of the magnetic field, preserving large-scale morphology and enabling statistically meaningful predictions.

Diffusion-Integrated Neural Operators↗

DOE OSTI2026

MTL_TX: A Multi-Task Transformer Model for Improved Radiation Time-Series Estimation

Controlling radiation doses at potential radioactive facilities is critical to ensuring the safety of both personnel and the public. At the Thomas Jefferson National Accelerator Facility (JLab), multiple sensors are deployed around the three experimental halls to monitor key parameters, including single-beam current, energy levels, current leakage, and radiation values during accelerator operations. In this study, we developed a Multi-task Transformer model, MTL_TX, to accurately estimate radiation doses at sensor locations based on historical data, with the aim of enhancing safety in accelerator facilities and surrounding public areas. To improve estimation accuracy, we integrated two innovative components into the proposed model: hierarchical feature embedding (HFE) and multi-level decomposition attention (MDA). Additionally, the multi-task learning (MTL) framework effectively leverages correlations among multiple sensors, enabling individual estimations for each sensor. MTL_TX achieved outstanding results on data collected in 2018, with an MSE of 0.1464, an RMSE of 0.2353, and an R 2 score of 0.8584. Furthermore, when trained on 2018 data, MTL_TX exhibited excellent generalization capability to unseen datasets from 2016 to 2019, achieving an MSE of 0.1407, an RMSE of 0.2263, and an R 2 score of 0.8831. These results demonstrate a significant improvement over existing state-of-the-art models.

Transformer↗

NASA NTRSDate not supplied

Contextualizing Air Traffic Management Conversations using Natural Language Understanding

Efficient management of air traffic and mitigation of delays depend on extracting actionable information from unstructured data, such as dialogues from the Federal Aviation Administration’s (FAA’s) Air Traffic Control System Command Center (ATCSCC) telecons. This study presents a pipeline utilizing Natural Language Processing (NLP) methods for Intent Classification (IC) and Slot Filling (SF) to identify and extract Traffic Management Initiatives (TMIs) from aviation-specific dialogues. We leveraged DeBERTa, a pre-trained transformer model, and fine-tuned it to the nuances of the aviation domain. Despite challenges posed by annotation complexities, the IC model achieved promising results with a weighted average F1-score of 0.81. Our results are close to those of human annotators, which demonstrates the model’s strong alignment with human-level performance. The SF model also showed strong performance, achieving a weighted F1-score of 0.97, which demonstrates its effectiveness in accurately predicting key slots. Our analysis revealed limitations in handling less frequent intents and slot labels due to data sparsity, motivating future efforts to adopt joint IC-SF modeling and data augmentation strategies. This research highlights the potential of domain-specific NLP to streamline decision-making in the aviation industry and improve the management of TMIs.

Air Traffic Control Management↗

NASA NTRS2005

Semantic Analysis of Email Using Domain Ontologies and WordNet

The problem of capturing and accessing knowledge in paper form has been supplanted by a problem of providing structure to vast amounts of electronic information. Systems that can construct semantic links for natural language documents like email messages automatically will be a crucial element of semantic email tools. We have designed an information extraction process that can leverage the knowledge already contained in an existing semantic web, recognizing references in email to existing nodes in a network of ontology instances by using linguistic knowledge and knowledge of the structure of the semantic web. We developed a heuristic score that uses several forms of evidence to detect references in email to existing nodes in the Semanticorganizer repository's network. While these scores cannot directly support automated probabilistic inference, they can be used to rank nodes by relevance and link those deemed most relevant to email messages.

Berrios, Daniel C.↗

DOE OSTI2026

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

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

Bruna, Tomas [Lawrence Berkeley National Laborator↗

DOE OSTI2026

Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy

Training machine learning models for radioisotope identification using gamma spectroscopy remains an elusive challenge for many practical applications, largely stemming from the difficulty of acquiring and labeling large, diverse experimental datasets. Simulations can mitigate this challenge, but the accuracy of models trained on simulated data can deteriorate substantially when deployed to an out-of-distribution operational environment. In this study, we demonstrate that unsupervised domain adaptation (UDA) can improve the ability of a model trained on synthetic data to generalize to a new testing domain, provided unlabeled data from the target domain are available. Conventional supervised techniques are unable to utilize this data because the absence of isotope labels precludes defining a supervised classification loss. Instead, we first pretrain a spectral classifier using labeled synthetic data and subsequently leverage unlabeled target data to align the learned feature representations between the source and target domains. We compare a range of different UDA techniques, finding that minimizing the maximum mean discrepancy (MMD) between source and target feature vectors yields the most consistent improvement to testing scores. For instance, using a custom transformer-based neural network, we achieved a testing accuracy of $0.904 \pm 0.022$ on an experimental LaBr test set after performing unsupervised feature alignment via MMD minimization, compared to $0.754 \pm 0.014$ before alignment. Overall, our results highlight the potential of using UDA to adapt a radioisotope classifier trained on synthetic data for real-world deployment.

Lalor, Peter W.↗

DOE OSTI2024

Machine Learning Applications in Analyzing the Role of Shale Barriers and Baffles for CO2 Storage

This study uses machine learning to analyze microseismic data from the Illinois Basin Decatur Project (IBDP) and quantify CO₂ plume extents. By leveraging well logs, microseismic records, and CO₂ injection metrics, the research predicts subsurface CO₂ plume dynamics. Findings show vertical clustering of microseismic events near the injection well, with CO₂ periodically breaching barriers due to buoyancy. K-Means clustering performed best, achieving the highest Silhouette Score and lowest Davies-Bouldin Index. This capability is crucial for real-time monitoring and management of CO₂ sequestration sites, validated against physical models and IBDP data, reinforcing CO₂ geological sequestration's viability and enhancing management tools.

Carr, Timothy↗

DOE OSTI2026

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

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

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Automating the Analysis of Large Language Models Responses through Zero-Shot Question Answering

Recent advancements in Large Language Models (LLMs) have shown significant potential in various applications, yet their evaluation, particularly in zero-shot question answering scenarios, remains a challenging task. In this study, our objective was to explore precision metrics for Large Language Models (LLM) and design and implement a software pipeline to automatically evaluate LLMs' outputs under zero-shot question answering. Zero-shot question answering involves a model providing answers to questions about topics it hasn't seen during training. It leverages the principles of zero-shot learning by relying on semantic understanding and generalization from related knowledge. The data used was metadata from medical databases on congenital heart disease. We explored eleven LLM metrics and selected three for our evaluation: BLEU, BERTScore, and MoverScore. BLEU calculates a score based on the overlap of n-grams (contiguous sequences of n items, typically words) between the machine-generated translation and the reference translations. Higher BLEU scores indicate better correspondence between the machine-generated and human-generated translations. BERTScore is a metric used to evaluate the quality of machine-generated text by measuring the similarity of token embeddings produced by BERT (Bidirectional Encoder Representations from Transformers) between the generated text and reference text. MoverScore is a metric that quantifies the dissimilarity between the distributions of word embeddings from machine-generated text and reference text, emphasizing semantic similarity over exact token overlap. We also introduced HBKI, a composite metric summarizing these approaches. We tested five models —GPT-3, Llama-2, Gemini 1.5 Pro, Solar 10.7B, and Mixtral-8x7b. Our software pipeline, designed and implemented using Object-Oriented Programming principles, allows users to customize the selection and extraction of features for topics of interest in their own research. Our results show that MoverScore delivered the most precise evaluation of the LLM's outputs, while Mixtral-8x7b achieved the best overall performance in extracting metadata from the databases.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Bigpicc: a graph-based approach to identifying carcinogenic gene combinations from mutation data

Abstract Genome data from cancer patients represents relationships between the presence of a gene mutation and cancer occurrence in a patient. Different types of cancer in human are thought to be caused by combinations of two to nine gene mutations. Identifying these combinations through traditional exhaustive search requires the amount of computation that scales exponentially with the combination size and in most cases is intractable even for cutting-edge supercomputers. We propose a parameter-free heuristic approach that leverages the intrinsic topology of gene-patient mutations to identify carcinogenic combinations. The biological relevance of the identified combinations is measured by using them to predict the presence of tumor in previously unseen samples. The resulting classifiers for 16 cancer types perform on par with exhaustive search results, and score the average of 80.1% sensitivity and 91.6% specificity for the best choice of hit range per cancer type. Our approach is able to find higher-hit carcinogenic combinations targeting which would take years of computations using exhaustive search.

Biochemistry & Molecular Biology↗

DOE OSTI2025

On the Abuse and Detection of Polyglot Files

A polyglot is a file that is valid in two or more formats. Polyglot files pose a problem for file-upload and generative AI web interfaces that rely on format identification to determine how to securely handle incoming files. In this work we found that existing file-format and embedded-file detection tools, even those developed specifically for polyglot files, fail to reliably detect polyglot files used in the wild. To address this issue, we studied the use of polyglot files by malicious actors in the wild, finding 30 polyglot samples and 15 attack chains that leveraged polyglot files. Using knowledge from our survey of polyglot usage in the wild---the first of its kind---we created a novel data set based on adversary techniques. We then trained a machine learning detection solution, PolyConv, using this data set. PolyConv achieves a precision-recall area-under-curve score of 0.999 with an F1 score of 99.20% for polyglot detection and 99.47% for file-format identification, significantly outperforming all other tools tested. We developed a content disarmament and reconstruction tool, ImSan, that successfully sanitized 100% of the tested image-based polyglots, which were the most common type found via the survey. Our work provides concrete tools and suggestions to enable defenders to better defend themselves against polyglot files, as well as directions for future work to create more robust file specifications and methods of disarmament.

Oesch, T [ORNL] (ORCID:0000000269091022)↗

DOE OSTI2025

AI-Enabled Operations at Fermi Complex: Multivariate Time Series Prediction for Outage Prediction and Diagnosis

The Main Control Room of the Fermilab accelerator complex continuously gathers extensive time-series data from thousands of sensors monitoring the beam. However, unplanned events such as trips or voltage fluctuations often result in beam outages, causing operational downtime. This downtime not only consumes operator effort in diagnosing and addressing the issue but also leads to unnecessary energy consumption by idle machines awaiting beam restoration. The current threshold-based alarm system is reactive and faces challenges including frequent false alarms and inconsistent outage-cause labeling. To address these limitations, we propose an AI-enabled framework that leverages predictive analytics and automated labeling. Using data from $2,703$ Linac devices and $80$ operator-labeled outages, we evaluate state-of-the-art deep learning architectures, including recurrent, attention-based, and linear models, for beam outage prediction. Additionally, we assess a Random Forest-based labeling system for providing consistent, confidence-scored outage annotations. Our findings highlight the strengths and weaknesses of these architectures for beam outage prediction and identify critical gaps that must be addressed to fully harness AI for transitioning downtime handling from reactive to predictive, ultimately reducing downtime and improving decision-making in accelerator management.

Jain, Milan [PNL, Richland] (ORCID:000000021676111↗

DOE OSTI2025

FL‐ADS: Federated learning anomaly detection system for distributed energy resource networks

Abstract With the ongoing development of Distributed Energy Resources (DER) communication networks, the imperative for strong cybersecurity and data privacy safeguards is increasingly evident. DER networks, which rely on protocols such as Distributed Network Protocol 3 and Modbus, are susceptible to cyberattacks such as data integrity breaches and denial of service due to their inherent security vulnerabilities. This paper introduces an innovative Federated Learning (FL)‐based anomaly detection system designed to enhance the security of DER networks while preserving data privacy. Our models leverage Vertical and Horizontal Federated Learning to enable collaborative learning while preserving data privacy, exchanging only non‐sensitive information, such as model parameters, and maintaining the privacy of DER clients' raw data. The effectiveness of the models is demonstrated through its evaluation on datasets representative of real‐world DER scenarios, showcasing significant improvements in accuracy and F1‐score across all clients compared to the traditional baseline model. Additionally, this work demonstrates a consistent reduction in loss function over multiple FL rounds, further validating its efficacy and offering a robust solution that balances effective anomaly detection with stringent data privacy needs.

Purohit, Shaurya [Iowa State University Ames Iowa ↗

DOE OSTI2024

Data-Informed Evaluation Framework for Integrated Energy Systems: Insights from Power, Process Heat, and Hydrogen Production Applications

The multi-criteria decision analysis (MCDA) framework provides a systematic evaluation of the diverse preferences and performance metrics associated with alternative solutions. This approach is advantageous over a single-criterion methodology, which are only valid under conditions that assume ceteris paribus or an "apples-to-apples" comparison. However, selecting suitable technologies for integrated energy systems (IES) can be likened to an "apples-to-oranges" comparison, given the heterogeneous factors at stake. These factors include economics and performance parameters, geological compatibility, and environmental impacts. Consequently, past research has often employed a mixture of qualitative and quantitative criteria tailored to the specific interests of each study. While the method proves effective in handling the intricate interplay of criteria, the resulting rankings and scores can vary from study to study. This inconsistency is introduced from the use of subjectively defined thresholds and weights. As a result, decision-makers frequently find it challenging to establish clear connections between specific criteria and the resulting scores, as the transformation of criteria into ordinal scores results in a substantial loss of information. To address this challenge, we introduce a data-informed IES evaluation framework that offers comprehensive, interpretable, and traceable evaluations backed by quantifiable rationale. First, we identified key IES evaluation criteria from a decade of literature, focusing on relevant IES applications in power, process heat, and hydrogen production. We leveraged state-of-the-art cost estimates from the Idaho National Laboratory (INL) and technical data from 78 reactor designs from the International Atomic Energy Agency (IAEA) and the Organization for Economic Co-operation and Development - Nuclear Energy Agency (OECD-NEA). Lastly, we established thresholds by analyzing the mean, variance, root mean square, and slope of values across alternatives, categorizing the preferences of decision-makers into distinct utility functions, such as linear, saturating, exponential, and stepwise. Our approach yielded two main outcomes: (1) it provided consistent assessments across different stakeholder groups and (2) it visualized uncertainties in the decision-making context via comprehensive sensitivity analysis. To demonstrate the impact of our framework, we conducted case studies on 6 reactor designs (AP1000, NuScale, BWRX-300, Xe-100, eVinci, iMSR) for the three applications. Our data-driven framework proved to be highly effective in addressing heterogenous uncertainties faced by varied decision-makers? preferences and IES applications, as well as cost and technical estimates of advanced reactors.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2024

Data-Informed Evaluation Framework for Integrated Energy Systems: Insights from Power, Process Heat, and Hydrogen Production Applications

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

NASA NTRS2019

Comprehensive Assessment of Models and Events Using Library Tools (CAMEL) Framework: Time Series Comparisons

The Comprehensive Assessment of Models and Events using Library Tools (CAMEL) framework leverages existing Community Coordinated Modeling Center services: Run on Request post processing tools that generate model time series outputs and the new Community Coordinated Modeling Center Metadata Registry that describes simulation runs using Space Physics Archive Search and Extract metadata. The new CAMEL visualization tool compares the modeled time series with observational data and computes a suite of skill scores such as Prediction Efficiency, Root Mean Square Error, and Symmetric Signed Percentage Bias. Model data pairs used for skill calculations are obtained considering a user selected maximum difference between the time of observation and the nearest model output. The system renders available data for all locations and time periods selected using interactive visualizations that allow the user to zoom, pan, and pick data values along traces. Skill scores are reported for each selected event or aggregated over all events for all participating model runs. Separately, scores are reported for all locations (satellites or stations) and for each location individually. We are building on past experiences with model data comparisons of magnetosphere and ionosphere model outputs from GEM2008, GEMCEDAR Electrodynamics Thermosphere Ionosphere, and the SWPC Operational Space Weather Model challenges. The CAMEL visualization tool is demonstrated using three validation studies: (a) Wang Sheeley Arge heliosphere simulations compared against OMNI solar wind data, (b) ground magnetic perturbations from several magnetosphere and ionosphere electrodynamics models as observed by magnetometers, and (c) electron fluxes from several ring current simulations compared to Radiation Belt Storm Probes Helium Oxygen Proton Electron instrument measurements, integrated over different energy ranges.

Rastätter, Lutz↗

DOE OSTI2025

Aided Active Learning (AAL) for Enhanced Critical Heat Flux Prediction

Accurate prediction of critical heat flux (CHF) is crucial for the safe and efficient operation of nuclear reactors. Traditional CHF modeling methods often require extensive experimental data, which are hard to obtain. This study introduces the Aided Active Learning (AAL) framework, which strategically minimizes data requirements without sacrificing model accuracy. Unlike conventional Active Learning (AL), AAL introduces an additional step of randomly selecting a subset from the sample pool before applying the query strategy. To evaluate the performance of AAL, two query strategies—uncertainty-based sampling and error-reduction sampling—were evaluated across the following models: random forest (RF), feedforward neural network (FNN), and variational feedforward neural network (vFNN). The proposed framework demonstrated that AAL effectively reduces the number of training samples needed to achieve comparable predictive accuracy. For the RF model, AL required only 710 samples to achieve an R2 score of 0.98, as compared to the 4,785 samples needed by random sampling. Similarly, the FNN model achieved the same R2 score with just 355 samples when using AL, a significant improvement over the 825 samples required by random sampling. In case of uncertainty-based sampling strategy, vFNN attained an R2 of 0.98 with 3,420 samples, reducing the sample requirement by 47% relative to the 6,440 samples needed for random sampling. Its performance suggests that larger training data are required to fully leverage its uncertainty quantification capabilities.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2024

Semantic Stealth: Crafting Covert Adversarial Patches for Sentiment Classifiers Using Large Language Models

Deep learning models have been shown to be vulnerable to adversarial attacks, in which perturbations to their inputs cause the model to produce incorrect predictions. As opposed to adversarial attacks in computer vision, where small changes introduced to pixel values can drastically alter a model's output while remaining imperceptible to humans, text-based attacks are difficult to conceal due to the discrete nature of tokens. Consequently, unconstrained gradient-based attacks often produce adversarial examples that lack semantic meaning, rendering them detectable through visual inspection or perplexity filters. In contrast to methods that rely on gradient-based optimization in the embedding space, we propose an approach that leverages a Large Language Model's ability to generate grammatically correct and semantically meaningful text to craft adversarial patches that seamlessly blend in with the original input text. These patches can be used to alter the behavior of a target model, such as a text classifier. Since our approach does not rely on gradient backpropagation, it only requires access to the target model's confidence scores, making it a grey-box attack. We demonstrate the feasibility of our approach using open-source LLMs, including Intel's Neural Chat, Llama2, and Mistral-Instruct, to generate adversarial patches capable of altering the predictions of a distilBERT model fine-tuned on the IMDB reviews dataset for sentiment classification.

Roa Carvajal, Maria↗