Search NASA⌕ Search

SEARCH · Search NASA

Results for “data classification”

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 1,423 records · Page 79

Galaxy Morphology Classification Using Bayesian Neural Networks for LSST

Within the decade, many new ground and space-based observatories will become operational, generating massive amounts of data on short timescales. New surveys like Rubin Observatory's Legacy Survey of Space and Time (LSST) will be capable of observing objects with greater resolution than ever before, but processing and analyzing these datasets optimally will pose a significant challenge. In an effort to prepare for this, we explore how incorporating Deep Neural Networks can better support future data-intensive Astrophysics tasks such as galaxy morphology classification.

79 ASTRONOMY AND ASTROPHYSICS↗

Pushing automated morphological classifications to their limits with the Dark Energy Survey

ABSTRACT We present morphological classifications of ∼27 million galaxies from the Dark Energy Survey (DES) Data Release 1 (DR1) using a supervised deep learning algorithm. The classification scheme separates: (a) early-type galaxies (ETGs) from late-type galaxies (LTGs); and (b) face-on galaxies from edge-on. Our convolutional neural networks (CNNs) are trained on a small subset of DES objects with previously known classifications. These typically have mr ≲ 17.7 mag; we model fainter objects to mr < 21.5 mag by simulating what the brighter objects with well-determined classifications would look like if they were at higher redshifts. The CNNs reach 97 per cent accuracy to mr < 21.5 on their training sets, suggesting that they are able to recover features more accurately than the human eye. We then used the trained CNNs to classify the vast majority of the other DES images. The final catalogue comprises five independent CNN predictions for each classification scheme, helping to determine if the CNN predictions are robust or not. We obtain secure classifications for ∼87 per cent and 73 per cent of the catalogue for the ETG versus LTG and edge-on versus face-on models, respectively. Combining the two classifications (a) and (b) helps to increase the purity of the ETG sample and to identify edge-on lenticular galaxies (as ETGs with high ellipticity). Where a comparison is possible, our classifications correlate very well with Sérsic index (n), ellipticity (ϵ), and spectral type, even for the fainter galaxies. This is the largest multiband catalogue of automated galaxy morphologies to date.

79 ASTRONOMY AND ASTROPHYSICS↗

Southwest Pacific tropical cyclone development classification utilizing machine learning and synoptic composites

This study evaluates the ability of machine learning algorithms to classify tropical depressions (TDs) and tropical storms (TSs) in the western region of the southwest Pacific Ocean (SWPO). Decision rules are generated to predict the environment required for a depression to fully develop into a mature storm, and the most influential predictors in the classification decision are ranked. TD and TS are discriminated based on a maximum sustained wind speed threshold (≥17 ms -1 ). Various aerosol, thermodynamic, and dynamic parameters are extracted closest to the initiation point of each non-developing and developing sample. The covariates associated with each labelled sample are used to train a decision tree and random forest model. Results using a testing dataset suggest the random forest approach more accurately distinguishes between non-developing and developing samples. The classification accuracy of the decision tree and random forest are 72% and 91%, respectively. Random forest outperformed the decision tree by providing higher accuracy in test data. The most important variables for binary classification are sea salt aerosol optical depth (AOD), 1,000 mb relative humidity, and sea surface temperature. AOD is a quantitative estimate of the aerosols presents in the air through the extinction of a ray of light as it passes through the atmosphere. Mean composite maps constructed in an unsupervised manner have been created for the most important variables identified by the random forest classifier during TD and TS events to highlight the difference in geophysical and aerosol variables' climatology during the two different classifications. This work will advance the risk management strategies for northeastern Australia and other SWPO basin islands to control their tropical cyclone related losses through prioritizing forecasting variables that are the strongest predictors of the strengthening of tropical depressions into tropical cyclones.

54 ENVIRONMENTAL SCIENCES↗

The CHRS Data Portal, an easily accessible public repository for PERSIANN global satellite precipitation data

The Center for Hydrometeorology and Remote Sensing (CHRS) has created the CHRS Data Portal to facilitate easy access to the three open data licensed satellite-based precipitation datasets generated by our Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN) system: PERSIANN, PERSIANN-Cloud Classification System (CCS), and PERSIANN-Climate Data Record (CDR). These datasets have the potential for widespread use by various researchers, professionals including engineers, city planners, and so forth, as well as the community at large. Researchers at CHRS created the CHRS Data Portal with an emphasis on simplicity and the intention of fostering synergistic relationships with scientists and experts from around the world. The following paper presents an outline of the hosted datasets and features available on the CHRS Data Portal, an examination of the necessity of easily accessible public data, a comprehensive overview of the PERSIANN algorithms and datasets, and a walk-through of the procedure to access and obtain the data.

54 ENVIRONMENTAL SCIENCES↗

Fusion of Experiments and Simulations for Real-Time Identification of Pipeline Defects

In this study, we explored fusion of experiments and simulations for real time identification of pipeline defects across physical and non-physical domains. The challenges associated to data processing were addressed and a combined classification models was presented via CNN models. In addition, regression model based on XGBOOST is built to determine the defect location and defect dimension from data-driven features of guided wave signals captured by SMS fiber optic sensor.

deep learning↗

Additional studies of forest classification accuracy as influenced by multispectral scanner spatial resolution

First, an analysis of forest feature signatures was used to help explain the large variation in classification accuracy that can occur among individual forest features for any one case of spatial resolution and the inconsistent changes in classification accuracy that were demonstrated among features as spatial resolution was degraded. Second, the classification rejection threshold was varied in an effort to reduce the large proportion of unclassified resolution elements that previously appeared in the processing of coarse resolution data when a constant rejection threshold was used for all cases of spatial resolution. For the signature analysis, two-channel ellipse plots showing the feature signature distributions for several cases of spatial resolution indicated that the capability of signatures to correctly identify their respective features is dependent on the amount of statistical overlap among signatures. Reductions in signature variance that occur in data of degraded spatial resolution may not necessarily decrease the amount of statistical overlap among signatures having large variance and small mean separations. Features classified by such signatures may thus continue to have similar amounts of misclassified elements in coarser resolution data, and thus, not necessarily improve in classification accuracy.

Sadowski, F. E.↗

Fusion of Experiments and Simulations for Real-Time Identification of Pipeline Defects

In this study, we explored fusion of experiments and simulations for real time identification of pipeline defects across physical and non-physical domains. The challenges associated to data processing were addressed and a combined classification models was presented via CNN models. In addition, regression model based on XGBOOST is built to determine the defect location and defect dimension from data-driven features of guided wave signals captured by SMS fiber optic sensor.

deep learning↗

How reliable is distribution of relaxation times (DRT) analysis? A dual regression-classification perspective on DRT estimation, interpretation, and accuracy

The distribution of relaxation times (DRT) has gained increasing attention and adoption in recent years as a versatile method for analyzing electrochemical impedance spectroscopy (EIS) data obtained from complex devices like fuel cells, electrolyzers, and batteries. The DRT deconvolutes the impedance without a priori specification of a generative model, which is especially useful for interpretation and model selection when the governing principles of the system under study are not fully understood. However, DRT estimation is an ill-posed inversion problem that must be addressed with a subjective choice of regularization and tuning, which leaves substantial risk of misleading interpretations of EIS data. In this work, we suggest a new classification view of the DRT inversion to clarify DRT estimation and interpretation. We introduce a dual regression-classification framework that unifies the classification and regression views of the DRT inversion with wide-reaching implications for DRT analysis. The dual framework is employed to demonstrate a new kind of DRT inversion algorithm and develop novel evaluation metrics that capture previously ignored aspects of DRT accuracy. These approaches are applied to both synthetic data and experimental spectra collected from a protonic ceramic fuel cell and a lithium-ion battery to illustrate their broad utility. The dual inversion algorithm shows promising performance for accurate DRT estimation and autonomous model identification, while the dual evaluation approach produces metrics that meaningfully assess the strengths and risks of DRT algorithms. Here this work provides valuable insight for both practical application of the DRT to experimental data and further development of EIS analysis methods.

36 MATERIALS SCIENCE↗

A framework for implementing data services in multi-service mobile satellite systems

Mobile satellite systems being planned for introduction in the early 1990s are expected to be invariably of the multi-service type. Mobile Telephone Service (MTS), Mobile Radio Service (MRS), and Mobile Data Service (MDS) are the major classifications used to categorize the many user applications to be supported. The MTS and MRS services encompass circuit-switched voice communication applications, and may be efficiently implemented using a centralized Demand-Assigned Multiple Access (DAMA) scheme. Applications under the MDS category are, on the other hand, message-oriented and expected to vary widely in characteristics; from simplex mode short messaging applications to long duration, full-duplex interactive data communication and large file transfer applications. For some applications under this service category, the conventional circuit-based DAMA scheme may prove highly inefficient due to the long time required to set up and establish communication links relative to the actual message transmission time. It is proposed that by defining a set of basic bearer services to be supported in MDS and optimizing their transmission and access schemes independent of the MTS and MRS services, the MDS applications can be more efficiently integrated into the multi-service design of mobile satellite systems.

Ali, Mohammed O.↗

Pattern recognition of Landsat data based upon temporal trend analysis

The Delta Classifier defined as an agricultural crop classification scheme employing a temporal trend procedure is applied to more than 100 different Landsat data sets collected during the 1974-1975 growing season throughout the major wheat-producing regions of the United States. The classification approach stresses examination of temporal trends of the Landsat mean vectors of crops in the absence of corresponding ground truth information. It is shown that the resulting classifications compare favorably to ground truth estimates for wheat proportion in those cases where ground truth is available, and that the temporal trend procedure yields estimates of the wheat proportion that are comparable to the best results from maximum likelihood classification with photointerpreter-defined training fields.

Engvall, J. L.↗

OPEN-Augmented Reality GUI for Bioenergy Crop Phenotyping and Precision Agriculture (Donald Danforth Plant Science Center Final Scientific Technical Report)

The project led by the Donald Danforth Plant Science Center, in collaboration with Arizona State University, George Washington University, and Saint Louis University, has made significant strides in advancing the phenotypic analysis of bioenergy crops through the development of an innovative AI processing pipeline. This initiative was primarily funded by ARPA-E, with additional cost-sharing provided by the participating institutions. The project successfully utilized a variety of sensors—3D scanners, thermal, RGB, and hyperspectral—to refine algorithms for data-driven trait signature identification and improve the classification and visualization of plant traits. The developed AI processing pipeline is capable of handling the complex, multidimensional data characteristic of dynamic agricultural environments. 1) Contributions to understanding: The research has advanced the field of plant phenomics by showcasing the synergistic use of various sensor data to enhance the precision of trait analysis in bioenergy crops. Through the integration of 3D scanners, thermal, RGB, and hyperspectral sensors, the project has developed robust data-driven trait signature algorithms and visualization techniques. These innovations have facilitated detailed monitoring and management of plant traits, providing vital insights into plant growth dynamics and stress responses. Further, the project has broadened our understanding of how machine learning can be effectively applied in multi-sensor environments to refine trait analysis. By leveraging diverse datasets, the research has not only improved the accuracy of phenotypic assessments but also established a versatile methodological framework that can be extended beyond agriculture to other fields requiring detailed phenotypic analysis. 2) Technical effectiveness and economic feasibility: The AI processing pipeline developed in this project demonstrated significant technical effectiveness, achieving high throughput analysis of extensive phenotypic data and meeting targeted accuracies. This system exemplified the capability of advanced machine learning technologies to efficiently manage and analyze large, complex datasets. Economically, the implementation of the project-developed pipelines may offer substantial cost savings across multiple sectors. It enhances data analysis processes and significantly reduces the need for manual data interpretation, thereby decreasing both the time and resources required. 3) Public benefit: The project has significantly broadened the scope of agricultural methodologies to enhance phenotypic analysis, with potential applications in various sectors beyond agriculture. Additionally, the initiative fostered an enriching educational and collaborative environment, significantly enhancing the technical skills of participants. It also made substantial contributions to the scientific community by providing open-access data sets and tools, encouraging ongoing research and development across various disciplines. Overall, the project not only met its scientific goals but also showcased the extensive utility of integrating advanced machine learning and sensor data analysis technologies. These advancements have proven instrumental in driving forward both theoretical research and practical applications, setting a strong foundation for future explorations and innovations in data-driven science.

60 APPLIED LIFE SCIENCES↗

Symposium on Machine Processing of Remotely Sensed Data, Purdue University, West Lafayette, Ind., June 29-July 1, 1976, Proceedings

Papers are presented on the applicability of Landsat data to water management and control needs, IBIS, a geographic information system based on digital image processing and image raster datatype, and the Image Data Access Method (IDAM) for the Earth Resources Interactive Processing System. Attention is also given to the Prototype Classification and Mensuration System (PROCAMS) applied to agricultural data, the use of Landsat for water quality monitoring in North Carolina, and the analysis of geophysical remote sensing data using multivariate pattern recognition. The Illinois crop-acreage estimation experiment, the Pacific Northwest Resources Inventory Demonstration, and the effects of spatial misregistration on multispectral recognition are also considered. Individual items are announced in this issue.

Source record↗

Comparison of Land Cover Information from LANDSAT Multispectral Scanner (MSS) and Airborne Thematic Mapper Simulator (TMS) Data for Hydrologic Applications

Thematic mapper simulator (TMS) data produced a more accurate and spatially contiguous classification than MSS for the Clinton River Basin in Michigan. While the accuracy of the 4-band TMS data set was as good as the 7-band, the 3-band TMS data sets were also better than the MSS. The combination of bands selected based on the transformed divergence technique provided one band in each of the major regions of the spectrum: visible (band 3), near IR (band 4), middle IR (band 5) and thermal IR (band 7). These results should be viewed with some caution, since the data are from a TMS rather than the actual TM and the MSS data were obtained in early summer while the TMS was flown in late summer. The higher accuracies for the developed categories (residential and commercial) should improve the predictions of runoff in flood forecasting models and of flood damage for damage calculation models appreciably.

Gervin, J. C.↗

FY2018 Discovery Through Situational Awareness: Anomalies, Oscillations, and Classification

This technical report is a summary of work performed under the DOE GMLC program under the task titled “Discovery through Situational Awareness”. The focus of this work was to apply big data, statistical techniques to PMU data to do the following: 1) baseline PMU data and find anomalies with a focus on phase angle pairs, 2) identify the frequencies of dominant modal oscillations between different parts of a power system, and 3) identify and classify frequency events in PMU data. This work was performed on PMU data from the Western Interconnect. Many of these algorithms will be applied to wide area phase angle pair data on the Eastern Interconnect in a tool called ESAMS (Eastern Interconnect Situational Awareness Monitoring System). ESAMS was built by EPG (Electric Power Group) and PNNL and is currently being installed on the Eastern Interconnect. The results discussed in this report were made from 14 PMUs from data ranging from Oct 2016 to May 2018. The PMU data were measured 60 times each second. Fourteen phase angle pairs were included, with reactive and active power being calculated at 14 sites. All results have been de-identified for this report. The methodologies applied in the ESAMS tool are described in Section 2. A baseline of PMU data is created using the last 120 days of data. This baseline describes typical behavior as understood from the data. The baseline is then applied to the next day’s data and anomalies from that baseline are identified. Plots are created to help describe what is anomalous during that specific moment in time. These algorithms are currently being installed on the Eastern Interconnect. FY19 work will include discussing the results and findings from the ESAMS tool. A new method of identifying the frequencies of dominant modal oscillations between different parts of a power system is described in Section 3. A list of 199 frequency events provided by Bonneville Power Administration were used to create algorithms to detect frequency events and to create classification rules that can be used to identify future frequency events. Section 4 discusses the results the performance of 7 different event detection, clustering-based methods. Accuracy percentages ranged from 93.59% to 99.16%, with most methods being very fast. GBM (Gradient Boosting Machine) performed well and quickly. These 7 different methods were also tested to determine how well each built classification rules on training data and then applied those rules to identify future frequency events. Accuracy percentages ranged from 89.09% to 99.9%, with all methods performing quickly. GLM (General Linear Model) was viewed as the top performer when considering accuracy and processing time. Because the list of events consisted of 80% of them as active power events and only 20% as faults, all methods struggled to identify events as faults. Small faults were especially difficult to identify. A separate algorithm was created to help with this. Additional work will be done in FY19 on event detection using more data and more events and refinements to the methods.

24 POWER TRANSMISSION AND DISTRIBUTION↗

taxadb: A high‐performance local taxonomic database interface

Abstract A familiar and growing challenge in ecological and evolutionary research is that of establishing consistent taxonomy when combining data from separate sources. While this problem is already well understood and numerous naming authorities have been created to address the issue, most researchers lack a fast, consistent, and intuitive way to retrieve taxonomic names. We present taxadb R package which creates a local database, managed automatically from within R, to provide fast operations on millions of taxonomic names. taxadb provides access to established naming authorities to resolve synonyms, taxonomic identifiers, and hierarchical classification in a consistent and intuitive data format. taxadb makes operation on millions of taxonomic names fast and manageable.

Norman, Kari E. A.↗

Processing Of Multispectral Data For Identification Of Rocks

Linear discriminant analysis and supervised classification evaluated. Report discusses processing of multispectral remote-sensing imagery to identify kinds of sedimentary rocks by spectral signatures in geological and geographical contexts. Raw image data are spectra of picture elements in images of seven sedimentary rock units exposed on margin of Wind River Basin in Wyoming. Data acquired by Landsat Thematic Mapper (TM), Thermal Infrared Multispectral Scanner (TIMS), and NASA/JPL airborne synthetic-aperture radar (SAR).

Evans, Diane L.↗

A Study on the Comparison of International WTS for Integrated Management of Radioactive Waste - 19034

Domestic radioactive waste is generated by nuclear power plants, the Korea Atomic Energy Research Institute and KEPCO Nuclear Fuel Company. These nuclear energy agencies have their own waste tracking system. To track waste more efficiently, it is necessary to build an integrated tracking system from the viewpoint of the final disposer. As for the korea Atomic Energy Research Institute, the decommissioning waste due to the decommissioning of research reactors No. 1 and 2, and the low and intermediate-level radioactive waste, generated by the operation of the High Flux Advanced Neutron Application Reactor(HANARO), account for the most. The solid waste from each facility and laboratory is sorted and collected according to radiation levels and the contents. For starters, according to the contents, the waste is divided into combustible, noncombustible compressible and non-compressible waste. The combustible waste, generated by the Korea Atomic Energy Research Institute, is treated according to the low and intermediate-level radioactive waste delivery regulation of the Nuclear Safety and Security Commission and the acceptance criteria of the disposal facility. KEPCO Nuclear Fuel Company is making the nuclear fuel used in nuclear power plants. Radioactive waste is generated in the nuclear fuel manufacturing process, and it is classified into 8 types of waste according to the solid waste management procedure. Most of the radioactive waste, generated while KEPCO Nuclear Fuel Company processes the light-water reactor and heavy-water reactor nuclear fuel, is classified as low and intermediate-level radioactive waste. The radioactive liquid waste, generated in the radiation controlled area in nuclear fuel processing facilities, is divided into low-concentration liquid waste and high-concentration liquid waste. The miscellaneous solids, generated in the Hanbit NPP of Korea Hydro and Nuclear Power Co., Ltd., are classified in consideration of the physical properties, density and amount of the waste, and substances subject to restricted disposal. This paper investigated information on the structure, functions and maintenance of the systems implemented and operated by individual countries and IAEA, and the types of managed data, and analyzed the detailed configuration of the system and the characteristics of DBMS (Data Base Management System), and discovered during the analysis process the information on the waste management in each country or institution. This paper investigated the classification standards and treatment methods according to the characteristics of the radioactive substances handled by each agency. These classification and treatment methods can be applied to the database when the radioactive waste tracking system is implemented in the future. Also, this paper analyzed the radioactive waste tracking system of each country. Most overseas waste tracking systems are configured based on the ORACLE DBMS. The ORACLE DBMS is highly secure, and can manage large-scale databases. Also, Germany's ReVK and US IWTS are using the Bar-Code system that can track and manage all waste data, generated during decommissioning or transportation, in real time, and the real-time tracking system of web-based US CID can simply create and output reports quickly. If the advantages of overseas waste tracking systems are added to the domestic integrated waste tracking system, more efficient and safer management of radioactive waste will be possible.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Various forms of indexing HDMR for modelling multivariate classification problems

The Indexing HDMR method was recently developed for modelling multivariate interpolation problems. The method uses the Plain HDMR philosophy in partitioning the given multivariate data set into less variate data sets and then constructing an analytical structure through these partitioned data sets to represent the given multidimensional problem. Indexing HDMR makes HDMR be applicable to classification problems having real world data. Mostly, we do not know all possible class values in the domain of the given problem, that is, we have a non-orthogonal data structure. However, Plain HDMR needs an orthogonal data structure in the given problem to be modelled. In this sense, the main idea of this work is to offer various forms of Indexing HDMR to successfully model these real life classification problems. To test these different forms, several well-known multivariate classification problems given in UCI Machine Learning Repository were used and it was observed that the accuracy results lie between 80% and 95% which are very satisfactory.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗