Search NASA⌕ Search

SEARCH · Search NASA

Results for “Misclassification”

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.

13 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Misclassification in Workers’ Telecommuting Frequency Choices Using a Generalized Extreme Value Model

Telecommuting frequency is a response variable collected in travel surveys and is, therefore, prone to errors leading to mismeasurements or misclassification. Misclassification of explanatory variables is a common risk when using statistical modeling techniques. We define “misclassification” as a response reported or recorded in the wrong category; for example, a variable is recorded as a 1 when it should be 0. Here, in this context, this study aims to develop a statistical model to analyze telecommuting data which accounts for potential misclassification errors by building on existing literature in econometrics. The empirical analysis was undertaken using the 2017 National Household Travel Survey (NHTS) and the general extreme value (GEV) models available in the literature. Specifically, the frequency of telecommuting days was analyzed using the negative binomial (NB) model recast as the multinomial logit (MNL) model. By nature—and consistent with other studies—NHTS data are prone to errors that can be classified as intentional or unintentional misinformation provided by the person being interviewed. Ignoring these errors while modeling telecommuting frequencies using standard discrete count models can result in biased parameter estimates. The misclassification parameter was calculated for both over-reporting and under-reporting scenarios. The misclassification errors can be as high as 14% over-reported and 10% under-reported, particularly for the neighboring values. Statistical fit comparison between the models shows that models that ignore misclassification have worse data fit and biased parameter estimates with significant policy implications.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

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

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

Shanmugavelu, Sanjif [Maxeler Technologies, a Groq↗
DOE OSTI2024

Proof-of-concept chemometric approach for environmental forensic sourcing of crude oil samples using SPME-GC-MS

Environmental exposure to crude oil through seepage and spillage poses risks to the immediate environment and the broader ecosystem as areas along the oil distribution path are affected by the influx of crude petroleum as well as the environmental, economic, and civil unrest that accompanies it. There is a large financial burden associated with the lost resources, including the cost of rehabilitation, and the affected sources of revenue for communities affected by oil spills. As such, it is crucial to determine the responsible parties. This work outlines an environmental forensics approach to determining the source of an un-weathered crude oil sample. The researchers employed solid phase microextraction coupled with gas chromatography mass spectrometry (SPME-GC-MS) to capture and analyze the gaseous components emitted by crude oil samples sourced from five locations. Samples were analyzed using Spearman's rank correlation and 3D covariance analysis. Both chemometric approaches yielded optimal performance results with no misclassifications, true positive rate (TPR) = 100 % and false positive rate (FPR) = 0 %. The similarity metrics calculated by each test noted clear delineations between the values of same-source and differently sourced samples. The Spearman's rank correlation test and 3D covariance calculations both demonstrated the ability to correctly identify sample source origin in this dataset. Finally, the authors outline an approach to the future application of these tests and suggest their joint use in future crude oil sourcing endeavors.

3D covariance mapping↗
DOE OSTI2026

Robust Containment Queries over Collections of Trimmed NURBS Surfaces via Generalized Winding Numbers

Here, we propose a containment query that is robust to the watertightness of regions bound by trimmed NURBS surfaces, as this property is difficult to guarantee for in-the-wild CAD models. Containment is determined through the generalized winding number (GWN), a mathematical construction that is indifferent to the arrangement of surfaces in the shape. Applying contemporary techniques for the 3D GWN to trimmed NURBS surfaces requires some form of geometric discretization, introducing computational inefficiency to the algorithm and even risking containment misclassifications near the surface. In contrast, our proposed method leverages properties of the 3D solid angle to solve the relevant surface integral using a boundary formulation with rapidly converging adaptive quadrature. Batches of queries are further accelerated by memoizing (i.e., caching and reusing) quadrature node positions and tangents as they are evaluated. We demonstrate that our GWN method is robust to complex trimming geometry in a CAD model, and is accurate up to arbitrary precision at arbitrary distances from the surface. The derived containment query is therefore robust to model non-watertightness while respecting all curved features of the input shape.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Anomaly Detection in Seismic Data with Deep Learning: Application for Instrument Failure Detection and Forecasting

Seismic data quality assessment (QA) is the first and one of the most important steps before conducting any further data analysis. Traditional methods involve checking various metrics, such as spike detection and power spectral density, by setting strict thresholds or comparing data against synthetic benchmarks. However, these approaches often rely on pre-existing knowledge and assumptions about data anomalies, leading to potential misclassification of unusual cases. Here, in this study, we propose a deep autoencoder model, an unsupervised learning approach that evaluates data quality without making assumptions about normal and anomalous data, which can be used to identify deviations in recorded data that may indicate nascent instrument failure. We test the model with the U.S. International Monitoring System (IMS) seismic stations and demonstrate the capability of detecting anomalies on a monthly scale. This could prompt station operators to examine potential problems early, allowing sufficient time for instrument maintenance to prevent data outages. In addition, we use a new manually selected testing dataset to compare our model performance against two supervised machine learning (ML) approaches and a standard QA package, as baseline models. When applied to the dataset containing known data anomalies, performance of the supervised and unsupervised ML approaches is similar, with an accuracy of 88.1% for our model compared to ∼90% for the supervised ML approach and 78.2% for the standard QA package. Our model outperforms the baseline models when applied to new stations, where new types of data anomalies can be station-specific and not included in the training dataset. Finally, we show model transferability by training the model with data from the Global Seismograph Network only and applying it to the IMS network data. The results suggest that our model is generalizable and can be applied to new stations with good accuracy.

Lin, Jiun-Ting [Lawrence Livermore National Labora↗
DOE OSTI2025

NeuroSymbolic Approaches as a Vector for Assured Artificial Intelligence

The deployment of artificial intelligence systems in critical applications requires higher levels of assurance for safety, security, and interpretability. While neurosymbolic (NESY) approaches combining neural networks with symbolic reasoning offer potential advantages for assured AI, existing differentiable neurosymbolic frameworks face significant limitations including computational overhead and performance constraints. This report investigates the ISED (InferSampleEstimateDescend) framework as an alternative approach that enables neurosymbolic learning without requiring endtoend differentiability. We evaluate ISED’s utility for geointelligence applications by comparing neurosymbolic models against standard neural networks on aircraft classification tasks using the RarePlanes and MTARSI imagery datasets. Our results demonstrate that while ISEDbased models achieve slightly lower accuracy (89.7% vs 92.1% on RarePlanes; 91.1% vs 92.5% on MTARSI), they provide critical explainability capabilities that enable tracing incorrect predictions back to specific attribute misclassifications. We also present an automated pipeline that generates both attributeclass mappings and neurosymbolic model architectures from natural language descriptions, significantly reducing the manual effort required for NESY model deployment. These findings suggest that ISED offers a promising direction for developing assured AI systems where interpretability and reasoning transparency are prioritized alongside performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

The Double-edged Sword of Data-driven Super-Resolution: Adversarial Super-resolution Models

Data-driven super-resolution (SR) methods are often integrated into imaging pipelines as preprocessing steps to improve downstream tasks such as classification and detection. However, these SR models introduce a previously unexplored attack surface into imaging pipelines. In this paper, we present AdvSR, a framework demonstrating that adversarial behavior can be embedded directly into SR model weights during training, requiring no access to inputs at inference time. Unlike prior attacks that perturb inputs or rely on backdoor triggers, AdvSR operates entirely at the model level. By jointly optimizing for reconstruction quality and targeted adversarial outcomes, AdvSR produces models that appear benign under standard image quality metrics while inducing downstream misclassification. We evaluate AdvSR on three SR architectures (SRCNN, EDSR, SwinIR) paired with a YOLOv11 classifier and demonstrate that AdvSR models can achieve high attack success rates with minimal quality degradation. These findings highlight a new model-level threat for imaging pipelines, with implications for how practitioners source and validate models in safety-critical applications.

Sullivan, Haley [ORNL] (ORCID:0000000274069217)↗
DOE OSTI2024

Recognizing Blazars Using Radio Morphology from the VLA Sky Survey

Abstract Blazars are radio-loud active galactic nuclei whose jets have a very small angle to our line of sight. Observationally, the radio emissions are mostly compact or compact-core with a one-sided jet. With 2.″5 resolution at 3 GHz, the Very Large Array Sky Survey (VLASS) enables us to resolve the structure of some blazar candidates in the sky north of decl. −40°. We introduce an algorithm to classify radio sources as either blazar-like or non-blazar-like based on their morphology in the VLASS images. We apply our algorithm to three existing catalogs, including one of the known blazars (Roma-BzCAT) and two blazar candidates identified by Wide-field Infrared Survey Explorer colors and radio emission (WIBRaLS, KDEBLLACS). We show that in all three catalogs, there are objects with morphologies inconsistent with being blazars. Considering all the catalogs, more than 12% of the candidates are unlikely to be blazars, based on this analysis. Notably, we show that 3% of the Roma-BzCATconfirmedblazars could be a misclassification based on their VLASS morphology. The resulting table with all sources and their radio morphological classification is available online.

Astronomy & Astrophysics↗
DOE OSTI2024

The Impact of Void-finding Algorithms on Galaxy Classification

We explore how the definition of a void influences the conclusions drawn about the impact of the void environment on galactic properties using two void-finding algorithms in the Void Analysis Software Toolkit: Voronoi Voids (V 2 ), a Python implementation of ZOnes Bordering On Voidness (ZOBOV); and VoidFinder, an algorithm that grows and merges spherical void regions. Using the Sloan Digital Sky Survey Data Release 7, we find that galaxies found in VoidFinder voids tend to be bluer and fainter and to have higher (specific) star formation rates than galaxies in denser regions. Conversely, galaxies found in V 2 voids show less significant differences when compared to galaxies in denser regions, less consistent with the large-scale environmental effects on galaxy properties expected from both simulations and previous observations. These results align with previous simulation results that show V 2 -identified voids “leak” into the dense walls between voids because their boundaries extend up to the density maxima in the walls. As a result, when using ZOBOV-based void-finders, galaxies likely to be part of wall regions are instead classified as void galaxies, a misclassification that can be critical to our understanding of galaxy evolution.

cosmic web↗
DOE OSTI2026

Robust Measurement of Stellar Streams around the Milky Way: Correcting Spatially Variable Observational Selection Effects in Optical Imaging Surveys

Observations of density variations in stellar streams are a promising probe of low-mass dark matter substructure in the Milky Way. However, survey systematics such as variations in seeing and sky brightness can also induce artificial fluctuations in the observed densities of known stellar streams. These variations arise because survey conditions affect both object detection and star–galaxy misclassification rates. To mitigate these effects, we use Balrog synthetic source injections in the Dark Energy Survey (DES) Y3 data to calculate detection rate variations and classification rates as functions of survey properties. We show that these rates are nearly separable with respect to survey properties and can be estimated with sufficient statistics from the synthetic catalogs. Applying these corrections reduces the standard deviation of relative detection rates across the DES footprint by a factor of 5, and our corrections significantly change the inferred linear density of the Phoenix stream when including faint objects. Additionally, for artificial streams with DES-like survey properties we are able to recover density power spectra with reduced bias. We also find that uncorrected power-spectrum results for Legacy Survey of Space and Time (LSST)-like data can be around 5 times more biased, highlighting the need for such corrections in future ground-based surveys.

79 ASTRONOMY AND ASTROPHYSICS↗
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↗
NASA NTRS2026

Incremental Learning for Passive Microwave Precipitation Retrievals using Advanced Technology Microwave Sounder

Spaceborne passive microwave (PMW) radiometry is central to global precipitation monitoring, yet retrieval uncertainties remain substantial, particularly for cross-track sounders whose variable footprints and channel configurations are optimized for atmospheric temperature and moisture profiling rather than precipitation. Consequently, existing operational products often exhibit angular-dependent biases, limited effective swath utilization, unrealistic rainfall probability distributions, and systematic misclassification of precipitation phase. These limitations are further compounded by the scarcity of globally accurate and representative precipitation observations, as training data from the Dual-frequency Precipitation Radar (DPR) and the Cloud Profiling Radar (CPR) are spatially sparse, lack uniform global coverage, and exhibit heterogeneous error characteristics across precipitation regimes. To address these challenges, this study presents a supervised retrieval algorithm that incrementally trains an ensemble of extreme gradient-boosted decision trees by augmenting base learners with pre-training on reanalysis data and post-training on coincident DPR and CPR observations matched with the Advanced Technology Microwave Sounder (ATMS). By transferring prior information from reanalysis to posterior constraints from radar observations and adopting a sequential detection–estimation strategy for precipitation phase and rate retrieval, the proposed approach yields retrievals across the full ATMS swath that are largely free from persistent deficiencies in current Global Precipitation Measurement (GPM) passive microwave operational products. In particular, the method resolves bimodal artifacts in rainfall retrievals and mitigates systematic high-latitude snowfall biases, including overestimation across the Arctic and underestimation across the Antarctic. Validation against independent Multi-Radar Multi-Sensor (MRMS) data over the Contiguous United States (CONUS) further demonstrates improved performance in precipitation phase detection and rate estimation relative to both reanalysis and current GPM PMW products.

Mahyar Garshasbi↗
DOE OSTI2026

Open Set Recognition for Unknown Waveform Classification

This presentation applies open set recognition to classify unknown waveforms, enabling systems to not only identify known types but also reliably detect when waveforms fall outside the training distribution. This approach enhances robustness by avoiding forced misclassification of novel or anomalous signals.

99 - GENERAL AND MISCELLANEOUS↗