Search NASA⌕ Search

SEARCH · Search NASA

Results for “Data segmentation”

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 865 records · Page 48

High-dimensional Data-driven Energy optimization for Multi-Modal Transit Agencies (HD-EMMA) (Final Technical Report)

Public bus transit services in the U.S. are responsible for at least 19.7 million metric tons of CO 2 emission annually. Electric vehicles (EVs) can have a much lower environmental impact than comparable internal combustion engine vehicles (ICEVs), especially in urban areas. Unfortunately, EVs are also much more expensive than ICEVs. As a result, many public transit agencies can afford only mixed fleets of transit vehicles, consisting of EVs, hybrids (HEVs), and ICEVs. Transit agencies that operate such mixed fleets of vehicles face a challenging optimization problem: these agencies need to decide which vehicles are assigned to serving which transit trips. Since the advantage of EVs over ICEVs varies depending on the route and time of day (e.g., the benefit of EVs is higher in slower traffic with frequent stops and lower on highways), the assignment can have a significant effect on energy use and, hence, environmental impact. Through this project, we have developed reference data about energy collections and constructed a set of machine learning models that can accurately predict the energy consumption for the whole fleet at the level of each trip. We have used these models to develop a scheduling and assignment strategy that can rotate the different vehicle types across the transit agencies’ routes. The optimization algorithm ensures that the vehicles are matched to trips considering weather patterns, expected congestion, and road gradients to minimize the overall energy usage. We list the key observations from our project for other practitioners below. Details are available in the report, and the list of source code and our publications are included in the appendix. 1. We have demonstrated the feasibility of collecting, merging and analyzing large volumes of high-resolution real-world telemetry data from a mixed vehicle fleet. To mitigate the inherent noise of the recorded GPS points, the team developed an algorithm that filters data and maps the points onto a street. The algorithm considers previous and subsequent location measurements and different characteristics of nearby streets to determine how likely the vehicle travels on them. Then, the team segmented the time series into disjoint contiguous samples based on adjacent road segments and repeated the outlier detection and removal. For each data point, the team added features corresponding to elevation changes within the samples, weather features, such as temperature, and traffic data, such as speed ratio between actual speed and free-flow speed. 2. We have developed two forms of machine learning models that be used to understand and analyze the energy operations of a mixed vehicle transit fleet. The micro prediction model provides estimates of instantaneous energy prediction for all types of buses (diesel, hybrid, and electric). Such a model is important in evaluating the energy impacts of real-time bus operation strategies, but it is challenging due to diversified driving cycles of transit buses. The model can help the drivers understand the impact of their driving behaviors and short-term congestions. The macro prediction models estimate average energy consumption across the whole trip considering the features: distance traveled, various road-type features, elevation change, day of the week, time of day, various weather features (temperature, humidity, etc.), and traffic features (speed ratio and jam factor). 3. We have demonstrated that it is possible to transfer the machine learning models we have developed in this project to other teams and cities by using inductive transfer learning. We also showed that the performance of the macro energy prediction models can be improved using a multi-task learning approach where the learning parameters are shared between the models being developed for different vehicle types. The advantage of this approach is improved learning performance as the models can exploit common spatio-temporal and environmental characteristics. 4. Finally, we have developed trip and vehicle assignment and scheduling algorithms that use the energy prediction models and develop a trip to vehicle type (diesel, electric, hybrid) assignment for the whole operation to reduce overall emissions and cost. We have shown through simulations that the proposed algorithms can save $\$$ 48,910 in energy costs and 175 metric tons of CO 2 emission annually for CARTA.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Developing Novel Performance Measures for Traffic Congestion Management and Operational Planning Based on Connected Vehicle Data

In this study, the authors present their efforts in exploring a new type of traffic data, referred to as internet-connected vehicle (ICV) data, for traffic congestion management and operational planning. Most currently manufactured vehicles contain onboard GPS and cellular modules, and they constantly connect to automobile manufacturers' clouds via cellular networks and upload their status. Some automobile manufacturers have recently redistributed the nonpersonal part of such data, such as geolocation, to third-party organizations for innovative applications. Compared with the traditional vehicle GPS data, the ICV data contain high-resolution GPS waypoints accompanied with the vehicles' abnormal moving events (e.g., hard braking). The ICV data also have huge potential in congestion management and operational planning. They explore to identify and analyze traffic congestion on both freeways and arterials using the ICV data. The ICV data adopted for this research are redistributed by Wejo Data Service, representing 10%-15% of all moving vehicles in the Dallas-Fort Worth (DFW) area in Texas. Through one case study for a freeway segment and one for an arterial segment, new traffic performance metrics based on the characteristics of ICV data have been presented. The highlights of these efforts are as follows: (I) queue length and propagation at freeway bottlenecks can be directly measured based on where and when most internet-connected vehicles slow down and join the queue; (II) an internet-connected vehicle's actual delay time on arterials can be directly measured according to its slow movement percentage, without assuming the nondelay travel speed; and (III) the ICV data set are also combined with the high-resolution traffic signal events to generate a ground-truth time-space diagram (TSD) on arterials - a common visualization of arterial signal performance for transportation planning and operations.

33 ADVANCED PROPULSION SYSTEMS↗

System Would Keep Telescope Reflector Segments Aligned

Proposed actuation system maintains alignments of reflector segments of large telescope. Sensors measure positions and orientations of segments. Figure-control computer calculates orientation and figure of overall reflector surface from sensor data. Responding to computer output, servocontroller for each actuator corrects piston and tilt errors of each segment. Actuators adjust segments in response to sensed positions. Concept applicable to such large segmented space-based reflectors as those used in communication and in collection of solar energy.

Mettler, Edward↗

Multimodal Few-Shot Segmentation of Electron Micrographs

Scanning transmission electron microscopy (STEM) is one of the most used methods of analyzing the chemistry and composition of materials. By analyzing microstructures, these microscopes can help scientists better understand the molecular underpinnings of microelectronics, batteries, and more. However, STEM data can be difficult to interpret, so recent developments have been made in applications of machine learning to analyze these images. The PNNL-developed pyCHIP Classifier has achieved results in segmenting STEM these images via few-shot learning, a method which requires little data and human input, perfect for quickly analysis. In my internship I (Eli Meyers) investigated a multimodal improvement of this classifier by incorporating energy dispersive x-ray spectroscopy (EDS) data into the classification process for a more accurate segmentation. Furthermore, I encoded the spectral data by training a mass spectrometry encoder on the EDS data to extract a more meaningful representation of the data.

36 MATERIALS SCIENCE↗

Automated Characterization of Uranium-Molybdenum Fuel Microstructures

Currently, performance evaluators rely on visual inspection or manual segmentation to assess most parameters of interest within an irradiated microstructure. Automating this process has the potential to significantly speed up the data extraction process, enhance its reliability, and improve its correctness. Automatic image segmentation of target features is a critical tool for providing measurements of features that may be used to increase the fidelity of fuel performance modeling. This summary will present the progress made in developing and testing automated image processing routines capable of fully characterizing the presence of fission gas bubbles in irradiated U-Mo plate-type fuel microstructures.

Image Processing↗

Delineation of major geologic structures in Turkey using SIR-B data

Shuttle Imaging Radar-B (SIR-B) images of well mapped segments of major faults, such as the North Anatolian Fault (NAF) and East Anatolian Fault (EAF) will be studied to identify the prominent signatures that characterize the fault zones for those specific regions. The information will be used to delineate the unmapped fault zones in areas with similar geological and geomorphological properties. The data obtained from SIR-B images will be compared and correlated with the LANDSAT thematic mapper and seismicity alignments based on well constrained earthquake epicenters.

Toksoz, M. N.↗

Orchestration of materials science workflows for heterogeneous resources at large scale

In the era of big data, materials science workflows need to handle large-scale data distribution, storage, and computation. Any of these areas can become a performance bottleneck. We present a framework for analyzing internal material structures (e.g., cracks) to mitigate these bottlenecks. We demonstrate the effectiveness of our framework for a workflow performing synchrotron X-ray computed tomography reconstruction and segmentation of a silica-based structure. Our framework provides a cloud-based, cutting-edge solution to challenges such as growing intermediate and output data and heavy resource demands during image reconstruction and segmentation. Specifically, our framework efficiently manages data storage, scaling up compute resources on the cloud. The multi-layer software structure of our framework includes three layers. A top layer uses Jupyter notebooks and serves as the user interface. A middle layer uses Ansible for resource deployment and managing the execution environment. A low layer is dedicated to resource management and provides resource management and job scheduling on heterogeneous nodes (i.e., GPU and CPU). At the core of this layer, Kubernetes supports resource management, and Dask enables large-scale job scheduling for heterogeneous resources. The broader impact of our work is four-fold: through our framework, we hide the complexity of the cloud’s software stack to the user who otherwise is required to have expertise in cloud technologies; we manage job scheduling efficiently and in a scalable manner; we enable resource elasticity and workflow orchestration at a large scale; and we facilitate moving the study of nonporous structures, which has wide applications in engineering and scientific fields, to the cloud. While we demonstrate the capability of our framework for a specific materials science application, it can be adapted for other applications and domains because of its modular, multi-layer architecture.

97 MATHEMATICS AND COMPUTING↗

Using Landsat digital data to detect moisture stress

A technique utilizing transformed Landsat digital data for detection of agricultural drought was empirically defined during the 1976 South Dakota drought. During 1977, the procedure was expanded to the Great Plains for evaluation as a technique for detecting and monitoring vegetative water stress over large areas. The technique, Green Index Number (GIN), uses Landsat digital data from 5 by 6 nautical mile sampling frames (segments) to indicate when the vegetation within the segment is undergoing drought. At known growth stages for wheat, segments were classified as drought or non-drought areas. The remote-sensing-based information was compared to a weekly ground-based index (Crop Moisture Index) provided by the United States Department of Commerce. This comparison demonstrated a high degree of agreement between the 18-day remote sensing technique and the ground-based weekly data. Maps based on GIN of parts of the USSR and Australia were produced with a two-week lag and later compared with other crop assessments of crop conditions in these areas. These maps were judged to be in general agreement with the other data sources.

Thompson, D. R.↗

Active figure maintenance control using an optical truss laser metrology system for a space-based far-IR segmented telescope

A two-stage active control approach was developed addressing the figure control problem for a spaceborne FIR telescope, the Precision Segmented Reflectors Focus Moderate Mission Telescope (FMMT). The first active control stage aligns the optical segments based on images; attention is here given to the second stage, active figure maintenance control system, which maintains the alignment of the optical elements between initializations to hold the mirror figure steady while obtaining data and fixes translational and rotational changes of the optical segments induced by long-term thermal drifts of the support structure. Errors are expected to be 10-100 microns at the nodes of the primary backup structure over the course of an orbit. An rms performance of 0.8 microns of wavefront error can be expected during the maintenance function based on specified nominal sensor noises, actuator accuracies, and system environments. A performance of less than 0.3 microns rms can be expected, based on advanced components.

Lau, Kenneth↗

Fracture Toughness Evaluation for Spent Nuclear Fuel Clad Systems Using Spiral Notch Torsion Fracture Toughness Test

Many radioactive materials within the nuclear fuel cycle present a significant hazard. Such materials include spent nuclear fuel, high-level waste, legacy waste and other nuclear materials. These materials are often held in long-term storage as an interim stage within their lifecycle, including reuse or disposal. Safety and security of spent nuclear fuel (SNF) interim storage installations and follow-on SNF transportations to its final repository sites are very important, due to a great concentration of fission products, actinides and activation products. Fracture mechanics approach in applying to SNF system reliability investigation, especially for the high burn up (HBU) SNF, during SNF long term dry storage or SNF transportation is necessary due to the inherited flaws and inhomogeneity structures existed in a SNF system from the reactor operation. For instance, such as hydride and oxide formation, surface flaw induced by SNF assembly contact interactions, or internal flaws induced by pellet-clad mechanical interaction (PCMI). However, none of the existing fracture toughness data deal with fuel cladding specific geometry or SNF material conditions, such as cladding structure with the segment fuel pellets configuration and the PCMI mechanism. Consequently, the application of existing fracture toughness data to SNF system reliability investigation can be error prone; thus, the development of an industry-wide consensus fracture mechanics approach is needed. The objective of this research is to develop an in-situ fracture mechanics testing protocol, including the associated analytical procedure, that is suitable for evaluating the SNF fracture toughness. Fracture toughness data was obtained under quasi-static fracture loading using Oak Ridge National Laboratory (ORNL) developed Spiral Notch Torsion Test (SNTT) technology carried out on a biaxial tension/torsion tester. These data will be used to support SNF reliability investigation during long-tern SNF dry storage stage or in the follow-on SNF system transport to the final repository sites. SNTT has been a recent breakthrough in measuring fracture toughness for different materials, including metals, ceramics, concrete and polymers composites. Due to its high geometry constraint and unique loading condition, SNTT can be used to measure the fracture toughness with smaller specimens without concern of size effects. The application of SNTT to brittle materials has been proved to be successful. The micro-cracks induced by original notches in brittle materials could ensure crack growth in SNTT samples. Therefore, no fatigue pre cracks are needed for brittle materials specimens. The application of SNTT to the ductile material to generate valid toughness data will require a test sample with sufficient pre-crack length to increase the sample localized constraint at crack front. Fatigue pre-crack growth techniques with the associated compliance function estimated was developed for estimating the crack penetration depth to monitor the fatigue crack growth evolution. In order to extend SNTT approach to a thin shell cladding structure material, a new testing protocol and the associated analytical procedure for estimating the SNF fracture toughness was developed. The detailed SNTT approach and its estimated fracture toughness for the Zr-4 cladding structure with segment alumina inserts are presented in this report. The SNTT test results indicate that SNTT method is a reliable test approach with good repeatability in applying to Zr-4 cladding material. For the medium and the short crack length, the estimate J Q upon fracture for the baseline Zr-4 cladding is at 285.7 lb/in with 2-sigma uncertainty of 18.59 lb/in., and the associated K Q is at 61.4 Ksi√in. For a long crack length, the crack initialization orientation is apparently deviated from the principle tensile stress contour – 45° spiral crack front (i.e., Mode I + Mode III failure mechanism); and the estimated J Q is at 108 lb/in., the associated K Q is at 37.7 Ksi√in. The estimate Mode I J Q (along the 45° pitch principle tensile stress contour) is at 200 lb/in.; which indicate a significant reduction in the fracture toughness in a tubing structure under mixed mode loading condition, Mode I + Mode III, compared to that of Mode I (tensile stress dominated) alone.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

BOREAS HYD-4 Areal Snow Course Data

The Boreal Ecosystem-Atmosphere Study (BOREAS) Hydrology (HYD)-4 team focused on collecting data during the 1994 winter focused field campaign (FFCW) to improve the understanding of winter processes within the boreal forest. Knowledge of snow cover and its variability in the boreal forest is fundamental if BOREAS is to achieve its goals of understanding the processes and states involved in the exchange of energy and water. The development and validation of remote sensing algorithms will provide the means to extend the knowledge of these processes and states from the local to the regional scale. A specific thrust of the hydrology research is the development and validation of snow cover algorithms from airborne passive microwave measurements. Airborne remote sensing data (gamma, passive microwave) were acquired along a series of flight lines established in the vicinity of the BOREAS study areas. Ground snow surveys were conducted along selected sections of these aircraft flight lines. These calibration segments were typically 10-20 km in length, and ground data were collected at one to two kilometer intervals. The data are provided in tabular ASCII files. The HYD-04 areal snow course data are available from the Earth Observing System Data and Information System (EOSDIS) Oak Ridge National Laboratory (ORNL) Distributed Active Archive Center (DAAC). The data files are available on a CD-ROM (see document number 20010000884).

Hall, Forrest G.↗

Synthetic data-driven deep learning for label-free autonomous atomic force microscopy

Atomic force microscopy (AFM) is a widely used tool for nanoscale characterization across materials science, energy research, and biology. However, its adoption in high-throughput materials discovery and statistically driven studies remains limited by a strong dependence on expert operator input and by the scarcity of annotated experimental AFM datasets needed to enable data-driven automation. Here, we introduce SimuScan, a synthetic-data–driven framework that enables reliable AFM feature identification, segmentation, and targeted imaging without requiring large manually labeled experimental datasets. SimuScan generates tunable, high-fidelity synthetic AFM images of defined morphologies while incorporating realistic experimental artifacts, including tip–sample convolution, noise, flattening distortions, and surface debris. These datasets are shown to support scalable, label-free training of modern deep learning models for AFM analysis. When integrated into data-driven AFM workflows, SimuScan-trained models can locate and analyze nanoscale structures across large datasets and guide targeted follow-up imaging. We validate this approach on nanostructured surfaces, DNA assemblies, and bacterial cells, demonstrating robust generalization across diverse sample types with minimal operator intervention. More broadly, this work establishes a general strategy for generating explicitly conditioned, task-relevant synthetic data to improve the reliability of downstream models in autonomous microscopy.

Millan-Solsona, Ruben [Oak Ridge National Laborato↗

Eco-PiNN: A Physics-informed Neural Network for Eco-toll Estimation

The eco-toll estimation problem quantifies the expected environmental cost (e.g., energy consumption, exhaust emissions) for a vehicle to travel along a path. This problem is important for societal applications such as eco-routing, which aims to find paths with the lowest exhaust emissions or energy need. The challenges of this problem are threefold: (1) the dependence of a vehicle's eco-toll on its physical parameters; (2) the lack of access to data with eco-toll information; and (3) the influence of contextual information (i.e. the connections of adjacent segments in the path) on the eco-toll of road segments. Prior work on eco-toll estimation has mostly relied on pure data-driven approaches and has high estimation errors given the limited training data. To address these limitations, we propose a novel Eco-toll estimation Physics-informed Neural Network framework (Eco-PiNN) using three novel ideas, namely, (1) a physics-informed decoder that integrates the physical laws governing vehicle dynamics into the network, (2) an attention-based contextual information encoder, and (3) a physics-informed regularization to reduce overfitting. Experiments on real-world heavy-duty truck data show that the proposed method can greatly improve the accuracy of eco-toll estimation compared with state-of-the-art methods.

97 MATHEMATICS AND COMPUTING↗

The evolution of AAOE observed constituents with the polar vortex

One of the difficulties in determining constituent trends from the ER-2 flight data is the large amount of day to day variability generated by the motion of the polar vortex. To reduce this variability, the observations have been transformed into the conservative (Lagrangian) reference frames consisting of the coordinate pairs, potential temperature (PT) and potential vorticity (PV), or PT and N2O. The requirement of only two independent coordinates rests on the assumption that constituent distributions and their chemical processes are nearly zonal in that coordinate system. Flight data is used everywhere for these transformation except for potential vorticity. Potential vorticity is determined from level flight segments, and NMC PV values during flight dives and takeoffs are combined with flight data in a smooth fashion.

Schoeberl, Mark R.↗

Mars Terrain Segmentation with Less Labels

Planetary rover systems need to perform terrain segmentation to identify drivable areas as well as identify specific types of soil for sample collection. The latest Martian terrain segmentation methods rely on supervised learning which is very data hungry and difficult to train where only a small number of labeled samples are available. Moreover, the semantic classes are defined differently for different applications (e.g., rover traversal vs. geological) and as a result the network has to be trained from scratch each time, which is an inefficient use of resources. This research proposes a semi-supervised learning framework for Mars terrain segmentation where a deep segmentation network trained in an unsupervised manner on unlabeled images is transferred to the task of terrain segmentation trained on few labeled images. The network incorporates a backbone module which is trained using a contrastive loss function and an output atrous convolution module which is trained using a pixel-wise cross-entropy loss function. Evaluation results using the metric of segmentation accuracy show that the proposed method with contrastive pre-training outperforms plain supervised learning by 2%-10%. Moreover, the proposed model is able to achieve a segmentation accuracy of 91.1% using only 161 training images (1% of the original dataset) compared to 81.9% with plain supervised learning.

Wilson, Brian D↗

Onboard Autonomous Rock Shape Analysis for Mars Rovers

In the quest to maximize the scientific return of future robotic missions, it is imperative that our rovers be capable of determining the importance of the science they collect so that they may prioritize the acquisition and relay of that data. As an important step in this process, we present an automated technique to allow a rover to classify the shape and other geologic characteristics of rocks from two-dimensional photographic images and three-dimensional stereographically produced data. Experiments were conducted in the Matlab environment using images returned by JPL's Mars Pathfinder mission. Our method begins by first segmenting the rocks from the background using a combination of image intensity and height data. Various metrics are then used to classify the region's sphericity, roundness, and other geometric properties. Preliminary experiments to determine the most useful metrics were conducted by characterizing the two-dimensional rock shape while the three-dimensional shape was later studied with metrics derived from these two-dimensional techniques. Seven measures were developed and implemented. The performance of each measure was characterized by analyzing imagesfrom the Pathfinder mission and ranking the rocks according to the measured properties. Combined, the measures would provide a tool by which an automated rover could discover a greater amount of information about the data it collects, leading to a more productive mission.

image segmentation↗

Crop Identification Technology Assessment for Remote Sensing (CITARS)

The results of classifications and experiments performed for the Crop Identification Technology Assessment for Remote Sensing (CITARS) project are summarized. Fifteen data sets were classified using two analysis procedures. One procedure used class weights while the other assumed equal probabilities of occurrence for all classes. In addition, 20 data sets were classified using training statistics from another segment or date. The results of both the local and non-local classifications in terms of classification and proportion estimation are presented. Several additional experiments are described which were performed to provide additional understanding of the CITARS results. These experiments investigated alternative analysis procedures, training set selection and size, effects of multitemporal registration, the spectral discriminability of corn, soybeans, and other, and analysis of aircraft multispectral data.

Bauer, M. E.↗

Using porous random fields to predict the elastic modulus of unoxidized and oxidized superfine graphite

Nuclear graphite is a candidate material for Generation IV nuclear power plants. Porous materials such as graphite can contain complex networks of pores that influence the material's mechanical and irradiation response. A methodology known as the random finite element method (RFEM) was adapted to create synthetic microstructures and predict the influence of porosity on the elastic properties of graphite during oxidation. RFEM combines random field theory and the finite element method in a Monte Carlo framework to estimate the mechanical response of a given grade of graphite. In this research, the random fields were verified through experimental characterization to predict the elastic response of three nuclear graphite grades, ETU-10, IG-110, and 2114. Finite element models (FEM) were generated using segmentations of x-ray computed tomography (XCT) data known as image-based models (IBMs) to validate and compare with the RFEM results and better understand the effects of uniform oxidation in these graphite grades. The RFEM predictions appear to correlate well with the experimental values of the measured Young’s modulus of the three graphite grades and display the same trends as IBMs.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗