SEARCH · Search NASA
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.
Stochastic approximation theory to obtain algorithms for recovery of functions, using noisy measurements taken at randomly selected points
Comparative tests were performed on seven signature extension algorithms to evaluate their effectiveness in correcting for changes in atmospheric haze and sun angle in a Landsat scene. Four of the algorithms were cluster matching, and two were maximum likelihood algorithms. The seventh algorithm determined the haze level in both training and recognition segments and used a set of tables calculated from an atmospheric model to determine the affine transformation that corrects the training signatures for changes in sun angle and haze level. Three of the algorithms were tested on a simulated data set, and all of the algorithms were tested on consecutive-day data. The classification performance on the data sets using the algorithms is presented, along with results of statistical tests on the accuracy and proportion estimates. The three algorithms tested on the simulated data produced significant improvements over the results obtained using untransformed signatures. For the consecutive-day data, the tested algorithms produced improvements in most but not all cases. The tests indicated also that no statistically significant differences were noted among the algorithms.
We propose a new feature extraction method for neural networks. The method is based on the recently published decision boundary feature extraction algorithm. It has been shown that all the necessary features for classification can be extracted from the decision boundary. To apply the decision boundary feature extraction method, we first define the decision boundary in neural networks. Next, we propose a procedure for extracting all the necessary features for classification from the decision boundary. The proposed algorithm preserves the characteristics of neural networks, which can define arbitrary decision boundary. Experiments show promising results.
To monitor seasonal flooding within the tri-National Maya Forest the team completed the methodology started by the Summer 2021 term to analyze changes in inundation dynamic throughout 2017. The team analyzed inundation dynamics in Google Earth Engine (GEE) using Earth observation products from the Landsat 8 Operational Land Imager (OLI), Advanced Land Observing Satellite (ALOS) Phased Array type L-band Synthetic Aperture Radar (PALSAR) 2, and International Space Station (ISS) Global Ecosystem Dynamics Investigation LiDAR (GEDI). The team improved the landcover classification using the Random Forest algorithm in GEE by adding canopy height data derived from GEDI, elevation and slope data from Copernicus, and additional multi-spectral band ratios from Landsat 8. The pixel-based land cover classification produced an overall accuracy of 88%. Experiments measuring inundation extent using L-band SAR included comparing results with a priori knowledge, topography datasets, and auxiliary datasets. We iteratively tested and found threshold values for identifying forested inundation using the ratio for HH divided by HV. The resulting methodology and products helped end users from Belize’s Land Information Center (LIC) and Forest Department, Guatemala’s Center for Monitoring and Evaluation (CEMEC), and Mexico’s El Colegio de la Frontera Sur (ECOSUR) manage land and water resources and protect communities.
Hurricane Katrina inflicted widespread damage to vegetation in southwestern coastal Mississippi upon landfall on August 29, 2005. Storm damage to surface vegetation types at the NASA John C. Stennis Space Center (SSC) was mapped and quantified using IKONOS data originally acquired on September 2, 2005, and later obtained via a Department of Defense ClearView contract. NASA SSC management required an assessment of the hurricane s impact to the 125,000-acre buffer zone used to mitigate rocket engine testing noise and vibration impacts and to manage forestry and fire risk. This study employed ERDAS IMAGINE software to apply traditional classification techniques to the IKONOS data. Spectral signatures were collected from multiple ISODATA classifications of subset areas across the entire region and then appended to a master file representative of major targeted cover type conditions. The master file was subsequently used with the IKONOS data and with a maximum likelihood algorithm to produce a supervised classification later refined using GIS-based editing. The final results enabled mapped, quantitative areal estimates of hurricane-induced damage according to general surface cover type. The IKONOS classification accuracy was assessed using higher resolution aerial imagery and field survey data. In-situ data and GIS analysis indicate that the results compare well to FEMA maps of flooding extent. The IKONOS classification also mapped open areas with woody storm debris. The detection of such storm damage categories is potentially useful for government officials responsible for hurricane disaster mitigation.
This study applies fuzzy k-means (FKM) cluster analyses to a subset of the parameters reported in the CALIPSO lidar level 2 data products in order to classify the layers detected as either clouds or aerosols. The results obtained are used to assess the reliability of the cloud–aerosol discrimination (CAD) scores reported in the version 4.1 release of the CALIPSO data products. FKM is an unsupervised learning algorithm, whereas the CALIPSO operational CAD algorithm (COCA) takes a highly supervised approach. Despite these substantial computational and architectural differences, our statistical analyses show that the FKM classifications agree with the COCA classifications for more than 94 % of the cases in the troposphere. This high degree of similarity is achieved because the lidar-measured signatures of the majority of the clouds and the aerosols are naturally distinct, and hence objective methods can independently and effectively separate the two classes in most cases. Classification differences most often occur in complex scenes (e.g., evaporating water cloud filaments embedded in dense aerosol) or when observing diffuse features that occur only intermittently (e.g., volcanic ash in the tropical tropopause layer). The two methods examined in this study establish overall classification correctness boundaries due to their differing algorithm uncertainties. In addition to comparing the outputs from the two algorithms, analysis of sampling, data training, performance measurements, fuzzy linear discriminants, defuzzification, error propagation, and key parameters in feature type discrimination with the FKM method are further discussed in order to better understand the utility and limits of the application of clustering algorithms to space lidar measurements. In general, we find that both FKM and COCA classification uncertainties are only minimally affected by noise in the CALIPSO measurements, though both algorithms can be challenged by especially complex scenes containing mixtures of discrete layer types. Our analysis results show that attenuated backscatter and color ratio are the driving factors that separate water clouds from aerosols; backscatter intensity, depolarization, and mid-layer altitude are most useful in discriminating between aerosols and ice clouds; and the joint distribution of backscatter intensity and depolarization ratio is critically important for distinguishing ice clouds from water clouds.
The Pandora Software Development Kit and algorithm libraries perform reconstruction of neutrino interactions in liquid argon time projection chamber detectors. Pandora is the primary event reconstruction software used at the Deep Underground Neutrino Experiment, which will operate four large-scale liquid argon time projection chambers at the far detector site in South Dakota, producing high-resolution images of charged particles emerging from neutrino interactions. While these high-resolution images provide excellent opportunities for physics, the complex topologies require sophisticated pattern recognition capabilities to interpret signals from the detectors as physically meaningful objects that form the inputs to physics analyses. A critical component is the identification of the neutrino interaction vertex. Subsequent reconstruction algorithms use this location to identify the individual primary particles and ensure they each result in a separate reconstructed particle. A new vertex-finding procedure described in this article integrates a U-ResNet neural network performing hit-level classification into the multi-algorithm approach used by Pandora to identify the neutrino interaction vertex. The machine learning solution is seamlessly integrated into a chain of pattern-recognition algorithms. The technique substantially outperforms the previous BDT-based solution, with a more than 20% increase in the efficiency of sub-1 cm vertex reconstruction across all neutrino flavours.
We describe an integrated system, SkICAT (Sky Image Cataloging and Analysis Tool), for the automated reduction and analysis of the Palomar Observatory-ST ScI Digitized Sky Survey. The Survey will consist of the complete digitization of the photographic Second Palomar Observatory Sky Survey (POSS-II) in three bands, comprising nearly three Terabytes of pixel data. SkICAT applies a combination of existing packages, including FOCAS for basic image detection and measurement and SAS for database management, as well as custom software, to the task of managing this wealth of data. One of the most novel aspects of the system is its method of object classification. Using state-of-theart machine learning classification techniques (GID3* and O-BTree), we have developed a powerful method for automatically distinguishing point sources from non-point sources and artifacts, achieving comparably accurate discrimination a full magnitude fainter than in previous Schmidt plate surveys. The learning algorithms produce decision trees for classification by examining instances of objects classified by eye on both plate and higher quality CCD data. The same techniques will be applied to perform higher-level object classification (e.g., of galaxy morphology) in the near future. Another key feature of the system is the facility to integrate the catalogs from multiple plates (and portions thereof) to construct a single catalog of uniform calibration and quality down to the faintest limits of the survey. SkICAT also provides a variety of data analysis and exploration tools for the scientific utilization of the resulting catalogs. We include initial results of applying this system to measure the counts and distribution of galaxies in two bands down to Bj is approximately 21 mag over an approximate 70 square degree multi-plate field from POSS-II. SkICAT is constructed in a modular and general fashion and should be readily adaptable to other large-scale imaging surveys.
Compress and clean raw data file for permanent storage We have identified various error conditions/types and developed algorithms to get rid of these errors/noises, including the more complicated noise in the newer data sets. (status = 100% complete). Internet access of compacted raw data. It is now possible to access the raw data via our web site, http://www.jhuapl.edu/Aurora/index.html. The software to read and plot the compacted raw data is also available from the same web site. The users can now download the raw data, read, plot, or manipulate the data as they wish on their own computer. The users are able to access the cleaned data sets. Internet access of the color spectrograms. This task has also been completed. It is now possible to access the spectrograms from the web site mentioned above. Improve the particle precipitation region classification. The algorithm for doing this task has been developed and implemented. As a result, the accuracies improved. Now the web site routinely distributes the results of applying the new algorithm to the cleaned data set. Mark the classification region on the spectrograms. The software to mark the classification region in the spectrograms has been completed. This is also available from our web site.
We present an algorithm for detecting a specified set of targets for an Automatic Target Recognition (ATR) application. ATR involves processing images for detecting, classifying, and tracking targets embedded in a background scene. We address the problem of discriminating between targets and nontarget objects in a scene by evaluating 40x40 image blocks belonging to an image. Each image block is first projected onto a set of templates specifically designed to separate images of targets embedded in a typical background scene from those background images without targets. These filters are found using directed principal component analysis which maximally separates the two groups. The projected images are then clustered into one of n classes based on a minimum distance to a set of n cluster prototypes. These cluster prototypes have previously been identified using a modified clustering algorithm based on prior sensed data. Each projected image pattern is then fed into the associated cluster's trained neural network for classification. A detailed description of our algorithm will be given in this paper. We outline our methodology for designing the templates, describe our modified clustering algorithm, and provide details on the neural network classifiers. Evaluation of the overall algorithm demonstrates that our detection rates approach 96% with a false positive rate of less than 0.03%.
Cities have been expanding rapidly worldwide, especially over the past few decades. Mapping the dynamic expansion of impervious surface in both space and time is essential for an improved understanding of the urbanization process, land-cover and land-use change, and their impacts on the environment. Landsat and other medium-resolution satellites provide the necessary spatial details and temporal frequency for mapping impervious surface expansion over the past four decades. Since the US Geological Survey opened the historical record of the Landsat image archive for free access in 2008, the decades-old bottleneck of data limitation has gone. Remote-sensing scientists are now rich with data, and the challenge is how to make best use of this precious resource. In this article, we develop an efficient algorithm to map the continuous expansion of impervious surface using a time series of four decades of medium-resolution satellite images. The algorithm is based on a supervised classification of the time-series image stack using a decision tree. Each imerpervious class represents urbanization starting in a different image. The algorithm also allows us to remove inconsistent training samples because impervious expansion is not reversible during the study period. The objective is to extract a time series of complete and consistent impervious surface maps from a corresponding times series of images collected from multiple sensors, and with a minimal amount of image preprocessing effort. The approach was tested in the lower Yangtze River Delta region, one of the fastest urban growth areas in China. Results from nearly four decades of medium-resolution satellite data from the Landsat Multispectral Scanner (MSS), Thematic Mapper (TM), Enhanced Thematic Mapper plus (ETM+) and China-Brazil Earth Resources Satellite (CBERS) show a consistent urbanization process that is consistent with economic development plans and policies. The time-series impervious spatial extent maps derived from this study agree well with an existing urban extent polygon data set that was previously developed independently. The overall mapping accuracy was estimated at about 92.5% with 3% commission error and 12% omission error for the impervious type from all images regardless of image quality and initial spatial resolution.
The Hierarchical SEGmentation (HSEG) algorithm, which is a combination of hierarchical step-wise optimization and spectral clustering, has given good performances for hyperspectral image analysis. This technique produces at its output a hierarchical set of image segmentations. The automated selection of a single segmentation level is often necessary. We propose and investigate the use of automatically selected markers for this purpose. In this paper, a novel Marker-based HSEG (M-HSEG) method for spectral-spatial classification of hyperspectral images is proposed. First, pixelwise classification is performed and the most reliably classified pixels are selected as markers, with the corresponding class labels. Then, a novel constrained marker-based HSEG algorithm is applied, resulting in a spectral-spatial classification map. The experimental results show that the proposed approach yields accurate segmentation and classification maps, and thus is attractive for hyperspectral image analysis.
Tree cover delineation is a useful instrument in deriving Above Ground Biomass (AGB) density estimates from Very High Resolution (VHR) airborne imagery data. Numerous algorithms have been designed to address this problem, but most of them do not scale to these datasets, which are of the order of terabytes. In this paper, we present a semi-automated probabilistic framework for the segmentation and classification of 1-m National Agriculture Imagery Program (NAIP) for tree-cover delineation for the whole of Continental United States, using a High Performance Computing Architecture. Classification is performed using a multi-layer Feedforward Backpropagation Neural Network and segmentation is performed using a Statistical Region Merging algorithm. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on Conditional Random Field, which helps in capturing the higher order contextual dependencies between neighboring pixels. Once the final probability maps are generated, the framework is updated and re-trained by relabeling misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates. The tree cover maps were generated for the whole state of California, spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles. The framework produced true positive rates of around 88% for fragmented forests and 74% for urban tree cover areas, with false positive rates lower than 2% for both landscapes. Comparative studies with the National Land Cover Data (NLCD) algorithm and the LiDAR canopy height model (CHM) showed the effectiveness of our framework for generating accurate high-resolution tree-cover maps.
Properties such as the fractal dimension (FD) can be used for feature extraction and classification of regions within an image. The FD measures the degree of roughness of a surface, so this number is used to characterize a particular region, in order to differentiate it from another. There are two basic approaches discussed in the literature to measure FD: the blanket method, and the box counting method. Both attempt to measure FD by estimating the change in surface area with respect to the change in resolution. We tested both methods but box counting resulted computationally faster and gave better results. Differential Box Counting (DBC) was used to segment a collage containing three textures. The FD is independent of directionality and brightness so five features were used derived from the original image to account for directionality and gray level biases. FD can not be measured on a point, so we use a window that slides across the image giving values of FD to the pixel on the center of the window. Windowing blurs the boundaries of adjacent classes, so an edge-preserving, feature-smoothing algorithm is used to improve classification within segments and to make the boundaries sharper. Segmentation using DBC was 90.8910 accurate.
The Support Vector Machine is a powerful algorithm, useful in classifying data in to species. The Support Vector Machines implemented in this research were used as classifiers for the final stage in a Multistage Autonomous Target Recognition system. A single kernel SVM known as SVMlight, and a modified version known as a Support Vector Machine with K-Means Clustering were used. These SVM algorithms were tested as classifiers under varying conditions. Image noise levels varied, and the orientation of the targets changed. The classifiers were then optimized to demonstrate their maximum potential as classifiers. Results demonstrate the reliability of SMV as a method for classification. From trial to trial, SVM produces consistent results
A calibration of the ATLAS flavour-tagging algorithms using a new calibration procedure based on optimal transportation maps is presented. Simultaneous, continuous corrections to the b-jet, c-jet, and light-flavour jet classification probabilities from jet-tagging algorithms in simulation are derived for b-jets using $t\bar{t} \rightarrow e\mu \nu \nu bb$ data. After application of the derived calibration maps, closure between simulation and observation is achieved for jet flavour observables used in ATLAS analyses of Large Hadron Collider (LHC) Run 2 proton-proton collision data. This continuous calibration opens up new possibilities for the future use of jet flavour information in LHC analyses and also serves as a guide for deriving high-dimensional corrections to simulation via transportation maps, an important development for a broad range of inference tasks.
Laser powder bed fusion is a mainstream additive manufacturing technology widely used to manufacture complex parts in prominent sectors, including aerospace, biomedical, and automotive industries. However, during the printing process, the presence of an unstable vapor depression can lead to a type of defect called keyhole porosity, which is detrimental to the part quality. In this study, we developed an effective approach to locally detect the generation of keyhole pores during the printing process by leveraging machine learning and a suite of optical and acoustic sensors. Simultaneous synchrotron x-ray imaging allows the direct visualization of pore generation events inside the sample, offering high-fidelity ground truth. A neural network model adopting SqueezeNet architecture using single-sensor data was developed to evaluate the fidelity of each sensor for capturing keyhole pore generation events. Our comparative study shows that the near infrared images gave the highest prediction accuracy, followed by 100 kHz and 20 kHz microphones, and the photodiode sensitive to processing laser wavelength had the lowest accuracy. Using a single sensor, over 90% prediction accuracy can be achieved with a temporal resolution as short as 0.1 ms. A data fusion scheme was also developed with features extracted using SqueezeNet neural network architecture and classification using different machine learning algorithms. Our work demonstrates the correlation between the characteristic optical and acoustic emissions and the keyhole oscillation behavior, and thereby provides strong physics support for the machine learning approach.
The author has identified the following significant results. An objective technique was developed to measure the surface area of water bodies. Nineteen water bodies in the Houston and Galveston, Texas area were selected as a basis for the technique development. The actual surface area of each body was determined from rectified and enlarged NASA aircraft photography. A clustering algorithm was used to produce classification maps of the region from ERTS-1 data. Certain classes were identified as being 100% water. Other classes were identified as being mixtures of water with land or vegetation. The number of picture elements falling on each water body and its boundary were counted. A linear regression analysis was performed to relate the total number of picture elements and boundary elements counted to the actual surface area. The standard error of the estimate was 6.7 acres. The absolute error was not a function of the actual surface area of the water body.