SEARCH · Engineering Papers
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.
Conference paper for the ASME 2022 Turbomachinery Technical Conference & ExpositionJune 13-17, 2022, Rotterdam, The Netherlands<br>
Investigation of the accuracy attainable in automatic land use classification using 13 bands of multispectral data from the Skylab S-192 scanner. Classification to levels containing seven urban classes, five agricultural, and three water classes is shown to be achievable. With 17 classes, a classification accuracy of 72% was obtained. A wide spectral range, including the thermal band, appears to be most useful for distinguishing urban classes. Agricultural and water classes can be separated using spectral bands covering the visible to far IR.
Application of neural networks to classification of remote sensing data is discussed. Conventional two-layer backpropagation is found to give good results in classification of remote sensing data but is not efficient in training. A more efficient variant, based on conjugate-gradient optimization, is used for classification of multisource remote sensing and geographic data and very-high-dimensional data. The conjugate-gradient neural networks give excellent performance in classification of multisource data, but do not compare as well with statistical methods in classification of very-high-dimentional data.
Abstract—Phasor Measurement Units (PMUs) provide time synchronized measurements across the power grid, enabling data driven event detection and classification for enhanced system monitoring and situational awareness. However, variations in event duration, spatial extent, and severity, along with coincident events, pose challenges for conventional classification models that require fixed-size inputs. This paper presents a feature-based framework that aggregates diverse attributes from all available PMUs for each event into a fixed-length vector, facilitating the application of standard machine learning classifiers, including Random Forest, XGBoost, and Multilayer Perceptron. A probabilistic post-processing scheme is further introduced to enable multi-label classification in the presence of overlapping events. Experiments using real-world PMU data demonstrate that the Random Forest model achieves 95% accuracy, while the proposed post-processing method yields an additional 3% improvement.
At a global level extreme events have increased in both scale and impact. These events have the potential to affect the electrical grid infrastructure and cause a wide range of outages, which can lead to a disruption in daily patterns, cost millions of dollars and also the loss of life. Currently, to track these outage events there have been various approaches developed ranging from regional to national level quantifications for what defines an outage. However, this variation in methods can potentially lead to subjective decision-making and a lack of proper management in relation to the event. While previous work has made strides in determining spatio-temporal patterns, minimal attention has been given to the type and number of outages an area may be exposed to. The differences in incurred cost and the overall severity of an event between a transformer box malfunction and a hurricane are drastic, and by finding historical signals, we can allow for more efficient management, potentially saving lives and millions of dollars. Here, we leverage unsupervised machine learning techniques to delineate outage patterns among 22 counties within the United States and find that there are clear, segregated clusters (0.93 silhouette) of data which are related by event behavior and underlying cause. This finding will allow for energy stakeholders, policy makers, and researchers to gain a deeper understanding of the extent and severity of historic events and to better prepare for electrical grid infrastructure planning and management.
An automated procedure for the classification of transient contamination of stationary acoustic data is proposed and analyzed. The procedure requires the assumption that the stationary acoustic data of interest can be modeled as a band-limited, Gaussian random process. It also requires that the transient contamination be of higher variance than the acoustic data of interest. When these assumptions are satisfied, it is a blind separation procedure, aside from the initial input specifying how to subdivide the time series of interest. No a priori threshold criterion is required. Simulation results show that for a sufficient number of blocks, the method performs well, as long as the occasional false positive or false negative is acceptable. The effectiveness of the procedure is demonstrated with an application to experimental wind tunnel acoustic test data which are contaminated by hydrodynamic gusts.
An experiment of a factorial design was conducted to test the effects on classification accuracy of land cover types due to the improved spatial, spectral and radiometric characteristics of the Thematic Mapper (TM) in comparison to the Multispectral Scanner (MSS). High altitude aircraft scanner data from the Airborne Thematic Mapper instrument was acquired over central California in August, 1983 and used to simulate Thematic Mapper data as well as all combinations of the three characteristics for eight data sets in all. Results for the training sites (field center pixels) showed better classification accuracies for MSS spatial resolution, TM spectral bands and TM radiometry in order of importance.
An experiment of a factorial design was conducted to test the effects on classification accuracy of land cover types due to the improved spatial, spectral and radiometric characteristics of the LANDSAT Thematic Mapper (TM) in comparison to the Multispectral Scanner (MSS). High altitude aircraft scanner data from the Airborne Thematic Mapper instrument was used to simulate TM data as well as all combinations of the three characteristics for eight data sets in all. Results for the training sites (field-center pixels) show better classification accuracies for MSS spatial resolution, TM spectral bands and TM radiometry in order of importance.
There are no author-identified significant results in this report.
Explore the source record for details and available documents.
Variations in sun angle and haze level change the spectral signatures collected by multispectral scanners (MSS). This paper describes methods and computer programs that have been developed to simulate the effect of such variations and to correct for them. A basic program, Prediction of the Response of Earth Pointed Sensors (PREPS), is used to calculate the response of the sensor as a function of solar angle, atmospheric haze level, and target reflectance. It is then simply a matter of interpolating these results to simulate changes in haze level or solar angle. In principle, this can be done for any sensor, although at the present time it has been completed for only one - the ERTS-1 MSS.
There are no author-identified significant results in this report.
There are no author-identified significant results in this report.
There are no author-identified significant results in this report.
There are no author-identified significant results in this report.
There are no author-identified significant results in this report.
Both C- and L-band radar data acquired over a test site near Colby, Kansas during the summer of 1978 were used to identify three types of vegetation cover and bare soil. The effects of frequency, polarization, and the look angle on the overall accuracy of recognizing the four types of ground cover were analyzed. In addition, multidate data were used to study the improvement in recognition accuracy possible with the addition of temporal information. The soil moisture conditions had changed considerably during the temporal sequence of the data; hence, the effects of soil moisture on the ability to discriminate between cover types were also analyzed. The results provide useful information needed for selecting the parameters of a radar system for monitoring crops.
The techniques used initially for the identification of cultivated crops from Landsat imagery depended greatly on the iterpretation of film products by a human analyst. This approach was not very effective and objective. Since 1978, new methods for crop identification are being developed. Badhwar et al. (1982) showed that multitemporal-multispectral data could be reduced to a simple feature space of alpha and beta and that these features would separate corn and soybean very well. However, there are disadvantages related to the use of alpha and beta parameters. The present investigation is concerned with a suitable method for extracting the required features. Attention is given to a profile model for crop discrimination, corn-soybean separation using profile parameters, and an automatic labeling (target recognition) method. The developed technique is extended to obtain a procedure which makes it possible to estimate the crop proportion of corn and soybean from Landsat data early in the growing season.