Detecting Label Noise in Kepler Confirmed Planet Catalog using Machine Learning
Explore the source record for details and available documents.
Exoplanet↗
SEARCH · Engineering Papers
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↗
SeismoGen: Seismic Waveform Synthesis Using GAN With Application to Seismic Data Augmentation
Abstract Detecting earthquake arrivals within seismic time series can be a challenging task. Visual, human detection has long been considered the gold standard but requires intensive manual labor that scales poorly to large data sets. In recent years, automatic detection methods based on machine learning have been developed to improve the accuracy and efficiency. However, the accuracy of those methods relies on access to a sufficient amount of high‐quality labeled training data, often tens of thousands of records or more. We aim to resolve this dilemma by answering two questions: (1) provided with a limited amount of reliable labeled data, can we use them to generate additional, realistic synthetic waveform data? and (2) can we use those synthetic data to further enrich the training set through data augmentation, thereby enhancing detection algorithms? To address these questions, we use a generative adversarial network (GAN), a type of machine learning model which has shown supreme capability in generating high‐quality synthetic samples in multiple domains. Once trained, our GAN model is capable of producing realistic seismic waveforms of multiple labels (noise and event classes). Applied to real Earth seismic data sets in Oklahoma, we show that data augmentation from our GAN‐generated synthetic waveforms can be used to improve earthquake detection algorithms in instances when only small amounts of labeled training data are available.
Wang, Tiantong↗
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↗
Improve Learning from Crowds via Generative Augmentation
Crowdsourcing provides an efficient label collection schema for supervised machine learning. However, to control annotation cost, each instance in the crowdsourced data is typically annotated by a small number of annotators. This creates a sparsity issue and limits the quality of machine learning models trained on such data. In this paper, we study how to handle sparsity in crowdsourced data using data augmentation. Specifically, we propose to directly learn a classifier by augmenting the raw sparse annotations. We implement two principles of high-quality augmentation using Generative Adversarial Networks: 1) the generated annotations should follow the distribution of authentic ones, which is measured by a discriminator; 2) the generated annotations should have high mutual information with the ground-truth labels, which is measured by an auxiliary network. Extensive experiments and comparisons against an array of state-of-the-art learning from crowds methods on three real-world datasets proved the effectiveness of our data augmentation framework. It shows the potential of our algorithm for low-budget crowdsourcing in general.
96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
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↗
Identifying Different Classes of Seismic Noise Signals Using Unsupervised Learning
Abstract Proper classification of nontectonic seismic signals is critical for detecting microearthquakes and developing an improved understanding of ongoing weak ground motions. We use unsupervised machine learning to label five classes of nonstationary seismic noise common in continuous waveforms. Temporal and spectral features describing the data are clustered to identify separable types of emergent and impulsive waveforms. The trained clustering model is used to classify every 1 s of continuous seismic records from a dense seismic array with 10–30 m station spacing. We show that dominate noise signals can be highly localized and vary on length scales of hundreds of meters. The methodology demonstrates the complexity of weak ground motions and improves the standard of analyzing seismic waveforms with a low signal‐to‐noise ratio. Application of this technique will improve the ability to detect genuine microseismic events in noisy environments where seismic sensors record earthquake‐like signals originating from nontectonic sources.
Johnson, Christopher W.↗
Machine Learning for Improved Availability of the SNS Klystron High Voltage Converter Modulators
Beam availability has increased at the SNS, however, the targeted availability is greater than 95 %, while the SNS has failed to meet lower targets in the past. The HVCM used to power the linac klystrons have been one source of lost beam time and was chosen to explore using AI/ML techniques to improve reliability. Among the possibilities being explored are automating the tuning of HVCMs and predicting component failures such as capacitor aging, rectifier assemblies containing hundreds of diodes, and insulating oil degradation. The methodology pursued includes data cleaning, de-noising, post-analysis data labeling, and machine learning model development. We explore using Long Short-Term Memory and autoencoders for anomaly detection and prognostication used to schedule maintenance. We evaluate the use of model regularizers and constraints to improve the performance of the model and investigate methods to estimate the uncertainty of the models to provide a robust prediction with statistical interoperability. This paper describes the operational experience and known failures of the HVCMs and the proposed ML methodology and the preliminary results of training the AI/ML algorithms.
Pappas, G. C.↗
Machine Learning for Improved Availability of the SNS Klystron High Voltage Converter Modulators
Beam availability has increased at the SNS, however, the targeted availability is greater than 95 %, while the SNS has failed to meet lower targets in the past. The HVCM used to power the linac klystrons have been one source of lost beam time and was chosen to explore using AI/ML techniques to improve reliability. Among the possibilities being explored are automating the tuning of HVCMs and predicting component failures such as capacitor aging, rectifier assemblies containing hundreds of diodes, and insulating oil degradation. The methodology pursued includes data cleaning, de-noising, post-analysis data labeling, and machine learning model development. We explore using Long Short-Term Memory and autoencoders for anomaly detection and prognostication used to schedule maintenance. We evaluate the use of model regularizers and constraints to improve the performance of the model and investigate methods to estimate the uncertainty of the models to provide a robust prediction with statistical interoperability. This paper describes the operational experience and known failures of the HVCMs and the proposed ML methodology and the preliminary results of training the AI/ML algorithms.
Pappas, Chris↗
Machine Learning for Improved Availability of the SNS Klystron High Voltage Converter Modulators
Beam availability has increased at the SNS, however, the targeted availability is greater than 95 %, while the SNS has failed to meet lower targets in the past. The HVCM used to power the linac klystrons have been one source of lost beam time and was chosen to explore using AI/ML techniques to improve reliability. Among the possibilities being explored are automating the tuning of HVCMs and predicting component failures such as capacitor aging, rectifier assemblies containing hundreds of diodes, and insulating oil degradation. The methodology pursued includes data cleaning, de-noising, post-analysis data labeling, and machine learning model development. We explore using Long Short-Term Memory and autoencoders for anomaly detection and prognostication used to schedule maintenance. We evaluate the use of model regularizers and constraints to improve the performance of the model and investigate methods to estimate the uncertainty of the models to provide a robust prediction with statistical interoperability. This paper describes the operational experience and known failures of the HVCMs and the proposed ML methodology and the preliminary results of training the AI/ML algorithms.
Pappas, Chris↗
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↗