Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed 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 1,783 records · Page 99

WE-G-207-05: Relationship Between CT Image Quality, Segmentation Performance, and Quantitative Image Feature Analysis

Purpose: Segmentation quality can affect quantitative image feature analysis. The objective of this study is to examine the relationship between computed tomography (CT) image quality, segmentation performance, and quantitative image feature analysis. Methods: A total of 90 pathology proven breast lesions in 87 dedicated breast CT images were considered. An iterative image reconstruction (IIR) algorithm was used to obtain CT images with different quality. With different combinations of 4 variables in the algorithm, this study obtained a total of 28 different qualities of CT images. Two imaging tasks/objectives were considered: 1) segmentation and 2) classification of the lesion as benign or malignant. Twenty-three image features were extracted after segmentation using a semi-automated algorithm and 5 of them were selected via a feature selection technique. Logistic regression was trained and tested using leave-one-out-cross-validation and its area under the ROC curve (AUC) was recorded. The standard deviation of a homogeneous portion and the gradient of a parenchymal portion of an example breast were used as an estimate of image noise and sharpness. The DICE coefficient was computed using a radiologist’s drawing on the lesion. Mean DICE and AUC were used as performance metrics for each of the 28 reconstructions. The relationship between segmentation and classification performance under different reconstructions were compared. Distributions (median, 95% confidence interval) of DICE and AUC for each reconstruction were also compared. Results: Moderate correlation (Pearson’s rho = 0.43, p-value = 0.02) between DICE and AUC values was found. However, the variation between DICE and AUC values for each reconstruction increased as the image sharpness increased. There was a combination of IIR parameters that resulted in the best segmentation with the worst classification performance. Conclusion: There are certain images that yield better segmentation or classification performance. The best segmentation Result does not necessarily lead to the best classification Result. This work has been supported in part by grants from the NIH R21-EB015053. R Nishikawa is receives royalties form Hologic, Inc.

60 APPLIED LIFE SCIENCES↗

Development of a Full-Scale Connected U-Net for Reflectivity Inpainting in Spaceborne Radar Blind Zones

CloudSat’s Cloud Profiling Radar is a valuable tool for remotely monitoring high-latitude snowfall, but its ability to observe hydrometeor activity near the Earth’s surface is limited by a radar blind zone caused by ground clutter contamination. This study presents the development of a deeply supervised U-Net-style convolutional neural network to predict cold season reflectivity profiles within the blind zone at two Arctic locations. The network learns to predict the presence and intensity of near-surface hydrometeors by coupling latent features encoded in blind zone-aloft clouds with additional context from collocated atmospheric state variables (i.e., temperature, specific humidity, and wind speed). Results show that the U-Net predictions outperform traditional linear extrapolation methods, with low mean absolute error, a 38% higher Sørensen–Dice coefficient, and vertical reflectivity distributions 60% closer to observed values. The U-Net is also able to detect the presence of near-surface cloud with a critical success index (CSI) of 72% and cases of shallow cumuliform snowfall and virga with 18% higher CSI values compared to linear methods. An explainability analysis shows that reflectivity information throughout the scene, especially at cloud edges and at the 1.2-km blind zone threshold, along with atmospheric state variables near the tropopause, are the most significant contributors to model skill. This surface-trained generative inpainting technique has the potential to enhance current and future remote sensing precipitation missions by providing a better understanding of the nonlinear relationship between blind zone reflectivity values and the surrounding atmospheric state.

54 ENVIRONMENTAL SCIENCES↗

From Images to Dark Matter: End-to-end Inference of Substructure from Hundreds of Strong Gravitational Lenses

Abstract Constraining the distribution of small-scale structure in our universe allows us to probe alternatives to the cold dark matter paradigm. Strong gravitational lensing offers a unique window into small dark matter halos (<10 10 M ⊙ ) because these halos impart a gravitational lensing signal even if they do not host luminous galaxies. We create large data sets of strong lensing images with realistic low-mass halos, Hubble Space Telescope (HST) observational effects, and galaxy light from HST’s COSMOS field. Using a simulation-based inference pipeline, we train a neural posterior estimator of the subhalo mass function (SHMF) and place constraints on populations of lenses generated using a separate set of galaxy sources. We find that by combining our network with a hierarchical inference framework, we can both reliably infer the SHMF across a variety of configurations and scale efficiently to populations with hundreds of lenses. By conducting precise inference on large and complex simulated data sets, our method lays a foundation for extracting dark matter constraints from the next generation of wide-field optical imaging surveys.

79 ASTRONOMY AND ASTROPHYSICS↗

Measurement of solar radiation at the Earth's surface

The characteristics of solar energy arriving at the surface of the Earth are defined and the history of solar measurements in the United States presented. Radiation and meteorological measurements being made at solar energy meteorological research and training sites and calibration procedures used there are outlined. Data illustrating the annual variation in daily solar radiation at Ann Arbor, Michigan and the diurnal variation in radiation at Albuquerque, New Mexico are presented. Direct normal solar radiation received at Albuquerque is contrasted with that received at Maynard, Massachusetts. Average measured global radiation for a period of one year for four locations under clear skies, 50% cloud cover, and 100% cloud cover is given and compared with the solar radiation at the top of the atmosphere. The May distribution of mean daily direct solar radiation and mean daily global solar radiation over the United States is presented. The effects of turbidity on the direct and circumsolar radiation are shown.

Bartman, F. L.↗

The Dark Energy Survey Supernova Programme: Modelling Selection Efficiency and Observed Core-collapse Supernova Contamination

The analysis of current and future cosmological surveys of Type Ia supernovae (SNe Ia) at high redshift depends on the accuratephotometric classification of the SN events detected. Generating realistic simulations of photometric SN surveys constitutes anessential step for training and testing photometric classification algorithms, and for correcting biases introduced by selectioneffects and contamination arising from core-collapse SNe in the photometric SN Ia samples. We use published SN time-seriesspectrophotometric templates, rates, luminosity functions, and empirical relationships between SNe and their host galaxies toconstruct a framework for simulating photometric SN surveys. We present this framework in the context of the Dark EnergySurvey (DES) 5-yr photometric SN sample, comparing our simulations of DES with the observed DES transient populations.We demonstrate excellent agreement in many distributions, including Hubble residuals, between our simulations and data.We estimate the core collapse fraction expected in the DES SN sample after selection requirements are applied and beforephotometric classification. After testing different modelling choices and astrophysical assumptions underlying our simulation,we find that the predicted contamination varies from 7.2 to 11.7 per cent, with an average of 8.8 per cent and an r.m.s. of 1.1 percent. Our simulations are the first to reproduce the observed photometric SN and host galaxy properties in high-redshift surveyswithout fine-tuning the input parameters. The simulation methods presented here will be a critical component of the cosmologyanalysis of the DES photometric SN Ia sample: correcting for biases arising from contamination, and evaluating the associatedsystematic uncertainty.

M Vincenzi↗

Transfer Learning Trained LSTM Models for Household Load Profile Forecasting

Grid edge renewable energy resources, such as rooftop solar photovoltaics, closely interact with consumer load profiles. Therefore, forecasting future electricity demand, ideally at the individual household level, is indispensable. In this paper, we present a transfer learning enhanced household load profile forecasting method. First, we tune a long short-term memory forecasting model to perform day-ahead prediction of household electricity load profiles. Then we improve these individualized models using transfer learning, and we use k-means clustering to create optimal source data sets. We find average improvements of 4.38% (largest improvement of 10.71%) when the entire data set was used to train the source model and 2.45% (largest improvement of 11.57%) in the mean absolute error when households were first clustered and used to train separate source models for each cluster. We find that transfer learning with clustered data can effectively boost the forecasting performance of the LSTM models. We use realistic household power measurements for 148 real residential households in Austin, Texas.

deep learning↗

Automated Integration of Continental-Scale Observations in Near-Real Time for Simulation and Analysis of Biosphere–Atmosphere Interactions

The National Ecological Observatory Network (NEON) is a continental-scale observatory with sites across the US collecting standardized ecological observations that will operate for multiple decades. To maximize the utility of NEON data, we envision edge computing systems that gather, calibrate, aggregate, and ingest measurements in an integrated fashion. Edge systems will employ machine learning methods to cross-calibrate, gap-fill and provision data in near-real time to the NEON Data Portal and to High Performance Computing (HPC) systems, running ensembles of Earth system models (ESMs) that assimilate the data. For the first time gridded EC data products and response functions promise to offset pervasive observational biases through evaluating, benchmarking, optimizing parameters, and training new machine learning parameterizations within ESMs all at the same model-grid scale. Leveraging open-source software for EC data analysis, we are already building software infrastructure for integration of near-real time data streams into the International Land Model Benchmarking (ILAMB) package for use by the wider research community. We will present a perspective on the design and integration of end-to-end infrastructure for data acquisition, edge computing, HPC simulation, analysis, and validation, where Artificial Intelligence (AI) approaches are used throughout the distributed workflow to improve accuracy and computational performance.

Durden, David J.↗

A large-scale evaluation of automated metadata inference approaches on sensors from air handling units

Building automation systems provide abundant sensor data to enable the potential of using data analytics to, among other things, improve the energy efficiency of the building. However, deployment of these applications for buildings, such as, fault detection and diagnosis (FDD) on multiple buildings remains a challenge due to the non-trivial efforts of organizing, managing and extracting metadata associated with sensors (e.g., information about their location, function, etc.), which is required by applications. One of the reasons leading to the problem is that varying conventions, acronyms, and standards are used to define this metadata. To better understand the nature of the problem, as well as the performance and scalability of existing solutions, in this report we implement and test 6 different time-series based metadata inference approaches on sensors from 614 air handling units (AHU) instrumented in 35 building sites accounting for more than 400 buildings distributed across United States of America. We infer 12 types of sensors and actuators in AHUs required by a rule-based FDD application: AHU performance and assessment rules (APAR). Our results show that: (1) the average performance of these approaches in terms of accuracy is similar across building sites, though there is significant variance; (2) the expected accuracy of classifying the type of points required by APAR for a new unseen building is, on average, 75%; (3) the performance of the model does not decrease as long as training data and testing data are extracted from adjacent months.

42 ENGINEERING↗

Automated defect identification in electroluminescence images of solar modules

Solar photovoltaic (PV) modules are susceptible to manufacturing defects, mishandling problems or extreme weather events that can limit energy production or cause early device failure. Trained professionals use electroluminescence (EL) images to identify defects in modules, however, field surveys or inline image acquisition can generate millions of EL images, which are infeasible to analyze by rote inspection. Here, we develop a rapid automatic computer vision pipeline (~0.5 seconds/module) to analyze EL images and identify defects including cracks, intra-cell defects, oxygen-induced defects, and solder disconnections. Defect identification is achieved with a machine learning model (Random Forest, ResNet models and YOLO) trained on 762 manually-labeled EL images of PV modules. We compare model performance on an imbalanced real-world validation set containing 134 EL images and determine that ResNet18 and YOLO are the optimal models; we next evaluated these models on a dedicated testing set (129 module images) with resulting macro F1 scores of 0.83 (ResNet18) and 0.78 (YOLO). Using a field EL survey of a PV power plant damaged in a vegetation fire, we analyze 18,954 EL images (2.4 million cells) and inspect the spatial distribution of defects on the solar modules. The results find increased frequency of ‘crack’, ‘solder’ and ‘intra-cell’ defects on the edges of the solar module closest to the ground after fire. We also find an abnormal increase of striation rings on cells which were assumed to be caused mainly in fabrication process. Our methods are published as open-source software. It can also be used to identify other kinds of defects or process different types of solar cells with minor modification on models by transfer learning.

14 SOLAR ENERGY↗

A Machine Learning Framework for Predicting Microphysical Properties of Ice Crystals From Cloud Particle Imagery

The microphysical properties of ice crystals are important because they significantly alter the radiative properties and spatiotemporal distributions of clouds, which in turn strongly affect Earth's climate. However, it is challenging to measure key properties of ice crystals, such as mass or morphological features. Here, we present a proof-of-concept framework for predicting three-dimensional (3D) microphysical properties of ice crystals from in situ two-dimensional (2D) imagery. First, we computationally generated synthetic ice crystals using 3D modeling software along with geometric parameters estimated from the 2021 Ice Cryo-Encapsulation Balloon (ICEBall) field campaign. Then, we used synthetic crystals to train machine learning (ML) models to predict effective density ($ρ_e$), effective surface area ($A_e$), and number of bullets ($N_b$) from synthetic rosette imagery. On unseen synthetic images, our ML models accurately predicted ice crystal properties. ResNet-18 performed best, achieving $R^2$ values of 0.99 and 0.98 for $ρ_e$ and $A_e$, respectively, and MAE of 0.10 for mathematical equation in single view tasks. Stereo view ResNet-18 further reduced RMSE by 40% for $ρ_e$ and $A_e$ and reduced MAE by 0.08 for $N_b$. This work provides a novel ML-driven framework for estimating ice microphysical properties from in situ imagery, which will allow for downstream constraints on microphysical parameterizations, such as the mass-size relationship.

Ko, J. [Columbia Univ., New York, NY (United State↗

The Significant Incidents and Close Calls in Human Space Flight Chart: Lessons Learned Gone Viral

This presentation will explore the surprising history and events that transformed a mundane spreadsheet of historical spaceflight incidents into a popular and widely distributed visual compendium of lessons learned. The Significant Incidents and Close Calls in Human Space Flight Chart (a.k.a. The Significant Incidents Chart) is a popular and visually captivating reference product that has arisen from the work of the Johnson Space Center (JSC) Safety and Mission Assurance (S&MA) Flight Safety Office (FSO). It began as an internal tool intended to increase our team s awareness of historical and modern space flight incidents. Today, the chart is widely recognized across the agency as a reference tool. It appears in several training and education programs. It is used in familiarization training in the JSC Building 9 Mockup Facility and is seen by hundreds of center visitors each week. The chart visually summarizes injuries, fatalities, and close calls sustained during the continuing development of human space flight. The poster-sized chart displays over 100 total events that have direct connections to human space flight endeavors. The chart is updated periodically. The update process itself has become a collaborative effort. Many people, spanning multiple NASA organizations, have provided suggestions for additional entries. The FSO maintains a growing list of subscribers who have requested to receive updates. The presenters will discuss the origins and motivations behind the significant incidents chart. A review of the inclusion criteria used to select events will be offered. We will address how the chart is used today by S&MA and offer a vision of how it might be used by other organizations now and in the future. Particular emphasis will be placed on features of the chart that have met with broad acceptance and have helped spread awareness of the most important lessons in human spaceflight.

Wood, Bill↗

Modeling the Swift Bat Trigger Algorithm with Machine Learning

To draw inferences about gamma-ray burst (GRB) source populations based on Swift observations, it is essential to understand the detection efficiency of the Swift burst alert telescope (BAT). This study considers the problem of modeling the Swift / BAT triggering algorithm for long GRBs, a computationally expensive procedure, and models it using machine learning algorithms. A large sample of simulated GRBs from Lien et al. is used to train various models: random forests, boosted decision trees (with AdaBoost), support vector machines, and artificial neural networks. The best models have accuracies of greater than or equal to 97 percent (less than or equal to 3 percent error), which is a significant improvement on a cut in GRB flux, which has an accuracy of 89.6 percent (10.4 percent error). These models are then used to measure the detection efficiency of Swift as a function of redshift z, which is used to perform Bayesian parameter estimation on the GRB rate distribution. We find a local GRB rate density of n (sub 0) approaching 0.48 (sup plus 0.41) (sub minus 0.23) per cubic gigaparsecs per year with power-law indices of n (sub 1) approaching 1.7 (sup plus 0.6) (sub minus 0.5) and n (sub 2) approaching minus 5.9 (sup plus 5.7) (sub minus 0.1) for GRBs above and below a break point of z (redshift) (sub 1) approaching 6.8 (sup plus 2.8) (sub minus 3.2). This methodology is able to improve upon earlier studies by more accurately modeling Swift detection and using this for fully Bayesian model fitting.

gamma-ray burst: general – gamma-rays: general â↗

Large-Scale Solar Panel Mapping from Aerial Images Using Deep Convolutional Networks

Up-to-date maps of installed solar photovoltaic panels are a critical input for policy and financial assessment of solar distributed generation. However, such maps for large areas are not available. With high coverage and low cost, aerial images enable large-scale mapping, bit it is highly difficult to automatically identify solar panels from images, which are small objects with varying appearances dispersed in complex scenes. We introduce a new approach based on deep convolutional networks, which effectively learns to delineate solar panels in aerial scenes. The approach has successfully mapped solar panels in imagery covering 200 square kilometers in two cities, using only 12 square kilometers of training data that are manually labeled.

Yuan, Jiangye↗

The Advanced Technology Operations System: ATOS

Mission control systems supporting new space missions face ever-increasing requirements in terms of functionality, performance, reliability and efficiency. Modern data processing technology is providing the means to meet these requirements in new systems under development. During the past few years the European Space Operations Centre (ESOC) of the European Space Agency (ESA) has carried out a number of projects to demonstrate the feasibility of using advanced software technology, in particular, knowledge based systems, to support mission operations. A number of advances must be achieved before these techniques can be moved towards operational use in future missions, namely, integration of the applications into a single system framework and generalization of the applications so that they are mission independent. In order to achieve this goal, ESA initiated the Advanced Technology Operations System (ATOS) program, which will develop the infrastructure to support advanced software technology in mission operations, and provide applications modules to initially support: Mission Preparation, Mission Planning, Computer Assisted Operations, and Advanced Training. The first phase of the ATOS program is tasked with the goal of designing and prototyping the necessary system infrastructure to support the rest of the program. The major components of the ATOS architecture is presented. This architecture relies on the concept of a Mission Information Base (MIB) as the repository for all information and knowledge which will be used by the advanced application modules in future mission control systems. The MIB is being designed to exploit the latest in database and knowledge representation technology in an open and distributed system. In conclusion the technological and implementation challenges expected to be encountered, as well as the future plans and time scale of the project, are presented.

Kaufeler, J.-F.↗

Modelling above-ground biomass stock over Norway using national forest inventory data with ArcticDEM and Sentinel-2 data

Boreal forests constitute a large portion of the global forest area, yet they are undersampled through field surveys, and only a few remotely sensed data sources provide structural information wall-to-wall throughout the boreal domain. ArcticDEM is a collection of high-resolution (2 m) space-borne stereogrammetric digital surface models (DSM) covering the entire land area north of 60° of latitude. The free-availability of ArcticDEM data offers new possibilities for aboveground biomass mapping (AGB) across boreal forests, and thus it is necessary to evaluate the potential for these data to map AGB over alternative open-data sources (i.e., Sentinel-2). This study was performed over the entire land area of Norway north of 60° of latitude, and the Norwegian national forest inventory (NFI) was used as a source of field data composed of accurately geolocated field plots (n=7710) systematically distributed across the study area. Separate random forest models were fitted using NFI data, and corresponding remotely sensed data consisting of either: i) a canopy height model (ArcticCHM) obtained by subtracting a high-quality digital terrain model (DTM) from the ArcticDEM DSM height values, ii) Sentinel-2 (S2), or iii) a combination of the two (ArcticCHM+S2). Furthermore, we assessed the effect of the forest- and terrain-specific factors on the models’ predictive accuracy. The best model (,i.e., ArcticCHM+S2) explained nearly 60% of the variance of the training set, which translated in the largest accuracy in terms of root mean square error (RMSE=41.4 t/ha). This result highlights the synergy between 3D and multispectral data in AGB modelling. Furthermore, this study showed that despite the importance of ArcticCHM variables, the S2 model performed slightly better than ArcticCHM model. This finding highlights some of the limitations of ArcticDEM, which, despite the unprecedented spatial resolution, is highly heterogeneous due to the blending of multiple acquisitions across different years and seasons. We found that both forest- and terrain-specific characteristics affected the uncertainty of the ArcticCHM+S2 model and concluded that the combined use of ArcticCHM and Sentinel-2 represents a viable solution for AGB mapping across boreal forests. The synergy between the two data sources allowed for a reduction of the saturation effects typical of multispectral data while ensuring the spatial consistency in the output predictions due to the removal of artifacts and data voids present in ArcticCHM data. While the main contribution of this study is to provide the first evidence of the best-case-scenario (i.e., availability of accurate terrain models) that ArcticDEM data can provide for large-scale AGB modelling, it remains critically important for other studies to investigate how ArcticDEM may be used in areas where no DTMs are available as is the case for large portions of the boreal zone.

space-borne imagery↗

star Miner: A suit of classifiers for spatial, temporal, ancillary, and remote sensing data mining

Thematic classification of multi-spectral remotely sensed imagery for large geographic regions requires complex algorithms and feature selection techniques. Traditional statistical classifiers rely exclusively on spectral characteristics, but thematic classes are often spectrally overlapping. The spectral response distributions of thematic classes are dependent on many factors including terrain, slope, aspect, soil type, and atmospheric conditions present during the image acquisition. With the availability of geo-spatial databases, it is possible to exploit the knowledge derived from these ancillary geo-spatial databases to improve the classification accuracies. However, it is not easy to incorporate this additional knowledge into traditional statistical classification methods. On the other hand, knowledge-based and neural network classifiers can readily incorporate these spatial databases, but these systems are often complex to train and their accuracy is only slightly better than statistical classifiers. In this paper we present a new suit of classifiers developed through NASA funding, which addresses many of these problems and provide a framework for mining multi-spectral and temporal remote sensing images guided by geo-spatial databases.

54 ENVIRONMENTAL SCIENCES↗

star Miner: A suit of classifiers for spatial, temporal, ancillary, and remote sensing data mining

Thematic classification of multi-spectral remotely sensed imagery for large geographic regions requires complex algorithms and feature selection techniques. Traditional statistical classifiers rely exclusively on spectral characteristics, but thematic classes are often spectrally overlapping. The spectral response distributions of thematic classes are dependent on many factors including terrain, slope, aspect, soil type, and atmospheric conditions present during the image acquisition. With the availability of geo-spatial databases, it is possible to exploit the knowledge derived from these ancillary geo-spatial databases to improve the classification accuracies. However, it is not easy to incorporate this additional knowledge into traditional statistical classification methods. On the other hand, knowledge-based and neural network classifiers can readily incorporate these spatial databases, but these systems are often complex to train and their accuracy is only slightly better than statistical classifiers. In this paper we present a new suit of classifiers developed through NASA funding, which addresses many of these problems and provide a framework for mining multi-spectral and temporal remote sensing images guided by geo-spatial databases.

54 ENVIRONMENTAL SCIENCES↗

Simulation-Based Parameter Optimization Framework for Large-Scale Hybrid Smart Grid Communications Systems Design

The design of reliable, dynamic, fault-tolerant hybrid smart grid communication networks is a challenge to achieve for autonomous power grids. Hybrid networks use different communications technologies for different area networks. A simulation-based parameter optimization framework is proposed to tune parameters of hybrid communication technologies to achieve the optimal network performance. It consists of three main components: a parallel executor used to speedup a list of simulations; a sampler running simulations using the parallel executor at each generation; and a hybrid stochastic optimization algorithm for tuning configurable parameters of hybrid designs and applications. The proposed hybrid metaheuristic optimization algorithm combines an evolutionary algorithm with a gradient method to quickly achieve an approximately global optimum solution. Three optimization test functions are employed to train the adjustable parameters of the hybrid algorithm. Results show the proposed parameter optimization framework can help the designer choose the right hybrid architecture with an optimal parameter set for a large-scale broadband PLC-WiMAX hybrid smart grid communication network.

24 POWER TRANSMISSION AND DISTRIBUTION↗