SEARCH · Engineering Papers
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.
Dataset including high-speed down-axis RDE images used for updated image classification study. This dataset includes 100,000 images with 10 classifications: 1CW, 1CCW, 2CW, 2CCW, 3CW, 3CCW, and Deflagration. Images are cropped to center annulus, and resized to 301x301 pixels. Images are filtered using the AFRL Beta correction factor.
High-Risk Property (HRP) classification is critical at U.S. Department of Energy (DOE) sites, where inventories include sensitive and often dual-use equipment. Compliance must track evolving rules designated by various export control policies to make transparent and auditable decisions. Traditional expert-only workflows are time-consuming, backlog-prone, and struggle to keep pace with shifting regulatory boundaries. We propose ORCHID, a modular agentic framework for HRP classification that pairs retrieval-augmented generation (RAG) with human oversight to produce policy based outputs that can be audited. Small cooperating agents—retrieval, description refiner, classifier, validator, and feedback logger—coordinate via agent-to-agent messaging and invoke tools through the Model Context Protocol (MCP) for model-agnostic on-premise operation. The interface follows an "Item to Evidence to Decision" loop with step-by-step reasoning, on-policy citations, and append-only audit bundles (run-cards, prompts, evidence). In preliminary tests on real HRP cases, ORCHID improves accuracy and traceability over a non-agentic baseline while deferring uncertain items to Subject Matter Experts (SMEs). The demonstration shows single item submission, grounded citations, SME feedback capture, and exportable audit artifacts—illustrating a practical path to trustworthy LLM assistance in sensitive DOE compliance workflows.
Optical systems provide valuable information for evaluating interactions and associations between organisms and MHK energy converters and for capturing potentially rare encounters between marine organisms and MHK device. The deluge of optical data from cabled monitoring packages makes expert review time-consuming and expensive. We propose algorithms and a processing framework to automatically extract events of interest from underwater video. The open-source software framework consists of background subtraction, filtering, feature extraction and hierarchical classification algorithms. This principle classification pipeline was validated on real-world data collected with an experimental underwater monitoring package. An event detection rate of 100% was achieved using robust principal components analysis (RPCA), Fourier feature extraction and a support vector machine (SVM) binary classifier. The detected events were then further classified into more complex classes – algae | invertebrate | vertebrate, one species | multiple species of fish, and interest rank. Greater than 80% accuracy was achieved using a combination of machine learning techniques.
To expand the capabilities of safeguards authorities to verify the integrity of fresh fuel assemblies, Oak Ridge National Laboratory has retrofit the existing electronics of the JCC-71 uranium neutron coincidence collar, which contains 18 3 He neutron detectors and an external 241 AmLi(α, n) neutron interrogation source arranged to surround a fresh nuclear fuel assembly. The new electronics system allows analysts to record list-mode neutron multiplicity data in addition to the singles and doubles rates that are currently measured. Based on previous proof-of-concept research, analysis of these new data will identify off-normal fuel configurations in an assembly and characterize or localize the specific partial fuel defects. The purpose of this report it to document the analysis algorithm development and then to demonstrate its capability for the safeguards verification of fresh fuel assemblies using list mode neutron collar data. To analyze the complex list-mode data collected with the upgraded uranium neutron collar, multivariate classification algorithms are being developed using a novel classification method, the relevance vector machine. This approach may be applied to multiclass problems to estimate the probability that test data belongs to one of many possible classes of data. In addition, our method identifies the most useful variables/channels for making predictions, which illuminates the basis for the model’s predictions, and this interpretability is largely unique among data analytics methods. Variable selection occurs during model training and parameter tuning and does not need any external hyperparameter tuning routines. Finally, we apply the modified relevance vector machine to a simulated dataset of list-mode neutron collar data generated with the radiation transport code MCNP. The method can correctly identify off-normal fuel configurations, categorize the data according to four fuel defect scenarios, and rank the channels in the data according to prediction utility. For nuclear safeguards applications, it is concluded that this method has the potential to increase the sensitivity and reliability to detect missing fuel rods from a standard 17 x 17 Pressurized Water Reactor (PWR) fresh fuel assembly. Within this analysis, “off-normal” (i.e., missing fuel rods) were correctly classified in 17 simulated test scenarios with one quarter (25%) of the fresh fuel rods missing using a training data set of 58 simulated measurements.
The leading edge erosion of wind turbine blades is a common issue that can have a range of implications for the operation and maintenance of the turbine. A variety of methods have attempted to determine the severity of erosion damage, applied in different academic, testing and in-situ settings. This paper describes the current state of the art in categorization, and the individual drivers in assessment. From this foundation, the IEA Wind Task 46 WP3 group collated key considerations from the process of categorizing erosion damage and a proposed erosion classification system was put forward. Trial assessments were performed using the initial system, which led to adjustments to the original proposition. The refined system defines discrete severity levels that concern the wind turbine blade: (1) Visual Condition (concerning blades with/without leading edge protection); (2) Mass Loss; (3) Aerodynamic Performance; and (4) Structural Integrity. The classification system presented is not intended to be a fixed entity. The Task 46 group has already identified specific challenges and opportunities that are applicable to individual use and the overall wind energy industry. The intention is for the system to evolve as improvements are identified, technology improves, and work progresses through other Task 46 activities. Several considerations and recommendations are discussed that could be applicable for future implementation of the system.
Binary classification using machine learning is needed to address engineering problems such as identifying passing/failing parts based on measured features from aging hardware. In these classifications, providing the uncertainty of each prediction is essential to support engineering decision making. One popular classifier is the support vector machine (SVM). There are many variations, with the simplest being a linear division between two classes with a hyperplane. Kernel methods can be implement
Crystallographic texture is an important descriptor of material properties but requires time-intensive electron backscatter diffraction (EBSD) for identifying grain orientations. While some metrics such as grain size or grain aspect ratio can distinguish textured microstructures from untextured microstructures after significant grain growth, such morphological differences are not always visually observable. This paper explores the use of deep learning to classify experimentally measured textured microstructures without knowledge of crystallographic orientation. A deep convolutional neural network is used to extract high-order morphological features from binary images to distinguish textured microstructures from untextured microstructures. The convolutional neural network results are compared with a statistical Kolmogorov–Smirnov tests with traditional morphological metrics for describing microstructures. Results show that the convolutional neural network achieves a significantly improved classification accuracy, particularly at early stages of grain growth, highlighting the capability of deep learning to identify the subtle morphological patterns resulting from texture. The results demonstrate the potential of a convolutional neural network as a tool for reliable and automated microstructure classification with minimal preprocessing.
Introduction Sequencing and phylogenetic classification have become a common task in human and animal diagnostic laboratories. It is routine to sequence pathogens to identify genetic variations of diagnostic significance and to use these data in realtime genomic contact tracing and surveillance. Under this paradigm, unprecedented volumes of data are generated that require rapid analysis to provide meaningful inference. Methods We present a machine learning logistic regression pipeline that can assign classifications to genetic sequence data. The pipeline implements an intuitive and customizable approach to developing a trained prediction model that runs in linear time complexity, generating accurate output rapidly, even with incomplete data. Our approach was benchmarked against porcine respiratory and reproductive syndrome virus (PRRSv) and swine H1 influenza A virus (IAV) datasets. Trained classifiers were tested against sequences and simulated datasets that artificially degraded sequence quality at 0, 10, 20, 30, and 40%. Results When applied to a poor-quality sequence data, the classifier achieved between >85% to 95% accuracy for the PRRSv and the swine H1 IAV HA dataset and this increased to near perfect accuracy when using the full dataset. The model also identifies amino acid positions used to determine genetic clade identity through a feature selection ranking within the model. These positions can be mapped onto a maximum-likelihood phylogenetic tree, allowing for the inference of clade defining mutations. Discussion Our approach is implemented as a python package with code available at https://github.com/flu-crew/classLog .
Models based on vision transformer architectures are considered state-of-the-art when it comes to image classification tasks. However, they require extensive computational resources both for training and deployment. The problem is exacerbated as the amount and complexity of the data increases. Quantum-based vision transformer models could potentially alleviate this issue by reducing the training and operating time while maintaining the same predictive power. Although current quantum computers are not yet able to perform high-dimensional tasks, they do offer one of the most efficient solutions for the future. In this work, we construct several variations of a quantum hybrid vision transformer for a classification problem in high-energy physics (distinguishing photons and electrons in the electromagnetic calorimeter). We test them against classical vision transformer architectures. Our findings indicate that the hybrid models can achieve comparable performance to their classical analogs with a similar number of parameters.
High-throughput analysis of biomass is necessary to ensure consistent and uniform feedstocks for agricultural and bioenergy applications and is needed to inform genomics and systems biology models. Pyrolysis followed by mass spectrometry such as molecular beam mass spectrometry (py-MBMS) analyses are becoming increasingly popular for the rapid analysis of biomass cell wall composition and typically require the use of different data analysis tools depending on the need and application. Here, the authors report the py-MBMS analysis of several types of lignocellulosic biomass to gain an understanding of spectral patterns and variation with associated biomass composition and use machine learning approaches to classify, differentiate, and predict biomass types on the basis of py-MBMS spectra. Py-MBMS spectra were also corrected for instrumental variance using generalized linear modeling (GLM) based on the use of select ions relative abundances as spike-in controls. Machine learning classification algorithms e.g., random forest, k-nearest neighbor, decision tree, Gaussian Naïve Bayes, gradient boosting, and multilayer perceptron classifiers were used. The k-nearest neighbors (k-NN) classifier generally performed the best for classifications using raw spectral data, and the decision tree classifier performed the worst. After normalization of spectra to account for instrumental variance, all the classifiers had comparable and generally acceptable performance for predicting the biomass types, although the k-NN and decision tree classifiers were not as accurate for prediction of specific sample types. Gaussian Naïve Bayes (GNB) and extreme gradient boosting (XGB) classifiers performed better than the k-NN and the decision tree classifiers for the prediction of biomass mixtures. The data analysis workflow reported here could be applied and extended for comparison of biomass samples of varying types, species, phenotypes, and/or genotypes or subjected to different treatments, environments, etc. to further elucidate the sources of spectral variance, patterns, and to infer compositional information based on spectral analysis, particularly for analysis of data without a priori knowledge of the feedstock composition or identity.
Ultrasound (US) imaging is a critical tool in emergency and military medicine because of its portability and immediate nature. However, proper image interpretation requires skill, limiting its utility in remote applications for conditions such as pneumothorax (PTX) which requires rapid intervention. Artificial intelligence has the potential to automate ultrasound image analysis for various pathophysiological conditions. Training models require large data sets and a means of troubleshooting in real-time for ultrasound integration deployment, and they also require large animal models or clinical testing. Here, we detail the development of a dynamic synthetic tissue phantom model for PTX and its use in training image classification algorithms. The model comprises a synthetic gelatin phantom cast in a custom 3D-printed rib mold and a lung mimicking phantom. When compared to PTX images acquired in swine, images from the phantom were similar in both PTX negative and positive mimicking scenarios. We then used a deep learning image classification algorithm, which we previously developed for shrapnel detection, to accurately predict the presence of PTX in swine images by only training on phantom image sets, highlighting the utility for a tissue phantom for AI applications.
The cloud phase is one of the most important parameters of clouds. In this paper, we propose a method for cloud phase classification that synergistically utilizes the far- and thermal-infrared bands based on the Atmospheric Emitted Radiance Interferometer (AERI) at the Atmospheric Radiation Measurement West Antarctic Radiation Experiment (AWARE) observatory in 2016. The possible features in the far- and thermal-infrared bands are analyzed based on the differences in the simulated cloud brightness temperature (BT) spectra with different cloud phases. Using the support vector machine (SVM) algorithm, four features are determined to identify the cloud phase, which include the BT at 900 cm -1 , the slope of the fitted function of BT in the 900–1000 cm -1 interval, the BT difference (BTD) between 512 cm -1 and 726 cm -1 , and the BTD between 550 cm -1 and 726 cm -1 . Here, the performance of the proposed method is evaluated with Shupe’s and Turner’s method. The monthly average accuracy of the proposed method, the method without the two far-infrared features, and Turner’s method are about 76%, 36%, and 49%, respectively, which infer the good performance of the proposed method and also indicate that the far-infrared band features can effectively enhance cloud phase classification. It is notable that, compared to Shupe’s method, the accuracy for the proposed method is only 61% during the Antarctic summer, which results from the definitions of cloud phase and radiative effect. In addition, the accuracy is only 44% for Turner’s method in seasons with a low frequency of mixed clouds due to the significant effect of water vapor.
Camera-based sensing has benefited in recent years from developments in machine learning data processing methods, as well as improved data collection options such as Unmanned Aerial Vehicles (UAV) mounted sensors. However, cost considerations, both for the initial purchase of sensors as well as updates, maintenance, or potential replacement if damaged, can limit adoption of more expensive sensing options for some applications. To evaluate more affordable options with less expensive, more available, and more easily replaceable hardware, we examine the use of machine learning-based image classification with custom datasets, utilizing deep learning based-image classification and the use of ensemble models for sensor fusion. Utilizing the same models for each camera to reduce technical overhead, we showed that for a very representative training dataset, camera-based detection can be successful for detection of electrical arcing. We also use multiple validation datasets, based on conditions expected to be of varying difficulty, to evaluate custom data. These results show that ensemble models of different data sources can mitigate risks from gaps in training data, though the system will be less redundant for those cases unless other precautions are taken. We found that with good quality custom datasets, data fusion models can be utilized without specialization in design to the specific cameras utilized, allowing for less specialized, more accessible equipment to be utilized as multispectral camera components. This approach can provide an alternative to expensive sensing equipment for applications in which lower-cost or more easily replaceable sensing equipment is desirable.
In many university and healthcare projects, models are built for very different data types such as tables, institutional time series, and medical images, but they are deployed as separate applications. In this work, that separation made testing and maintenance difficult because each module had its own pipeline and runtime requirements. This paper presents an integrated AI lakehouse-style implementation that runs three model pipelines inside one containerized backend. For medical imaging, we used MRI datasets from IEEE DataPort: a four-class classification set with 7012 images (5708 train/1304 test) and a segmentation set with 3063 image–mask pairs. The classification model (ResNet50 transfer learning) is evaluated using a proper train–validation–test protocol across multiple splits (80/10/10, 70/10/20, 60/10/30, and 10/30/60), achieving a test accuracy of 99.00% under the standard 80/10/10 split. Additionally, a patient-level evaluation is conducted using an external glioma dataset to provide a more realistic assessment without data leakage. The segmentation model (DeepLabV3-ResNet50) achieved 83.09% validation mIoU and 88.79% Dice score. For university KPI forecasting, we used annual IPEDS and NSF HERD data from 2010 to 2023 for three universities (BSU, EOU, and UAB). To examine the effect of preprocessing on forecasting performance, two case studies are conducted. In the first case, linear interpolation is applied to generate semester-level data. In the second case, the original annual data is used directly without interpolation. Random Forest regression and ARIMA models are evaluated using MAE, RMSE, MAPE, and R 2 . The results showed that interpolation improved apparent forecasting performance due to smoothing, while evaluation on the original annual data provided a more realistic assessment of model behavior. To further validate the framework on a larger dataset, an additional case study is conducted using a student dropout dataset. For water potability, we trained and compared multiple tabular classifiers on a large dataset (1,048,575 samples). A Random Forest model (100 trees, max depth 10) achieved 85.86% test accuracy and high recall for unsafe samples (0.8447). All modules are served via FastAPI and deployed together using Docker, with workflow automation routing requests to the correct endpoint. System-level benchmarking indicates that the backend maintains stable throughput and latency under concurrent requests.
Lambda Boo-type stars are a group of late B to early F-type Population I dwarfs that show mild to extreme deficiencies of iron-peak elements (up to 2 dex), but their C, N, O, and S abundances are near solar. This intriguing stellar class has recently regained the spotlight because of the directly imaged planets around a confirmed Lambda Boo star, HR 8799, and a suggested Lambda Boo star, Beta Pictoris. The discovery of a giant asteroid belt around Vega, another possible Lambda Boo star, also suggests hidden planets. The possible link between Lambda Boo stars and planet-bearing stars motivates us to study Lambda Boo stars systematically. Since the peculiar nature of the prototype Lambda Boötis was first noticed in 1943, Lambda Boo candidates published in the literature have been selected using widely different criteria. In order to determine the origin of Lambda Boo stars’ unique abundance pattern and to better discriminate between theories explaining the Lambda Boo phenomenon, a consistent working definition of Lambda Boo stars is needed. We have re-evaluated all published Lambda Boo candidates and their available ultraviolet and visible spectra. In this paper, using observed and synthetic spectra, we explore the physical basis for the classification of Lambda Boo stars, and develop quantitative criteria that discriminate metal-poor stars from bona fide Lambda Boo stars. Based on these stricter Lambda Boo classification criteria, we conclude that neither Beta Pictoris nor Vega should be classified as Lambda Boo stars.
The ρ Puppis stars are mid-F-type stars that show peculiar chemical-abundance patterns similar to those of the Am stars. Typically they exhibit overabundances of iron-peak elements such as Fe and Ni and s- and r-process elements such as Sr and Eu, and underabundances of certain other elements including He, Ca, and Sc. It has been proposed that these stars are evolving Am stars passing through the short-lived phase that occurs between the re-establishment of convection and the consequent erasure of their chemical peculiarities. In this paper we suggest a second hypothesis: these stars may have acquired their peculiar abundance patterns in a fashion similar to the Barium stars, i.e., they may have gained the s-process element enhancements via mass transfer from a once asymptotic giant-branch companion star, now turned white dwarf. This study will detail our efforts to investigate the ρ Puppis stars with regard to these two hypotheses, with a view to understanding these stars and their significance in terms of stellar evolution. We have performed a spectral classification survey, and a detailed chemical-abundance analysis of selected ρ Puppis stars. This paper gives an overview of the ρ Puppis stars and describes the spectral classification survey which has increased the number of ρ Puppis stars currently known from 6 to 49. A future paper will describe the chemical-abundance analysis which should provide insight into the nature of these stars.
The Zwicky Transient Facility (ZTF) has been observing the entire northern sky since the start of 2018 down to a magnitude of 20.5 (5σ for 30 s exposure) in the g, r, and i filters. Over the course of two years, ZTF has obtained light curves of more than a billion sources, each with 50–1000 epochs per light curve in g and r, and fewer in i. To be able to use the information contained in the light curves of variable sources for new scientific discoveries, an efficient and flexible framework is needed to classify them. In this paper, we introduce the methods and infrastructure that will be used to classify all ZTF light curves. Our approach aims to be flexible and modular and allows the use of a dynamical classification scheme and labels, continuously evolving training sets, and the use of different machine-learning classifier types and architectures. Finally with this setup, we are able to continuously update and improve the classification of ZTF light curves as new data become available, training samples are updated, and new classes need to be incorporated.
Clouds are highly variable in time and space, affecting climate sensitivity and climate change. To study and distinguish the different influences of clouds on the climate system, it is useful to separate clouds into individual cloud regimes. In this work we present a new cloud classification for liquid water clouds at cloud scale defined using cloud parameters retrieved from combined satellite measurements from CloudSat and CALIPSO. The idea is that cloud heterogeneity is a measure that allows us to distinguish cumuliform and stratiform clouds, and cloud-base height is a measure to distinguish cloud altitude. The approach makes use of a newly developed cloud-base height retrieval. Using three cloud-base height intervals and two intervals of cloud-top variability as an inhomogeneity parameter provides six new liquid cloud classes. The results show a smooth transition between marine and continental clouds as well as between stratiform and cumuliform clouds in different latitudes at the high spatial resolution of about 20 km. Analysing the micro- and macrophysical cloud parameters from collocated combined MODIS, CloudSat and CALIPSO retrievals shows distinct characteristics for each cloud regime that are in agreement with expectation and literature. This demonstrates the usefulness of the classification.