SEARCH · Engineering Papers

Results for “classification models”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

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

At least 865 records · Page 48

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Expression of a mammalian RNA demethylase increases flower number and floral stem branching in Arabidopsis thaliana

Abstract RNA methylation plays a central regulatory role in plant biology and is a relatively new target for plant improvement efforts. In nearly all cases, perturbation of the RNA methylation machinery results in deleterious phenotypes. However, a recent landmark paper reported that transcriptome‐wide use of the human RNA demethylase FTO substantially increased the yield of rice and potatoes. Here, we have performed the first independent replication of those results and demonstrated broader transferability of the trait, finding increased flower and fruit count in the model species Arabidopsis thaliana . We also performed RNA‐seq of our FTO‐transgenic plants, which we analyzed in conjunction with previously published datasets to detect several previously unrecognized patterns in the functional and structural classification of the upregulated and downregulated genes. From these, we present mechanistic hypotheses to explain these surprising results with the goal of spurring more widespread interest in this promising new approach to plant engineering.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2020

Deep learning model to detect various synchrophasor data anomalies

High-density synchrophasors provide valuable information for power grid situational awareness, operation and control. Unfortunately, due to factors including communication instability and hardware failure, their data quality can be greatly deteriorated by anomalies. Since the anomalies can impact the performance of the synchrophasor applications, it is of paramount significance to propose a model to detect anomalies in synchrophasor. In this study, a convolutional neural network model is established to detect and classify the anomalies in the synchrophasor measurements. Additionally, four types of anomalies observed in actual synchrophasors including erroneous patterns, random spikes, missing points and high-frequency interferences are considered in this study. The proposed model is extensively evaluated via field-collected measurements from the synchrophasor network in Jiangsu grid, China. The superior performance of the proposed model indicates the great potential of using deep learning for the detection of abnormal synchrophasor measurements.

42 ENGINEERING↗

DOE OSTI2026

Sensor Reduction for Diversion Detection in a Realistic Heat Pipe Microreactor Using Supervised Machine Learning

Microreactors are designed as a smaller, cheaper, and safer alternative to traditional nuclear power plants. Their non-traditional characteristics and prospect of mass production and deployment will likely require new approaches to nuclear safeguards. The primary proliferation concern with microreactors is the diversion of fuel material. Such diversion may produce measurable defects in key physical attributes like neutron flux, which may in turn be detectable using machine learning models. Preliminary work has demonstrated this ability for modeled nominal and diversion scenarios using large quantities of energy integrated neutron flux data. In practice, the number of available sensors for such measurements will be limited and energy integrated flux information will not be available. This work explores the ability of tree-based gradient boosted ensemble models to classify a given microreactor core is nominal or diversion, and determine the number of fuel pins diverted in the case of diversion with reduced numbers of sensors and more realistic detector responses. Classification accuracy of greater than 98% and regression errors as low as 5% of the total number of fuel pins were achieved with as few as 15 sensors, compared to 99% and 4.1% with a maximum of 240 sensors.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2020

Compressing deep neural networks on FPGAs to binary and ternary precision with hls4ml

We present the implementation of binary and ternary neural networks in the hls4ml library, designed to automatically convert deep neural network models to digital circuits with FPGA firmware. Starting from benchmark models trained with floating point precision, we investigate different strategies to reduce the network's resource consumption by reducing the numerical precision of the network parameters to binary or ternary. We discuss the trade-off between model accuracy and resource consumption. In addition, we show how to balance between latency and accuracy by retaining full precision on a selected subset of network components. As an example, we consider two multiclass classification tasks: handwritten digit recognition with the MNIST data set and jet identification with simulated proton-proton collisions at the CERN Large Hadron Collider. The binary and ternary implementation has similar performance to the higher precision implementation while using drastically fewer FPGA resources.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2023

Optimized Carbon Fiber Composites in Wind Turbine Blade Design: Follow-On Studies

This project has identified opportunities to bring further reductions in the mass and cost of modern wind turbine blades through the use of alternative material systems and manufacturing processes. The fiber reinforced polymer material systems currently used by the wind industry have stagnated as the technology continues to mature and as a means to reduce risk while introducing new products with continually increasing blade lengths. However, as blade lengths continue to increase, the challenge of controlling blade mass becomes even more critical to enabling the associated levelized cost of energy reductions. Stiffer and stronger reinforcement fibers can help to resolve the challenges of meeting the loading demands while limiting the increase in weight, but these materials are substantially more expensive than the traditional E-glass fiber systems. One goal of this project and associated work is to identify pathways that improve the cost-effectiveness of carbon fiber such that it is the reinforcement of choice in the primary structural elements of wind blades. The use of heavy-tow textile carbon fiber material systems has been shown to reduce the blade mass by 30-31% when used in the spar cap and by up to 7% when used in edgewise reinforcement. A pultrusion cost model was developed to enable a material cost comparison that includes an accurate estimate of the intermediate manufacturing step of pultrusion for the carbon fiber composite. Material cost reductions were revealed in most cases for the heavy-tow textile carbon fiber compared to infused fiberglass. The use of carbon fiber in the edgewise reinforcement produced the most notable material cost reduction of 33% for the heavy-tow textile carbon fiber. The mass and cost savings observed when using carbon fiber in edgewise reinforcement demonstrate a clear opportunity of this design approach. A carbon fiber conversion cost model was expanded to include a characterization of manufacturing costs when using advanced conversion processes with atmospheric plasma oxidation. This manufacturing approach was estimated to reduce the cost of carbon fiber material systems by greater than 10% and can be used with textile carbon systems or traditional carbon fiber precursors. The pultrusion cost model was also used to assess the opportunity for using pultruded fiberglass in wind blades, studying conventional E-glass fiber reinforcement. When using pultruded fiberglass as the spar cap material for two design classifications, the blade weight was reduced by 6% and 9% compared to infused fiberglass. However, due to the relatively large share of the pultrusion manufacturing cost compared to fiber cost, the spar cap material cost increased by 12% and 7%. When considering the system benefits of reduced blade mass and potentially lower blade manufacturing costs for pultruded composites, there may be opportunity for pultruded E-glass in wind blade spar caps, but further studies are needed. There is a clearer outcome for using pultruded fiberglass in the edgewise reinforcement where it resulted in a blade mass reduction of 2% and associated reinforcement material cost reduction of 1% compared to infused E-glass. The use of higher performing glass fibers, such as S-glass and H-glass systems, will produce greater mass savings but a study is needed to assess the cost implications for these more expensive systems. The most likely opportunity for these high-performance glass fibers is in the edgewise reinforcement, where the increased strength will reduce the damage accumulation of this fatigue-driven component. The blade design assessments in this project characterize the controlling material properties for the primary structural components in the flapwise and edgewise directions for modern wind blades. The observed trends with low and high wind speed turbine classifications for carbon and glass fiber reinforced polymer systems help to identify where cost reductions are needed, and where improvements in mechanical properties would help to reduce the material demands.

17 WIND ENERGY↗

DOE OSTI2021

Training Restricted Boltzmann Machines With a D-Wave Quantum Annealer

Restricted Boltzmann Machine (RBM) is an energy-based, undirected graphical model. It is commonly used for unsupervised and supervised machine learning. Typically, RBM is trained using contrastive divergence (CD). However, training with CD is slow and does not estimate the exact gradient of the log-likelihood cost function. In this work, the model expectation of gradient learning for RBM has been calculated using a quantum annealer (D-Wave 2000Q), where obtaining samples is faster than Markov chain Monte Carlo (MCMC) used in CD. Training and classification results of RBM trained using quantum annealing are compared with the CD-based method. The performance of the two approaches is compared with respect to the classification accuracies, image reconstruction, and log-likelihood results. The classification accuracy results indicate comparable performances of the two methods. Image reconstruction and log-likelihood results show improved performance of the CD-based method. It is shown that the samples obtained from quantum annealer can be used to train an RBM on a 64-bit “bars and stripes” dataset with classification performance similar to an RBM trained with CD. Though training based on CD showed improved learning performance, training using a quantum annealer could be useful as it eliminates computationally expensive MCMC steps of CD.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2022

Classification of animal sounds in a hyperdiverse rainforest using convolutional neural networks with data augmentation

To protect tropical forest biodiversity, we need to be able to detect it reliably, cheaply, and at scale. Automated detection of sound producing animals from passively recorded soundscapes via machine-learning approaches is a promising technique towards this goal, but it is constrained by the necessity of large training data sets. Using soundscapes from a tropical forest in Borneo and a Convolutional Neural Network model (CNN), we investigate i) the minimum viable training data set size for accurate prediction of call types (‘sonotypes’), and ii) the extent to which data augmentation and transfer learning can overcome the issue of small and imbalanced training data sets. We found that even relatively high sample sizes (>80 per sonotype) lead to mediocre accuracy, which however improved significantly with data augmentation and transfer learning, including at extremely small sample sizes (3 per sonotype), regardless of taxonomic group or call characteristics. Neither transfer learning nor data augmentation alone achieved high accuracy. Our results suggest that transfer learning and data augmentation could make the use of CNNs to classify species’ vocalizations feasible even for small soundscape-based projects with many rare species. Retraining our open-source model requires only basic programming skills which makes it possible for individual conservation initiatives to match their local context, in order to enable more evidence-informed management of biodiversity.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

Unsupervised Power System Event Detection and Classification Using Unlabeled PMU Data

This paper proposes a novel data-driven power system event detection and classification method based on 5TB of actual PMU measurements collected from the US western interconnect. Firstly, a set of comprehensive power quality rules are proposed to pre-filter the raw data and extract the regions of interest (ROI). Six distinct event categories are defined and corresponding patterns are chosen as references. Meanwhile, detailed characteristics of patterns are summarized to enhance our understanding of the actual events. Then, the time-independent feature vectors are generated by extracting the statistical, temporal, and spectral features from the raw time-series data. Furthermore, an ensemble model is proposed to cluster the events by combining multiple K-means clustering models using a voting strategy. Besides, both system-level and PMU-level clustering models are developed. The accuracy and robustness of the event detection method are further improved through interactive evaluation of the two-level clustering results. This paper summarizes the actual characteristics of each event category and provides a reliable basis for accurate label generation. The experiments demonstrate the effectiveness of the proposed event detection and classification method.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2021

Unsupervised Power System Event Detection and Classification Using Unlabeled PMU Data

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2023

23, 381, 6242, 103268, 1743183, ...:Hilbert series for CP-violating operators in SMEFT

We introduce a systematic method to classify the Standard Model Effective Field Theory (SMEFT) operators based on their CP properties with the Hilbert series techniques. Our method makes it possible to enumerate operators violating CP symmetry in a few seconds. We present the complete classification of dimension eight operators under CP transformation, and the number of CP-odd or CP-violating operators are listed up to dimension 14. We also provide a companion code in Form that allows anybody to reproduce our results.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2025

Energy-enhanced expansion of the standard model effective field theory

We formalize energy-scaling arguments in the standard model effective field theory (SMEFT) to estimate the effects of operators up to dimension ten. Our approach relies on weakly coupled UV completions with no presumed large hierarchies between the Wilson coefficients. We introduce a classification based on the number of external legs and an energy-counting parameter. We establish a dual expansion in 𝑣/Λ and 𝐸/Λ. Extending to four-, five-, and six-particle vertices, our framework highlights energy-enhanced operators that dominate high-energy processes at the High Luminosity-Large Hadron Collider. This organization streamlines experimental analyses to only include operators with energetic impact in their analyses and enhances the discoverability of new physics within the SMEFT framework.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2026

Interpretable Models for Workflow Differentiation in High-Performance Scientific Networks

Scientific workflows in high-performance networks spawn hundreds of interdependent flows that must be managed collectively—yet existing network classifiers treat each flow in isolation, leading to fragmented QoS decisions and missed interflow patterns. We present a novel traffic classification solution that operates at the workflow level, distinguishing entire filetransfer operations from streaming analytics by capturing how concurrent flows interact and burst together. We introduce a workflow identification window (WIW) that ingests raw packet headers from parallel flows into unified tensors, preserving the spatial-temporal patterns that differentiate scientific workflows. This approach achieves 98.7% accuracy using CNN, LSTM, and hybrid architectures, while maintaining 84% accuracy on production traffic collected a week later—demonstrating robustness to temporal drift. By integrating SHAP and GradCAM explainability, we reveal that early-packet timing patterns and cross-flow correlations drive classification decisions, providing operators with interpretable insights. Our system enables coherent workflow-level QoS enforcement and dynamic bandwidth allocation in scientific networks, eliminating manual per-flow configuration while maintaining classification latency at millisecond level.

Giannakou, Anna [LBL, Berkeley]↗

DOE OSTI2025

SigTime: Learning and Visually Explaining Time Series Signatures

Understanding and distinguishing temporal patterns in time series data is essential for scientific discovery and decision-making. For example, in biomedical research, uncovering meaningful patterns in physiological signals can improve diagnosis, risk assessment, and patient outcomes. However, existing methods for time series pattern discovery face major challenges, including high computational complexity, limited interpretability, and difficulty in capturing meaningful temporal structures. Here, to address these gaps, we introduce a novel learning framework that jointly trains two Transformer models using complementary time series representations: shapelet-based representations to capture localized temporal structures and traditional feature engineering to encode statistical properties. The learned shapelets serve as interpretable signatures that differentiate time series across classification labels. Additionally, we develop a visual analytics system—SigTime—with coordinated views to facilitate exploration of time series signatures from multiple perspectives, aiding in useful insights generation. We quantitatively evaluate our learning framework on eight publicly available datasets and one proprietary clinical dataset. Additionally, we demonstrate the effectiveness of our system through two usage scenarios along with the domain experts: one involving public ECG data and the other focused on preterm labor analysis.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Training data selection for event classification in a highly variable environment

A problem of interest for nuclear nonproliferation is monitoring activities at nuclear facilities, where proliferation events may only take place a few times and often under variable conditions. Machine learning has revolutionized data analytics by enabling the use of measurable signatures to generate predictive models of facility operations. However, traditional methods for training these models require large, reliable data sets with labeled observations, a challenge for nonproliferation. Highly variable conditions further complicate this as events from training data may have occurred in conditions quite different from the event of interest. Our hypothesis is that when events occur in a highly variable environment, careful training data selection for each test event could outperform the standard approach of using all available training data. We developed a method to optimize training data selection for the given test event and applied it to predicting the power level of the High Flux Isotope Reactor (HFIR) at Oak Ridge National Laboratory. In this study, the reactor startup exhibits variability between occurrences due to natural variability in environmental conditions and operational procedures. Using a combination of analysis techniques, a similitude assessment was performed on data collected from HFIR to isolate clusters that were optimal for training a predictive model. Concepts such as dynamic time warping and Jaccard similarity were used in conjunction with clustering analysis. In order to validate this approach, the model was trained on every combination of unique training events and the predictive performance was compared to the performance using a subset of the training data selected by isolated clusters found through the similitude assessment.

Iyer, A↗

DOE OSTI2022

The K2 Galactic Archaeology Program Data Release 3: Age-abundance Patterns in C1–C8 and C10–C18

We present the third and final data release of the K2 Galactic Archaeology Program (K2 GAP) for Campaigns C1–C8 and C10–C18. We provide asteroseismic radius and mass coefficients, κ R and κ M , for ~19,000 red giant stars, which translate directly to radius and mass given a temperature. As such, K2 GAP DR3 represents the largest asteroseismic sample in the literature to date. K2 GAP DR3 stellar parameters are calibrated to be on an absolute parallactic scale based on Gaia DR2, with red giant branch and red clump evolutionary state classifications provided via a machine-learning approach. Combining these stellar parameters with GALAH DR3 spectroscopy, we determine asteroseismic ages with precisions of ~20%–30% and compare age-abundance relations to Galactic chemical evolution models among both low- and high-α populations for α, light, iron-peak, and neutron-capture elements. We confirm recent indications in the literature of both increased Ba production at late Galactic times as well as significant contributions to r-process enrichment from prompt sources associated with, e.g., core-collapse supernovae. With an eye toward other Galactic archeology applications, we characterize K2 GAP DR3 uncertainties and completeness using injection tests, suggesting that K2 GAP DR3 is largely unbiased in mass/age, with uncertainties of 2.9% (stat.) ± 0.1% (syst.) and 6.7% (stat.) ± 0.3% (syst.) in κ R and κ M for red giant branch stars and 4.7% (stat.) ± 0.3% (syst.) and 11% (stat.) ± 0.9% (syst.) for red clump stars. We also identify percent-level asteroseismic systematics, which are likely related to the time baseline of the underlying data, and which therefore should be considered in TESS asteroseismic analysis.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2023

Application of a deep learning semantic segmentation model to helium bubbles and voids in nuclear materials

Imaging nanoscale radiation-induced defects using the transmission electron microscope (TEM) is a key factor in the successful implementation of materials for nuclear energy structural applications. Analyzing each defect in a TEM micrograph is currently a manual task. To identify the defects in a single image can take anywhere from 15 min to an hour and a project can require the analysis of anywhere from tens to ≥ 100 images. Here, we use artificial intelligence (AI) models to automate this task. For simplification, we evaluated images with only a single type of defect; helium bubbles. Additionally, we performed semantic segmentation of these helium bubble defects in electron microscopy images of irradiated FeCrAl alloys using a deep learning DefectSegNet model. This model, which was previously used to classify crystal defects, is inspired by the classic DenseNet and U-Net image segmentation models. It claims high spatial resolution, but has poor performance at object boundaries. Our paper improves the DefectSegNet model’s application by adding two new features. First, the DefectSegNet model is applied not only to perform calculation pixel-wise but also object (or feature) wise. Because object-wise metrics are directly relevant to our final goal of detecting bubbles, whereas pixel-wise classification is only an intermediate step, it is an important part of our study. Second, a distance map loss (DML) function has been added to increase its performance at object boundaries. It is crucial to accurately represent defects boundaries, especially bubbles, in order to track the bubble-induced swelling caused by irradiation. The boundary-focused DML function is also compared to other loss functions like Cross-entropy, Weighted Binary Cross Entropy (WBCE), Dice and Intersection over Union (IOU). Finally, by incorporating new features, we found a marked improvement on segmentation quality and better shape preservation at the boundaries and areas of the bubbles.

42 ENGINEERING↗

DOE OSTI2025

deadtrees.earth — An open-access and interactive database for centimeter-scale aerial imagery to uncover global tree mortality dynamics

Excessive tree mortality is a global concern and remains poorly understood as it is a complex phenomenon. We lack global and temporally continuous coverage on tree mortality data. Ground-based observations on tree mortality, e.g., derived from national inventories, are very sparse, and may not be standardized or spatially explicit. Earth observation data, combined with supervised machine learning, offer a promising approach to map overstory tree mortality in a consistent manner over space and time. However, global-scale machine learning requires broad training data covering a wide range of environmental settings and forest types. Low altitude observation platforms (e.g., drones or airplanes) provide a cost-effective source of training data by capturing high-resolution orthophotos of overstory tree mortality events at centimeter-scale resolution. Here, we introduce deadtrees.earth, an open-access platform hosting more than two thousand centimeter-resolution orthophotos, covering more than 1,000,000 ha, of which more than 58,000 ha are manually annotated with live/dead tree classifications. This community-sourced and rigorously curated dataset can serve as a comprehensive reference dataset to uncover tree mortality patterns from local to global scales using space-based Earth observation data and machine learning models. This will provide the basis to attribute tree mortality patterns to environmental changes or project tree mortality dynamics to the future. The open nature of deadtrees.earth, together with its curation of high-quality, spatially representative, and ecologically diverse data will continuously increase our capacity to uncover and understand tree mortality dynamics.

Citizen science↗

DOE OSTI2020

Machine learning study of magnetism in uranium-based compounds

Actinide and lanthanide-based materials display exotic properties that originate from the presence of itinerant or localized f electrons and include unconventional superconductivity and magnetism, hidden order, and heavy-fermion behavior. Due to the strongly correlated nature of the 5f electrons, magnetic properties of these compounds depend sensitively on applied magnetic field and pressure, as well as on chemical doping. However, precise connection between the structure and magnetism in actinide-based materials is currently unclear. In this investigation, we established such structure-property links by assembling and mining two datasets that aggregate, respectively, the results of high-throughput density functional theory simulations and experimental measurements for the families of uranium- and neptunium-based binary compounds. Various regression algorithms were utilized to identify correlations among accessible attributes (features or descriptors) of the material systems and predict their cation magnetic moments and general forms of magnetic ordering. Descriptors representing compound structural parameters and cation f-subshell occupation numbers were identified as most important for accurate predictions. The best machine learning model developed employs the random forest regression algorithm. It can predict both spin and orbit moment size with root-mean-square error of 0.17 μ B and 0.19 μ B , respectively. Lastly, the random forest classification algorithm is used to predict the ordering (paramagnetic, ferromagnetic, and antiferromagnetic) of such systems with 76% accuracy.

36 MATERIALS SCIENCE↗