RNN-Based online anomaly detection in nuclear reactors for highly imbalanced datasets with uncertainty
Not provided.
Nuclear Science & Technology↗
SEARCH · Search NASA
Results for “imbalanced datasets”
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.
Avian Activity Classification Using Recurrent Networks to Fuse Videos with Metadata on Imbalanced Datasets
Activity classification plays a crucial role in various real-life scenarios involving both humans and animals. There is an increasing need for precise activity classification focused on avian-solar interactions, as the usage of solar energy facilities, such as photovoltaic array power stations, has been observed to impact bird species richness, behavior, and activity. However, there has been no work to develop an automated system to monitor and classify these avian-solar interactions. All current methods rely on human observers, which is time and human resources costly and subject to errors related to searcher efficiency. With the recent success of Deep Learning models in activity classification problems, this paper develops a recurrent neural network-based model to automatically classify six avian activities around solar energy facilities. Our proposed model integrates critical feature engineering metadata with video frame data, enabling improved learning and more accurate activity classification. Furthermore, we address the challenge of data imbalance during training and demonstrate the efficacy of our model in detecting and classifying different activities within video tracks. Additionally, we analyze the saliency/backpropagation map of the trained proposed model and validate its decision-making rationale.
Avian activity classification; bidirectional LSTM;↗
Structure–activity relationship-based chemical classification of highly imbalanced Tox21 datasets
Abstract The specificity of toxicant-target biomolecule interactions lends to the very imbalanced nature of many toxicity datasets, causing poor performance in Structure–Activity Relationship (SAR)-based chemical classification. Undersampling and oversampling are representative techniques for handling such an imbalance challenge. However, removing inactive chemical compound instances from the majority class using an undersampling technique can result in information loss, whereas increasing active toxicant instances in the minority class by interpolation tends to introduce artificial minority instances that often cross into the majority class space, giving rise to class overlapping and a higher false prediction rate. In this study, in order to improve the prediction accuracy of imbalanced learning, we employed SMOTEENN, a combination of Synthetic Minority Over-sampling Technique (SMOTE) and Edited Nearest Neighbor (ENN) algorithms, to oversample the minority class by creating synthetic samples, followed by cleaning the mislabeled instances. We chose the highly imbalanced Tox21 dataset, which consisted of 12 in vitro bioassays for > 10,000 chemicals that were distributed unevenly between binary classes. With Random Forest (RF) as the base classifier and bagging as the ensemble strategy, we applied four hybrid learning methods, i.e., RF without imbalance handling (RF), RF with Random Undersampling (RUS), RF with SMOTE (SMO), and RF with SMOTEENN (SMN). The performance of the four learning methods was compared using nine evaluation metrics, among which F 1 score, Matthews correlation coefficient and Brier score provided a more consistent assessment of the overall performance across the 12 datasets. The Friedman’s aligned ranks test and the subsequent Bergmann-Hommel post hoc test showed that SMN significantly outperformed the other three methods. We also found that a strong negative correlation existed between the prediction accuracy and the imbalance ratio (IR), which is defined as the number of inactive compounds divided by the number of active compounds. SMN became less effective when IR exceeded a certain threshold (e.g., > 28). The ability to separate the few active compounds from the vast amounts of inactive ones is of great importance in computational toxicology. This work demonstrates that the performance of SAR-based, imbalanced chemical toxicity classification can be significantly improved through the use of data rebalancing.
Idakwo, Gabriel↗
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 ↗
Accelerating cavity fault prediction using deep learning at Jefferson Laboratory
Abstract Accelerating cavities are an integral part of the continuous electron beam accelerator facility (CEBAF) at Jefferson Laboratory. When any of the over 400 cavities in CEBAF experiences a fault, it disrupts beam delivery to experimental user halls. In this study, we propose the use of a deep learning model to predict slowly developing cavity faults. By utilizing pre-fault signals, we train a long short-term memory-convolutional neural network binary classifier to distinguish between radio-frequency (RF) signals during normal operation and RF signals indicative of impending faults. We optimize the model by adjusting the fault confidence threshold and implementing a multiple consecutive window criterion to identify fault events, ensuring a low false positive rate. Results obtained from analysis of a real dataset collected from the accelerating cavities simulating a deployed scenario demonstrate the model’s ability to identify normal signals with 99.99% accuracy and correctly predict 80% of slowly developing faults. Notably, these achievements were achieved in the context of a highly imbalanced dataset, and fault predictions were made several hundred milliseconds before the onset of the fault. Anticipating faults enables preemptive measures to improve operational efficiency by preventing or mitigating their occurrence.
43 PARTICLE ACCELERATORS↗
Resampling and data augmentation for short-term PV output prediction based on an imbalanced sky images dataset using convolutional neural networks
Integrating photovoltaics (PV) into electricity grids is challenged by potentially large fluctuations in power generation. In recent years, sky image-based PV output prediction using convolutional neural networks (CNNs) has emerged as a promising approach to forecasting fluctuations. A key challenge is imbalanced sky image datasets: because of the geography of solar PV system installations, sky image datasets are often rich in sunny condition data but deficient in cloudy condition data. This imbalance contrasts with the fact that model errors are dominated by cloudy condition performance. In this study, we attempt to remedy this by exploring the enrichment and augmentation of an imbalanced sky images dataset for two PV output prediction tasks: nowcasting (predicting concurrent PV output) and forecasting (predicting 15-minute-ahead future PV output). We empirically examine the efficacy of using different resampling and data augmentation approaches to create a rebalanced dataset for model development. A three-stage greedy search is used to determine the optimal resampling approach, data augmentation techniques and over-sampling rate. The results show that for the nowcast problem, resampling and data augmentation can effectively enhance the model performance, reducing overall root mean squared error (RMSE) by an average of 4%, or a 15 std. (standard deviation) of improvement compared to the variability of the baseline model. In contrast, the treatment RMSE for the forecast problem nearly always overlaps the baseline performance at the ± 2 std. level. The optimal resampling approach expands on the original dataset by over-sampling the minority cloudy data, with the best results from large over-sampling rate (e.g., 4 ~ 6 times over-sampling of cloudy images).
14 SOLAR ENERGY↗
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↗
Class imbalance in out-of-distribution datasets: Improving the robustness of the TextCNN for the classification of rare cancer types
In the last decade, the widespread adoption of electronic health record documentation has created huge opportunities for information mining. Natural language processing (NLP) techniques using machine and deep learning are becoming increasingly widespread for information extraction tasks from unstructured clinical notes. Disparities in performance when deploying machine learning models in the real world have recently received considerable attention. In the clinical NLP domain, the robustness of convolutional neural networks (CNNs) for classifying cancer pathology reports under natural distribution shifts remains understudied. In this research, we aim to quantify and improve the performance of the CNN for text classification on out-of-distribution (OOD) datasets resulting from the natural evolution of clinical text in pathology reports. We identified class imbalance due to different prevalence of cancer types as one of the sources of performance drop and analyzed the impact of previous methods for addressing class imbalance when deploying models in real-world domains. Our results show that our novel class-specialized ensemble technique outperforms other methods for the classification of rare cancer types in terms of macro F1 scores. We also found that traditional ensemble methods perform better in top classes, leading to higher micro F1 scores. Based on our findings, we formulate a series of recommendations for other ML practitioners on how to build robust models with extremely imbalanced datasets in biomedical NLP applications.
60 APPLIED LIFE SCIENCES↗
A comparison of machine learning methods to classify radioactive elements using prompt-gamma-ray neutron activation data
The detection of illicit radiological materials is critical to establishing a robust second line of defence in nuclear security. Neutron-capture prompt-gamma activation analysis (PGAA) can be used to detect multiple radioactive materials across the entire Periodic Table. However, long detection times and a high rate of false positives pose a significant hindrance in the deployment of PGAA-based systems to identify the presence of illicit substances in nuclear forensics. In the present work, six different machine-learning algorithms were developed to classify radioactive elements based on the PGAA energy spectra. The model performance was evaluated using standard classification metrics and trend curves with an emphasis on comparing the effectiveness of algorithms that are best suited for classifying imbalanced datasets. We analyse the classification performance based on Precision, Recall, F1-score, Specificity, Confusion matrix, ROC-AUC curves, and Geometric Mean Score (GMS) measures. The tree-based algorithms (Decision Trees, Random Forest and AdaBoost) have consistently outperformed Support Vector Machine and K-Nearest Neighbours. Based on the results presented, AdaBoost is the preferred classifier to analyse data containing PGAA spectral information due to the high recall and minimal false negatives reported in the minority class.
97 MATHEMATICS AND COMPUTING↗
Using convolutional neural networks to detect edge localized modes in DIII-D from Doppler backscattering measurements
In H-mode tokamak plasmas, the plasma is sometimes ejected beyond the edge transport barrier. These events are known as edge localized modes (ELMs). ELMs cause a loss of energy and damage the vessel walls. Understanding the physics of ELMs, and by extension, how to detect and mitigate them, is an important challenge. In this paper, we focus on two diagnostic methods—deuterium-alpha (D α ) spectroscopy and Doppler backscattering (DBS). The former detects ELMs by measuring Balmer alpha emission, while the latter uses microwave radiation to probe the plasma. DBS has the advantages of having a higher temporal resolution and robustness to damage. These advantages of DBS diagnostic may be beneficial for future operational tokamaks, and thus, data processing techniques for DBS should be developed in preparation. In sight of this, we explore the training of neural networks to detect ELMs from DBS data, using D α data as the ground truth. With shots found in the DIII-D database, the model is trained to classify each time step based on the occurrence of an ELM event. The results are promising. When tested on shots similar to those used for training, the model is capable of consistently achieving a high f1-score of 0.93. Furthermore, this score is a performance metric for imbalanced datasets that ranges between 0 and 1. We evaluate the performance of our neural network on a variety of ELMs in different high confinement regimes (grassy ELM, RMP mitigated, and wide-pedestal), finding broad applicability. Beyond ELMs, our work demonstrates the wider feasibility of applying neural networks to data from DBS diagnostic.
70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
The Impact of Time-Aware Design Choices in ICS Anomaly Detection
Industrial control systems (ICS) remain vulnerable to increasingly sophisticated cyberattacks, yet evaluating anomaly detection models in these environments is challenging due to temporal dependencies, missing-not-at-random patterns, and extremely imbalanced datasets. These factors make common practices—especially random data splits and na¨ıve imputation— prone to severe temporal leakage, which can inflate reported performance and obscure real-world limitations. In this work, we systematically examine classical machine learning models, temporal deep learning architecture, and tensordecomposition– based methods on a gas-pipeline dataset using a fully temporally separated evaluation pipeline designed to mimic realistic deployment conditions. Our findings show that proper temporal handling and MNAR-aware preprocessing significantly alter the relative performance of popular anomaly-detection methods, providing practical guidance for designing reliable, leakage-resistant ICS intrusion-detection systems.
97 MATHEMATICS AND COMPUTING↗
Deep Point Cloud Building Envelope Segmentation (DeeP-CuBES) using Deep Learning
Building Information Modeling (BIM) plays an important role in building design and construction, particularly for achieving energy-efficient retrofits. Building envelope retrofits using panelized prefabricated system, such as those popularized by the Energiesprong program, need accurate as-built dimensions of facade features (windows, doors, etc.) to achieve the desired thermal and air tightness. Traditionally, building surveying is done manually, resulting in a time-consuming and labor-intensive process. Recently, 3D point clouds from terrestrial LiDAR have been used to automate the generation of as-built dimensions of existing buildings. However, automated BIM using LiDAR relies on solving the point cloud semantic segmentation (PCSS) problem. In this work, we propose a robust pipeline for solving the PCSS problem using deep neural networks, focusing on overcoming challenges posed by imbalanced datasets and complex architectural features. We introduce the first high-density, labeled, and validated building envelope point cloud dataset derived from multiple building scans, specifically curated to tackle challenges in facade-level segmentation. Results from the trained neural networks show that advanced attention-based architectures and incorporating radiometry (light intensity and RGB) features significantly boost segmentation accuracy for windows and doors.
Selvakumar, Balaji [ORNL]↗
Design Choices in Anomaly Detection for Industrial Control Systems: Insights from Gas Pipeline Data
Industrial control systems (ICS) remain vulnerable to increasingly sophisticated cyberattacks, yet evaluating anomaly detection models in these environments is challenging due to temporal dependencies, missing-not-at-random patterns, and extremely imbalanced datasets. These factors make common practices—especially random data splits and naïve imputation—prone to severe temporal leakage, which can inflate reported performance and obscure real-world limitations. In this work, we systematically examine classical machine learning models, temporal deep learning architecture, and tensor-decomposition–based methods on a gas-pipeline dataset using a fully temporally separated evaluation pipeline designed to mimic realistic deployment conditions. Our findings show that proper temporal handling and MNAR-aware preprocessing significantly alter the relative performance of popular anomaly-detection methods, providing practical guidance for designing reliable, leakage-resistant ICS intrusion-detection systems.
97 MATHEMATICS AND COMPUTING↗
Training a Quantum Annealing Based Restricted Boltzmann Machine on Cybersecurity Data
A restricted Boltzmann machine (RBM) is a generative model that could be used in effectively balancing a cybersecurity dataset because the synthetic data a RBM generates follows the probability distribution of the training data. RBM training can be performed using contrastive divergence (CD) and quantum annealing (QA). QA-based RBM training is fundamentally different from CD and requires samples from a quantum computer. We present a real-world application that uses a quantum computer. Specifically, we train a RBM using QA for cybersecurity applications. The D-Wave 2000Q has been used to implement QA. RBMs are trained on the ISCX data, which is a benchmark dataset for cybersecurity. For comparison, RBMs are also trained using CD. CD is a commonly used method for RBM training. Our analysis of the ISCX data shows that the dataset is imbalanced. We present two different schemes to balance the training dataset before feeding it to a classifier. The first scheme is based on the undersampling of benign instances. The imbalanced training dataset is divided into five sub-datasets that are trained separately. A majority voting is then performed to get the result. Our results show the majority vote increases the classification accuracy up from 90.24% to 95.68%, in the case of CD. For the case of QA, the classification accuracy increases from 74.14% to 80.04%. In the second scheme, a RBM is used to generate synthetic data to balance the training dataset. We show that both QA and CD-trained RBM can be used to generate useful synthetic data. Balanced training data is used to evaluate several classifiers. Among the classifiers investigated, K-Nearest Neighbor (KNN) and Neural Network (NN) perform better than other classifiers. They both show an accuracy of 93%. Our results show a proof-of-concept that a QA-based RBM can be trained on a 64-bit binary dataset. The illustrative example suggests the possibility to migrate many practical classification problems to QA-based techniques. Further, we show that synthetic data generated from a RBM can be used to balance the original dataset.
97 MATHEMATICS AND COMPUTING↗
Resilience Assessment for Distribution Systems during Hurricanes: A Learning-Based Framework
This paper presents a proactive strategy for hurricane-resilient distribution systems. It proposes a Bayesian Neural Network-based outage prediction model considering various parameters, including electrical components, and weather and environmental factors. Addressing challenges in imbalanced outage datasets, a Bias-Variance Tradeoff method is proposed. A resilience assessment model quantifies resilience indices, providing insights into system weaknesses. The approach identifies weak points and serves as a planning benchmark. Numerical results on the modified IEEE 123-node test system demonstrate effectiveness in realistic hurricane scenarios.
Vahedi, Soroush↗
Conditional Experts for Improved Building Damage Assessment Across Satellite Imagery View Angles
Rapid building damage assessment (BDA) is vital in guiding disaster response missions and estimating population distribution across impacted areas. While commercial satellite imagery providers have enabled near-daily monitoring of the Earth, near-realtime assessment of disaster scenarios frequently requires analysis of off-nadir imagery, as satellites are often far from impacted areas for at-nadir post-event imaging to occur Such scenarios are, however, underrepresented in existing BDA datasets and methodologies. With this motivation, we investigate generalization capabilities of current BDA practices across overhead view-angles and strategies for their improvement. Using a labeled dataset of images capturing conflict-related damages, we first train a baseline BDA architecture using imbalanced and balanced datasets with respect to view-angle. Then, we explore conditional convolutions parameterized on image features, image nadir, and their combination as a mechanism for conditioning on view-angles. Experiments demonstrate the limitations of current practice and the potential of conditional mechanisms to increase model robustness to view-angle variations.
Ambrozio Dias, Philipe↗
Deep reinforcement learning for class imbalance fault diagnosis of equipment in nuclear power plants
In equipment fault diagnosis in nuclear power plants, there may be far more samples in one class (e.g., a health state) than in another class (e.g., a fault state). The distribution of data in each class is highly skewed. Most machine learning algorithms are suitable for balanced training datasets. When faced with imbalanced samples, these algorithms tend to provide good identification for the majority classes and bias for the minority classes. However, the misclassification of minority classes can lead to high costs. To address the above problem, this paper develops a deep reinforcement learning-based diagnosis method that models fault diagnosis as a sequential decision-making process. At each time step, the agent receives the state of the environment represented by the training samples and then takes a diagnosis action guided by a policy. If the action is correct/incorrect, the agent receives a positive/negative reward. The reward for minority classes is higher than that for majority classes. The agent’s goal is to obtain as many cumulative rewards as possible in the process, i.e., to identify the sample as correctly as possible. Six demonstration scenarios are constructed, depending on the selected fault datasets and the designed model structures. Experiments show that the proposed method achieves a higher weighted-averaged F1 score than the classical supervised learning method in most cases of class imbalance. Finally, the proposed method has potential applications in the field of class imbalance fault diagnosis of equipment in nuclear power plants.
21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗