Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “supervised training”

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.

At least 217 records · Page 12

Combining synchrotron X-ray diffraction, mechanistic modeling and machine learning for in situ subsurface temperature quantification during laser melting

Laser melting, such as that encountered during additive manufacturing, produces extreme gradients of temperature in both space and time, which in turn influence microstructural development in the material. Qualification and model validation of the process itself and the resulting material necessitate the ability to characterize these temperature fields. However, well established means to directly probe the material temperature below the surface of an alloy while it is being processed are limited. To address this gap in characterization capabilities, a novel means is presented to extract subsurface temperature-distribution metrics, with uncertainty, from in situ synchrotron X-ray diffraction measurements to provide quantitative temperature evolution data during laser melting. Temperature-distribution metrics are determined using Gaussian process regression supervised machine-learning surrogate models trained with a combination of mechanistic modeling (heat transfer and fluid flow) and X-ray diffraction simulation. The trained surrogate model uncertainties are found to range from 5 to 15% depending on the metric and current temperature. The surrogate models are then applied to experimental data to extract temperature metrics from an Inconel 625 nickel superalloy wall specimen during laser melting. The maximum temperatures of the solid phase in the diffraction volume through melting and cooling are found to reach the solidus temperature as expected, with the mean and minimum temperatures found to be several hundred degrees less. The extracted temperature metrics near melting are determined to be more accurate because of the lower relative levels of mechanical elastic strains. However, uncertainties for temperature metrics during cooling are increased due to the effects of thermomechanical stress.

36 MATERIALS SCIENCE↗

Cavity contour segmentation in chest radiographs using supervised learning and dynamic programming

Purpose: Efficacy of tuberculosis (TB) treatment is often monitored using chest radiography. Monitoring size of cavities in pulmonary tuberculosis is important as the size predicts severity of the disease and its persistence under therapy predicts relapse. The authors present a method for automatic cavity segmentation in chest radiographs. Methods: A two stage method is proposed to segment the cavity borders, given a user defined seed point close to the center of the cavity. First, a supervised learning approach is employed to train a pixel classifier using texture and radial features to identify the border pixels of the cavity. A likelihood value of belonging to the cavity border is assigned to each pixel by the classifier. The authors experimented with four different classifiers:k-nearest neighbor (kNN), linear discriminant analysis (LDA), GentleBoost (GB), and random forest (RF). Next, the constructed likelihood map was used as an input cost image in the polar transformed image space for dynamic programming to trace the optimal maximum cost path. This constructed path corresponds to the segmented cavity contour in image space. Results: The method was evaluated on 100 chest radiographs (CXRs) containing 126 cavities. The reference segmentation was manually delineated by an experienced chest radiologist. An independent observer (a chest radiologist) also delineated all cavities to estimate interobserver variability. Jaccard overlap measure Ω was computed between the reference segmentation and the automatic segmentation; and between the reference segmentation and the independent observer's segmentation for all cavities. A median overlap Ω of 0.81 (0.76 ± 0.16), and 0.85 (0.82 ± 0.11) was achieved between the reference segmentation and the automatic segmentation, and between the segmentations by the two radiologists, respectively. The best reported mean contour distance and Hausdorff distance between the reference and the automatic segmentation were, respectively, 2.48 ± 2.19 and 8.32 ± 5.66 mm, whereas these distances were 1.66 ± 1.29 and 5.75 ± 4.88 mm between the segmentations by the reference reader and the independent observer, respectively. The automatic segmentations were also visually assessed by two trained CXR readers as “excellent,” “adequate,” or “insufficient.” The readers had good agreement in assessing the cavity outlines and 84% of the segmentations were rated as “excellent” or “adequate” by both readers. Conclusions: The proposed cavity segmentation technique produced results with a good degree of overlap with manual expert segmentations. The evaluation measures demonstrated that the results approached the results of the experienced chest radiologists, in terms of overlap measure and contour distance measures. Automatic cavity segmentation can be employed in TB clinics for treatment monitoring, especially in resource limited settings where radiologists are not available.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

DONUT: Physics-aware Machine Learning for Real-time X-ray Nanodiffraction Analysis

SF-25-088 Coherent X-ray scattering techniques are critical for investigating the fundamental structural properties of materials at the nanoscale. While advancements have made these experiments more accessible, real-time analysis remains a significant bottleneck, often hindered by artifacts and computational demands. In scanning X-ray nanodiffraction microscopy, which is widely used to spatially resolve structural heterogeneities, this challenge is compounded by the convolution of the divergent beam with the sample’s local structure. To address this, we introduce DONUT (Diffraction with Optics for Nanobeam by Unsupervised Training), a physics-aware neural network designed for the rapid and automated analysis of nanobeam diffraction data. By incorporating a differentiable geometric diffraction model directly into its architecture, DONUT learns to predict crystal lattice strain and orientation in real-time. Crucially, this is achieved without reliance on labeled datasets or pre-training, overcoming a fundamental limitation for supervised machine learning in X-ray science. We demonstrate experimentally that DONUT accurately extracts all features within the data over 200 times more efficiently than conventional fitting methods.

Zhou, Tao [Argonne National Laboratory (ANL), Argo↗

The Mantis Shrimp Dataset

The Mantis Shrimp Dataset (MSD) is a combination of matched cutouts of galaxies with known redshift in the ultra-violet, optical, and infrared wavelengths. MSD redshifts come from ''high-quality'' (as reported by the spectroscopic experiment) redshift measurements from a variety of spectroscopic surveys, including: SDSS, DESI early release, DEEP2, GAMA, VVDS, VIPERS, 6dF, and WiggleZ. Each redshift is accompanies with astrometry (ra,dec) pairs that were used to query cutout image services from PanSTARRs, UnWISE, and GALEX servers. The main data products are image vectors of these cutouts accompanied by the redshift value to be used to train computer vision networks on the supervised photometric redshift task. We also provide extinction values pre-queried at each galaxies' astrometry from the PLANCK and SFD dutstmaps, the SDSS MGS photometric redshift from Beck 2014 (if available) and the WISE x PS1 STRM photometric redshift for the galaxy (if available).

79 ASTRONOMY AND ASTROPHYSICS↗

Automatic classification of soils and vegetation with ERTS-1 data

Preliminary results of a test of a computerized analysis method using ERTS 1 data are presented. The method consisted of a four-spectral-band supervised, maximum likelihood, Gaussian classifier with training statistics derived through a combination of clustering and manual methods. The multivariate analysis method leads to the assignment of each resolution element of the data to one of a preselected set of discrete classes. The data frame was an area over the Texas-Oklahoma border including Lake Texoma. The study suggests that multispectral scanner data coupled with machine processing shows promise for earth surface cover surveys. Futhermore, the processing time is short and consequently the costs are low; a full frame can be analyzed completely within 48 hours.

Landgrebe, D. A.↗

The use of ERTS/LANDSAT imagery in relation to airborne remote sensing for terrain analysis in western Queensland, Australia

The author has identified the following significant results. Series of linears were identified on the March imagery of Lady Annie-Mt. Gordon fault zone area. The series with a WSW-ENE orientation which is normal to the major structural units and also several linears with NNW-SSE orientation appears to be particularly important. Copper mineralization is known at several localities where these linears are intersected by faults. Automated outputs using supervised methods involving the selection of training sets selected by visual recognition of spectral signatures on the color composites obtained from combinations of MSS bands 4, 5 and 7 projected through appropriate filters, were generated.

Cole, M. M.↗

Evaluation of SLAR and thematic mapper MSS data for forest cover mapping using computer-aided analysis techniques

To facilitate comparison between the four different spatial resolution of the NS-001 MSS data sets, a supervised approach was taken in defining training blocks for each of the different cover types. The training fields representing each cover type category were grouped and this group was clustered to determine the individual spectral classes within each cover type category which would effectively characterize the entire test site. Graphs show the variation in spectral response level with respect to distance in the across track dimension for four sampling intervals. Radar digitization procedures were developd. Flight characteristics and parameters for digitization of radar imagery are tabulated. The statement of work for phase 3 was reviewed and modifications were suggested to meet funding reduction.

Hoffer, R. M.↗

LANDSAT landcover information applied to regional planning decisions

Land cover information derived from LANDSAT is being utilized by Piedmont Planning District Commission located in the State of Virginia. Progress to date is reported on a level one land cover classification map being produced with nine categories. The nine categories of classification are defined. The computer compatible tape selection is presented. Two unsupervised classifications were done, with 50 and 70 classes respectively. Twenty-eight spectral classes were developed using the supervised technique, employing actual ground truth training sites. The accuracy of the unsupervised classifications are estimated through comparison with local county statistics and with an actual pixel count of LANDSAT information compared to ground truth.

Dixon, C. M.↗

Graphic overlays in high-precision teleoperation: Current and future work at JPL

In space teleoperation additional problems arise, including signal transmission time delays. These can greatly reduce operator performance. Recent advances in graphics open new possibilities for addressing these and other problems. Currently a multi-camera system with normal 3-D TV and video graphics capabilities is being developed. Trained and untrained operators will be tested for high precision performance using two force reflecting hand controllers and a voice recognition system to control two robot arms and up to 5 movable stereo or non-stereo TV cameras. A number of new techniques of integrating TV and video graphics displays to improve operator training and performance in teleoperation and supervised automation are evaluated.

Diner, Daniel B.↗

Modeling Weather Impact on Airport Arrival Miles-in-Trail Restrictions

When the demand for either a region of airspace or an airport approaches or exceeds the available capacity, miles-in-trail (MIT) restrictions are the most frequently issued traffic management initiatives (TMIs) that are used to mitigate these imbalances. Miles-intrail operations require aircraft in a traffic stream to meet a specific inter-aircraft separation in exchange for maintaining a safe and orderly flow within the stream. This stream of aircraft can be departing an airport, over a common fix, through a sector, on a specific route or arriving at an airport. This study begins by providing a high-level overview of the distribution and causes of arrival MIT restrictions for the top ten airports in the United States. This is followed by an in-depth analysis of the frequency, duration and cause of MIT restrictions impacting the Hartsfield-Jackson Atlanta International Airport (ATL) from 2009 through 2011. Then, machine-learning methods for predicting (1) situations in which MIT restrictions for ATL arrivals are implemented under low demand scenarios, and (2) days in which a large number of MIT restrictions are required to properly manage and control ATL arrivals are presented. More specifically, these predictions were accomplished by using an ensemble of decision trees with Bootstrap aggregation (BDT) and supervised machine learning was used to train the BDT binary classification models. The models were subsequently validated using data cross validation methods. When predicting the occurrence of arrival MIT restrictions under low demand situations, the model was able to achieve over all accuracy rates ranging from 84% to 90%, with false alarm ratios ranging from 10% to 15%. In the second set of studies designed to predict days on which a high number of MIT restrictions were required, overall accuracy rates of 80% were achieved with false alarm ratios of 20%. Overall, the predictions proposed by the model give better MIT usage information than what has been currently provided under current day operations. Traffic flow managers can use these predictions to identify potential MIT restrictions to eliminate (e.g., those occurring during low arrival demand periods), and to determine the days in which a significant number of restrictions may be required

Operation↗

Earth Science Deep Learning: Applications and Lessons Learned

Deep learning has revolutionized computer vision and natural language processing with various algorithms scaled using high-performance computing. At the NASA Marshall Space Flight Center (MSFC), the Data Science and Informatics Group (DSIG) has been using deep learning for a variety of Earth science applications. This paper provides examples of the applications and also addresses some of the challenges that were encountered.

Training↗

A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain

Magnetic resonance (MR) brain section images are segmented and then synthetically colored to give visual representations of the original data with three approaches: the literal and approximate fuzzy c-means unsupervised clustering algorithms and a supervised computational neural network, a dynamic multilayered perception trained with the cascade correlation learning algorithm. Initial clinical results are presented on both normal volunteers and selected patients with brain tumors surrounded by edema. Supervised and unsupervised segmentation techniques provide broadly similar results. Unsupervised fuzzy algorithms were visually observed to show better segmentation when compared with raw image data for volunteer studies. However, for a more complex segmentation problem with tumor/edema or cerebrospinal fluid boundary, where the tissues have similar MR relaxation behavior, inconsistency in rating among experts was observed.

Hall, Lawrence O.↗

Accelerated Over-The-Air Neural Receiver Training Using Self-Contrastive Learning

Self-contrastive learning (SCL), a self-supervised learning method, has been shown to improve image and signal classifier accuracies and reduce the training time for neural communications receivers. In particular, prior work has shown that SCL applied as a pre-training step can improve simulated performance of OFDM in 3GPP TDL channel models by reducing the training time of the downstream classification task (demodulation and demapping). In this work a practical implementation demonstrating SCL pre-training using software defined radios (SDRs) is proposed.

Cooke, Corey [ORNL] (ORCID:0000000234263672)↗

(Machine) learning to do more with less

Determining the best method for training a machine learning algorithm is critical to maximizing its ability to classify data. In this paper, we compare the standard “fully supervised” approach (which relies on knowledge of event-by-event truth-level labels) with a recent proposal that instead utilizes class ratios as the only discriminating information provided during training. This so-called “weakly supervised” technique has access to less information than the fully supervised method and yet is still able to yield impressive discriminating power. In addition, weak supervision seems particularly well suited to particle physics since quantum mechanics is incompatible with the notion of mapping an individual event onto any single Feynman diagram. We examine the technique in detail — both analytically and numerically — with a focus on the robustness to issues of mischaracterizing the training samples. Weakly supervised networks turn out to be remarkably insensitive to a class of systematic mismodeling. Furthermore, we demonstrate that the event level outputs for weakly versus fully supervised networks are probing different kinematics, even though the numerical quality metrics are essentially identical. This implies that it should be possible to improve the overall classification ability by combining the output from the two types of networks. For concreteness, we apply this technology to a signature of beyond the Standard Model physics to demonstrate that all these impressive features continue to hold in a scenario of relevance to the LHC. Example code is provided on GitHub.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Gaussian Process for Flight Delay Prediction: Learning a Stochastic Process

This paper presents a machine-learning approach to predict flight delays. Whereas neural networks are extensively studied for predictive capabilities, they involve non-intuitive design and extensive analysis, particularly in training and optimization processes. Instead, the proposed framework employs Gaussian Processes as a supervised learning technique for flight delay prediction. This data-driven approach trains the model using prior information, specifically the mean and covariance tied to existing data. The proposed Gaussian Process Regression (GPR) model employs the day of flight as a pivotal feature for delay forecasting. We analyze flights from various routes and gauge the accuracy of the presented learning technique by comparing the predicted delays with the actual ones. Given the inherent challenges in precisely forecasting delays, we predict the delays with a 95 % confidence interval. Also, an error propagation analysis in the prediction horizon is carried out to determine the optimal time frame for prediction. The proposed method for flight delay prediction is important as airlines can strategize flight operations and issue timely advisories.

stochastic↗

Improving an Acoustic Vehicle Detector Using an Iterative Self-Supervision Procedure

In many non-canonical data science scenarios, obtaining, detecting, attributing, and annotating enough high-quality training data is the primary barrier to developing highly effective models. Moreover, in many problems that are not sufficiently defined or constrained, manually developing a training dataset can often overlook interesting phenomena that should be included. To this end, we have developed and demonstrated an iterative self-supervised learning procedure, whereby models are successfully trained and applied to new data to extract new training examples that are added to the corpus of training data. Successive generations of classifiers are then trained on this augmented corpus. Using low-frequency acoustic data collected by a network of infrasound sensors deployed around the High Flux Isotope Reactor and Radiochemical Engineering Development Center at Oak Ridge National Laboratory, we test the viability of our proposed approach to develop a powerful classifier with the goal of identifying vehicles from continuously streamed data and differentiating these from other sources of noise such as tools, people, airplanes, and wind. Using a small collection of exhaustively manually labeled data, we test several implementation details of the procedure and demonstrate its success regardless of the fidelity of the initial model used to seed the iterative procedure. Finally, we demonstrate the method’s ability to update a model to accommodate changes in the data-generating distribution encountered during long-term persistent data collection.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗