Detecting Label Noise in Kepler Confirmed Planet Catalog using Machine Learning
Explore the source record for details and available documents.
Exoplanet↗
SEARCH · Search NASA
Results for “label noise”
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.
BUTTER - Empirical Deep Learning Dataset
The BUTTER Empirical Deep Learning Dataset represents an empirical study of the deep learning phenomena on dense fully connected networks, scanning across thirteen datasets, eight network shapes, fourteen depths, twenty-three network sizes (number of trainable parameters), four learning rates, six minibatch sizes, four levels of label noise, and fourteen levels of L1 and L2 regularization each. Multiple repetitions (typically 30, sometimes 10) of each combination of hyperparameters were preformed, and statistics including training and test loss (using a 80% / 20% shuffled train-test split) are recorded at the end of each training epoch. In total, this dataset covers 178 thousand distinct hyperparameter settings ("experiments"), 3.55 million individual training runs (an average of 20 repetitions of each experiments), and a total of 13.3 billion training epochs (three thousand epochs were covered by most runs). Accumulating this dataset consumed 5,448.4 CPU core-years, 17.8 GPU-years, and 111.2 node-years.
Array↗
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↗
A knowledge-informed large language model framework for U.S. nuclear power plant shutdown initiating event classification for probabilistic risk assessment
Identifying and classifying shutdown initiating events (SDIEs) is critical for developing shutdown probabilistic risk assessment for nuclear power plants. Existing computational approaches cannot achieve satisfactory performance due to the challenges of unavailable large, labeled datasets, imbalanced event types, and label noise. To address these challenges, we propose a hybrid pipeline that integrates a knowledge-informed machine learning model to prescreen non-SDIEs and a large language model (LLM) to classify SDIEs into four types. In the prescreening stage, we proposed a set of 44 SDIE text patterns that consist of the most salient keywords and phrases from six SDIE types. Text vectorization based on the SDIE patterns generates feature vectors that are highly separable by using a simple binary classifier. The second stage builds Bidirectional Encoder Representations from Transformers (BERT)-based LLM, which learns generic English language representations from self-supervised pretraining on a large dataset and adapts to SDIE classification by fine-tuning it on an SDIE dataset. The proposed approaches are evaluated on a dataset with 10,928 events using precision, recall ratio, F 1 score, and average accuracy. In conclusion, the results demonstrate that the prescreening stage can exclude more than 97% non-SDIEs, and the LLM achieves an average accuracy of 95.1% for SDIE classification.
99 - GENERAL AND MISCELLANEOUS↗
Assessing Membership Inference Attacks under Distribution Shifts
Membership inference attacks (MIAs) exploit machine learning models to infer whether a data point was in the training set, posing significant privacy risks even with limited black-box access. These attacks rely on the attacker approximating the target model’s training distribution, yet the impact of distribution shifts between target and shadow models on MIA success remains underexplored. We systematically evaluate five types of distribution shifts —-cutout, jitter, Gaussian noise, label shift, and attribute shift —- at varying intensities. Our results reveal that these shifts affect MIA effectiveness in nuanced ways, with some reducing attack success while others exacerbate vulnerabilities, and the same shift can have opposite effects depending on the type of MIA. This highlights the complex interplay between distributional differences and attack performance, offering critical insights for improving model defenses against MIAs.
Shi, Yichuan [Massachusetts Institute of Technolog↗
Small Hot Jet Acoustic Rig Validation
The Small Hot Jet Acoustic Rig (SHJAR), located in the Aeroacoustic Propulsion Laboratory (AAPL) at the NASA Glenn Research Center in Cleveland, Ohio, was commissioned in 2001 to test jet noise reduction concepts at low technology readiness levels (TRL 1-3) and develop advanced measurement techniques. The first series of tests on the SHJAR were designed to prove its capabilities and establish the quality of the jet noise data produced. Towards this goal, a methodology was employed dividing all noise sources into three categories: background noise, jet noise, and rig noise. Background noise was directly measured. Jet noise and rig noise were separated by using the distance and velocity scaling properties of jet noise. Effectively, any noise source that did not follow these rules of jet noise was labeled as rig noise. This method led to the identification of a high frequency noise source related to the Reynolds number. Experiments using boundary layer treatment and hot wire probes documented this noise source and its removal, allowing clean testing of low Reynolds number jets. Other tests performed characterized the amplitude and frequency of the valve noise, confirmed the location of the acoustic far field, and documented the background noise levels under several conditions. Finally, a full set of baseline data was acquired. This paper contains the methodology and test results used to verify the quality of the SHJAR rig.
Brown, Cliff↗
Statistical and Neural Network for Real Sensor-Data-Driven Anomaly Detection in Nuclear Applications
Anomaly detection (AD) in sensor data is critical to ensure uninterrupted functionality of nuclear power plants (NPPs). Consequently, AD model validation through real-world sensor data is important for applications in nuclear facilities. In this paper, we propose an Autoencoder (AE)—a multi-layered neural network, for AD in sensor data from an operational NPP testbed. Since the dataset lacks labels for irregularities, we introduce random noise and label them to effectively train our model. The proposed AE model assigns a higher reconstruction error to the abnormal samples that deviate from those encountered during the training phase and uses the reconstruction loss to detect anomalies in a representative imbalanced dataset. We also introduce an analytical solution—seasonal trend decomposition (STD)—as another AD scheme for identifying irregularities withinthe same time-series dataset. In contrast to the AE model which relies on reconstruction loss, the STD scheme decomposes the entire dataset into its trend, seasonality, and residual components to pinpoint irregularities. Our findings indicate that the proposed AE and STD models individually achieve recall scores of 97% and 92%, respectively. We validate the performance of the two models on both balanced and imbalanced data. We further solidify the results by picking the combined selected anomalies of the two solutions with an "AND" operator for more reliable predictions.
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
Statistical and Neural Network for Real Sensor-Data-Driven Anomaly Detection in Nuclear Applications
Anomaly detection (AD) in sensor data is critical to ensure uninterrupted functionality of nuclear power plants (NPPs). Consequently, validation of AD models through real-world sensor data is important for their application in nuclear facilities. In this paper, we propose an Autoencoder (AE)— a multi-layered neural network, for AD in sensor data from an operational NPP testbed. Since the dataset lacks labels for irregularities, we introduce random noise and label them to effectively train our model. The proposed AE model assigns a higher reconstruction error to the abnormal samples that deviate from those encountered during the training phase and uses the reconstruction loss to detect anomalies in a representative imbalanced dataset. We also introduce an analytical solution—seasonal trend decomposition (STD) — as another AD scheme for identifying irregularities within the same time-series dataset. In contrast to the AE model which relies on reconstruction loss, the STD scheme decomposes the entire dataset into its trend, seasonality, and residual components to pinpoint irregularities. Our findings indicate that the proposed AE and STD models individually achieve recall scores of 97% and 92%, respectively. We also validate the performance of the two models on both balanced and imbalanced data. We further solidify the results by picking the combined selected anomalies of the two solutions with an "AND" operator for more reliable predictions.
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
AveBoost2: Boosting for Noisy Data
AdaBoost is a well-known ensemble learning algorithm that constructs its constituent or base models in sequence. A key step in AdaBoost is constructing a distribution over the training examples to create each base model. This distribution, represented as a vector, is constructed to be orthogonal to the vector of mistakes made by the pre- vious base model in the sequence. The idea is to make the next base model's errors uncorrelated with those of the previous model. In previous work, we developed an algorithm, AveBoost, that constructed distributions orthogonal to the mistake vectors of all the previous models, and then averaged them to create the next base model s distribution. Our experiments demonstrated the superior accuracy of our approach. In this paper, we slightly revise our algorithm to allow us to obtain non-trivial theoretical results: bounds on the training error and generalization error (difference between training and test error). Our averaging process has a regularizing effect which, as expected, leads us to a worse training error bound for our algorithm than for AdaBoost but a superior generalization error bound. For this paper, we experimented with the data that we used in both as originally supplied and with added label noise-a small fraction of the data has its original label changed. Noisy data are notoriously difficult for AdaBoost to learn. Our algorithm's performance improvement over AdaBoost is even greater on the noisy data than the original data.
Oza, Nikunj C.↗
Towards Geospatial Knowledge Graph Infused Neuro-Symbolic AI for Remote Sensing Scene Understanding
Deep learning has proven its effectiveness in numerous tasks for remote sensing scene understanding. However there is an increasing interest to explore fusion of domain-specific background information to the deep neural network to further improve its performance. Remote sensing researchers are also working towards developing models that generalize and adapt to multiple applications. Generalization challenges coupled with the scarcity of large corpora of high-quality noise-free labelled data, have together fueled an interest for leveraging background information. Knowledge graphs serve as excellent choice to represent domain-specific information in a structured, standardized and extensible manner. Integrating symbolic knowledge representations in the form of Knowledge Graph Embedding (KGE) to perform neuro-symbolic reasoning is an emerging research direction promising significant impacts. This vision paper seeks to position ideas and provoke early thoughts toward advancing neuro-symbolic artificial intelligence in the context of geospatial challenges. Specifically, it conceptualizes and elaborates on an architecture for infusing geospatial knowledge from knowledge graph in a deep neural network pipeline. As guiding case studies - land-use land-cover classification, object detection and instance segmentation can benefit from infusing spatio-contextual information with remote sensing imagery. The discussion further reflects on and articulates the challenges and explainable AI opportunities anticipated when scaling and maintaining large-scale geospatial knowledge graphs.
Potnis, Abhishek↗
Regularization via f -Divergence: An Application to Multi-Oxide Spectroscopic Analysis
In this paper, we explore the application of convolutional neural networks (CNNs) for predicting the chemical composition of complex geologic samples in a simulated Martian atmospheric environment. Specifically, we aim to characterize oxide weight percentages (wt.%) of rock samples analyzed by remote Laser-Induced Breakdown Spectroscopy (LIBS), framing the problem as a multi-target regression task . Neural networks trained on LIBS spectra are prone to overfitting due to high spectral complexity, limited labeled data, and measurement noise. While regularization is critical for improving generalization, common methods (e.g., ℓ 2 regularization) impose constraints not directly tied to data distribution properties. We propose a novel regularization method based on a specific ƒ-divergence induced by a graph-based estimator, designed to constrain the distributional discrepancy between predictions and targets. This regularizer serves a dual purpose: (a) mitigating overfitting by enforcing a constraint on the distributional difference between predictions and noisy targets, and (b) acting as an auxiliary loss that penalizes large divergences. To enable backpropagation, we develop a differentiable approximation of this particular ƒ-divergence, making the method feasible for neural networks. Experiments on ChemCam and SuperCam LIBS calibration spectra show that mathematical equation-divergence regularization outperforms or matches standard regularization methods (ℓ 1 , ℓ 2 , dropout) and the classical baseline, partial least squares (PLS). Combining ƒ-divergence regularization with standard regularization yields further performance gains, indicating that distributional regularization is useful in this context giving a promising direction for robust model training in planetary science applications. Source code is publicly available at Klein and Li (2025), https://doi.org/10.11578/dc.20250530.7.
58 GEOSCIENCES↗
Automatic Waveform Quality Control for Surface Waves Using Machine Learning
Surface-wave seismograms are widely used by researchers to study Earth’s interior and earthquakes. To extract information reliably and robustly from a suite of surface waveforms, the signals require quality control screening to reduce artifacts from signal complexity and noise. This process has usually been completed by human experts labeling each waveform visually, which is time consuming and tedious for large data sets. We explore automated approaches to improve the efficiency of waveform quality control processing by investigating logistic regression, support vector machines, K-nearest neighbors, random forests (RF), and artificial neural networks (ANN) algorithms. To speed up signal quality assessment, we trained these five machine learning (ML) methods using nearly 400,000 human-labeled waveforms. The ANN and RF models outperformed other algorithms and achieved a test accuracy of 92%. We evaluated these two best-performing models using seismic events from geographic regions not used for training. The results show that the two trained models agree with labels from human analysts but required only 0.4% of the time. Although the original (human) quality assignments assessed general waveform signal-to-noise, the ANN or RF labels can help facilitate detailed waveform analysis. Our investigations demonstrate the capability of the automated processing using these two ML models to reduce outliers in surface-wave-related measurements without human quality control screening.
58 GEOSCIENCES↗
Improving Signal to Noise Ratios in Ion Mobility Spectrometry and Structures for Lossless Ion Manipulations (SLIM) using a High Dynamic Range Analog-to-Digital Converter
Signal digitization is a commonly overlooked part of ion mobility-mass spectrometry (IMS-MS) workflows, yet it is a significant contributor for determining signal-to-noise ratios and MS resolution. Here we report on the integration of a 2 GS/s, 14-bit ADC with a structures for lossless ion manipulations (SLIM)-IMS-MS and compare the performance to a commonly used 8-bit ADC. The 14-bit ADC provided an effective reduction in digitized noise by factor of ~6, owing largely to the use of smaller bit sizes. The low baseline allowed the threshold voltage levels to be set very close to the MCP baseline voltage, allowing for as much signal to be acquired as possible without causing overloading or excessive digitization of MCP baseline noise. Analyses of Agilent tuning mixture ions and a complex mixture of heavy labeled phosphopeptides showed that the 14-bit ADC (compared to the 8-bit ADC) provided a modest signal-to-noise increase (~1.5 to 2-fold) for high intensity ions, such as the Agilent tuning mixture ions and the 2+ and 3+ charge states of many phosphopeptide constituents. However, signal enhancements were as much as 10-fold for low intensity ions, and the 14-bit ADC enabled discernable signal intensities otherwise lost using an 8-bit digitizer. Additionally, the 14-bit ADC required ~14-fold fewer mass spectra to be averaged to produce a mass spectrum with similar S/N as the 8-bit ADC under identical conditions, potentially providing an order of magnitude higher measurement throughput. The high resolution, low baseline, and fast speed of the new 14-bit ADC enables high performance digitization of MS, IMS-MS, and SLIM-IMS-MS spectra, and allows a much fuller picture of analyte profiles in complex mixtures to be acquired.
data acquisition, digitization, ion mobility spect↗
Evidence of hyperbolic cosmic dust particles.
Cosmic dust data from the helicentric Pioneers 8 and 9 have been gathered for more than 7 years. A review and detailed study of these data are given and show that events which were previously labeled solar disturbance events and assumed to be noise generated by solar effects are, logically, true cosmic dust impact events. They are shown as an extension of the range of particle parameters exhibited by the time-of-flight measurements. The effects of accepting the sun-oriented events as authentic impact events are discussed.
Berg, O. E.↗
The stellar parameters and elemental abundances from low-resolution spectra – I. 1.2 million giants from LAMOST DR8
As a typical data-driven method, deep learning becomes a natural choice for analysing astronomical data. In this study, we built a deep convolutional neural network (NN) to estimate basic stellar parameters $T\rm {_{eff}}$, log g , metallicity ([M/H] and [Fe/H]) and [α/M] along with nine individual elemental abundances ([C/Fe], [N/Fe], [O/Fe], [Mg/Fe], [Al/Fe], [Si/Fe], [Ca/Fe], [Mn/Fe], and [Ni/Fe]). The NN is trained using common stars between the APOGEE survey and the LAMOST survey. We used low-resolution spectra from LAMOST survey as input, and measurements from APOGEE as labels. For stellar spectra with the signal-to-noise ratio in g band larger than 10 in the test set, the mean absolute error (MAE) is 29 K for $T\rm {_{eff}}$, 0.07 dex for log g , 0.03 dex for both [Fe/H] and [M/H], and 0.02 dex for [α/M]. The MAE of most elements is between 0.02 and 0.04 dex. The trained NN was applied to 1210 145 giants, including sub-giants, from LAMOST DR8 within the range of stellar parameters 3500 K < $T\rm {_{eff}}$ < 5500 K, 0.0 dex < log g < 4.0 dex, −2.5 dex < [Fe/H] < 0.5 dex. The distribution of our results in the chemical spaces is highly consistent with APOGEE labels and stellar parameters show consistency with external high-resolution measurements from GALAH. The results in this study allow us to further studies based on LAMOST data and deepen our understanding of the accretion and evolution history of the Milky Way. The electronic version of the value added catalog is available at http://www.lamost.org/dr8/v1.1/doc/vac.
79 ASTRONOMY AND ASTROPHYSICS↗
Determining Stellar Elemental Abundances from DESI Spectra with the Data-driven Payne
Abstract Stellar abundances for a large number of stars provide key information for the study of Galactic formation history. Large spectroscopic surveys such as the Dark Energy Spectroscopic Instrument (DESI) and LAMOST take median-to-low-resolution (R≲ 5000) spectra in the full optical wavelength range for millions of stars. However, the line-blending effect in these spectra causes great challenges for elemental abundance determination. Here we employDD-Payne, a data-driven method regularized by differential spectra from stellar physical models, to the DESI early data release spectra for stellar abundance determination. Our implementation delivers 15 labels, including effective temperatureT eff , surface gravity log g , microturbulence velocityv mic , and the abundances for 12 individual elements, namely C, N, O, Mg, Al, Si, Ca, Ti, Cr, Mn, Fe, and Ni. Given a spectral signal-to-noise ratio of 100 per pixel, the internal precisions of the label estimates are about 20 K forT eff , 0.05 dex for log g , and 0.05 dex for most elemental abundances. These results agree with the theoretical limits from the Crámer–Rao bound calculation within a factor of 2. The majority of the accreted halo stars contributed by the Gaia–Enceladus–Sausage are discernible from the disk and in situ halo populations in the resultant [Mg/Fe]–[Fe/H] and [Al/Fe]–[Fe/H] abundance spaces. We also provide distance and orbital parameters for the sample stars, which spread over a distance out to ∼100 kpc. The DESI sample has a significantly higher fraction of distant (or metal-poor) stars than the other existing spectroscopic surveys, making it a powerful data set for studying the Galactic outskirts. The catalog is publicly available.
Astronomy & Astrophysics↗
Synthetic data-driven deep learning for label-free autonomous atomic force microscopy
Atomic force microscopy (AFM) is a widely used tool for nanoscale characterization across materials science, energy research, and biology. However, its adoption in high-throughput materials discovery and statistically driven studies remains limited by a strong dependence on expert operator input and by the scarcity of annotated experimental AFM datasets needed to enable data-driven automation. Here, we introduce SimuScan, a synthetic-data–driven framework that enables reliable AFM feature identification, segmentation, and targeted imaging without requiring large manually labeled experimental datasets. SimuScan generates tunable, high-fidelity synthetic AFM images of defined morphologies while incorporating realistic experimental artifacts, including tip–sample convolution, noise, flattening distortions, and surface debris. These datasets are shown to support scalable, label-free training of modern deep learning models for AFM analysis. When integrated into data-driven AFM workflows, SimuScan-trained models can locate and analyze nanoscale structures across large datasets and guide targeted follow-up imaging. We validate this approach on nanostructured surfaces, DNA assemblies, and bacterial cells, demonstrating robust generalization across diverse sample types with minimal operator intervention. More broadly, this work establishes a general strategy for generating explicitly conditioned, task-relevant synthetic data to improve the reliability of downstream models in autonomous microscopy.
Millan-Solsona, Ruben [Oak Ridge National Laborato↗
Automated detection of photovoltaic cleaning events: A performance comparison of techniques as applied to a broad set of labeled photovoltaic data sets
Extracting accurate soiling loss information from photovoltaic (PV) production data first requires segmenting the time series data per natural or manually occurring cleaning events. Maintenance logs are often incomplete, rain data are often unavailable, and the debate on rain thresholds for cleaning and dew or wind cleanings is still ongoing. The present work aims to overtake these issues by improving automated methods to detect these cleaning events and therefore improve extraction of soiling loss information. Time series power production data from 22 PV inverters were labeled for natural or manually occurring cleaning events. The data sets were carefully selected to include varying degrees of soiling, cleaning events, and noise. Several algorithms, including filtering logic and change point detection, were examined for efficacy at detecting the labeled cleanings. All the methods introduced except for changepoint detection showed significant improvement at detecting the labeled cleaning events per the mean F 1 score. Furthermore, the highest performing cleaning detection algorithm achieved an absolute increase in the mean F 1 score of 43% over the default version of the RdTools stochastic rate and recovery (SRR) algorithm. The highest performing algorithm included irradiance filtering and a cleaning detection threshold, adjusted based on the 40-day centered rolling median of the absolute day-to-day deviations in the daily performance index (PI). Furthermore, these improvements are promising as cleaning detection is an essential step in the automated analysis of PV soiling.
14 SOLAR ENERGY↗