Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “classification models”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
NASA NTRS1980

Development of an information data base for watershed monitoring

Landsat multispectral scanner data, Defense Mapping Agency digital terrain data, conventional maps, and ground data were integrated to create a comprehensive information data base (the Image Based Information System), to monitor the water quality of the Lake Tahoe Basin. Landsat imagery was used as the planimetric base to which all other data were registered. A georeference image plane, which provided an interface between all data planes for the Lake Tahoe Basin data base, was created from the drainage basin map. The data base was used to extract each drainage basin for separate display. The Defense Mapping Agency-created elevation image was processed with VICAR software to produce a component representing slope magnitude, which was cross-tabulated with the drainage basin georeference table. Future applications of the data base include the development of precipitation modeling, surface runoff models, and classification of drainage basin cover types.

Smith, A. Y.↗
NASA NTRS1989

KL techniques for optimal processing of time sequential imagery

Time-sequential imagery is difficult to analyze because of its high dimensionality. This paper advances a new algorithm that screens input data in an intelligent way, discards data with negligible information, and uses the remaining images to represent the sequence in an optimal compact form. Data are presented to illustrate how this algorithm can be used to do novelty filtering, novelty detection, segmentation, background independent modeling, and classification.

Vermeulen, Pieter↗
NASA NTRS1991

Gravitational lenses: The current sample, recent results, and continuing searches

Gravitational lensing is one of the topics in astrophysics that was quite extensively discussed over time before it was actually discovered. Ten years after the discovery of the first one, it is interesting to note how the field has developed. After an initial slow rate of discovery, the last few years have seen an explosion in the number of reported cases. Attention was drawn to the first few cases because quasars at the same red shift, with similar optical spectra, were observed with angular separations of only a few arc seconds. Most observational effort has been devoted to searching for new candidate lens systems and carefully measuring their properties, both to test whether they are indeed lensed and to provide constraints for modeling. A classification of the lenses is into rings, arcs, multiples, and doubles, where the progression is from sources close to the optical axis to far from the optical axis. The known candidate systems are listed. The searches for gravitational lenses are proving to be successful, and more lenses continue to be discovered serendipitously. Many searches are under way, along with instruments that will routinely increase the resolution of astronomical imaging.

Hewitt, Jacqueline N.↗
NASA NTRS1989

Experiment and simulation for CSI: What are the missing links?

Viewgraphs on experiment and simulation for control structure interaction (CSI) are presented. Topics covered include: control structure interaction; typical control/structure interaction system; CSI problem classification; actuator/sensor models; modeling uncertainty; noise models; real-time computations; and discrete versus continuous.

Belvin, W. Keith↗
NASA NTRS1995

ROSAT observation program

In this annual progress report (November 1, 1993 to October 31, 1994), the geminga pulsar was observed by the ROSAT PSPC for 37,000 s in September 1993, in order to make a more detailed study than was previously possible of the pulse profile and two-component spectrum, and to do phase-resolved spectroscopy. This exposure was 2.5 times longer than the original discovery observation. In addition, a shorter 4,000 s exposure was made in October 1992, simultaneously with a GRO observation of Geminga, in order to verify the absolute phasing of the X-ray and gamma-ray peaks. We verified that the spectrum can be described as the sum of two black bodies, whose temperatures are 6 x 10(exp 5) K and 3 - 4 x 10(exp 6) K, with the latter covering 3 x 10(exp -5) the area of the former. The pulse profiles indicate that the intensity of the two emitting regions peak is approximately 90 deg out of phase in rotation, but that the temperatures are otherwise independent of phase. An improved estimate of the distance can be made from the cooler (larger) blackbody component, yielding d = 440 +/- 120 pc. Another program of this report was to obtain PSPC spectra of an important class of Seyfert galaxies which have narrow lines and stron permitted Fe II emission. Sometines called I Zw 1 objects, or narrow-line Seyfert 1s, they are crucial to our understanding of Seyfert classification and models of Seyfert unification. We observed four new objects and, in addition, obtained data on 17 more from the ROSAT archive. A third program combined PSPC and HRI observations of selected Seyfert galaxies which have unusual and variable spectra. The purpose was to disentangle diffuse X-ray emission from the nuclear source, in order to properly interpret the soft X-ray spectral shapes in terms of partial covering and/or warm-absorber models. The targets of the program are NGC 3516, NGC 3227, and NGC 7314. So far, we have only performed a dtailed analysis on NGC 3516. The fourth program of this report is the NGC 1672, the second brightest Seyfert galaxy and one or the original 'composite' Seyfert/starburst galaxies which have evidence for both Seyfert activity and H II regions in their optical spectra. It is one of the lowest luminosity Seyfert 2 galaxies that can be studied in detail.

Halpern, Jules P.↗
NASA NTRS1995

Accurate estimation of sigma(exp 0) using AIRSAR data

During recent years signature analysis, classification, and modeling of Synthetic Aperture Radar (SAR) data as well as estimation of geophysical parameters from SAR data have received a great deal of interest. An important requirement for the quantitative use of SAR data is the accurate estimation of the backscattering coefficient sigma(exp 0). In terrain with relief variations radar signals are distorted due to the projection of the scene topography into the slant range-Doppler plane. The effect of these variations is to change the physical size of the scattering area, leading to errors in the radar backscatter values and incidence angle. For this reason the local incidence angle, derived from sensor position and Digital Elevation Model (DEM) data must always be considered. Especially in the airborne case, the antenna gain pattern can be an additional source of radiometric error, because the radar look angle is not known precisely as a result of the the aircraft motions and the local surface topography. Consequently, radiometric distortions due to the antenna gain pattern must also be corrected for each resolution cell, by taking into account aircraft displacements (position and attitude) and position of the backscatter element, defined by the DEM data. In this paper, a method to derive an accurate estimation of the backscattering coefficient using NASA/JPL AIRSAR data is presented. The results are evaluated in terms of geometric accuracy, radiometric variations of sigma(exp 0), and precision of the estimated forest biomass.

Holecz, Francesco↗
NASA NTRS2020

Lower Omo Food Security & Agriculture: Mapping Land Cover Change in Unprotected and Protected Areas in the Lower Omo River Valley, Ethiopia

Ethiopia is home to unique wildlife, biodiversity, and ecosystem services and, like much of the world, is undergoing population growth, development, and land use change. As a result, some biodiverse regions may be at risk of being urbanized, cultivated as agricultural plots, or losing access to water bodies that are essential for maintaining both terrestrial and aquatic life. The DEVELOP team partnered with the Ethiopian Wildlife Conservation Authority to quantify the land cover change between the years 1994, 2010, and 2018. The team utilized Ethiopia’s dry season (January to May) for training point development which was crucial in differentiating the level of greenness between the four land cover classes: water, natural vegetation, cultivated land, and bare ground. The study area covered 62,000 km2 of the Lower Omo River Valley and includes eight protected areas. Data from Landsat 5 Thematic Mapper, Landsat 7 Enhanced Thematic Mapper Plus, Landsat 8 Operational Land Imager, and Shuttle Radar Topography Mission were used to employ a Random Forest classifier and identify the four classes within Google Earth Engine. For each of the supervised classifications, overall model accuracy was between 83% (2018) and 89% (1994). Between 1994 and 2018, the Lower Omo Valley experienced an overall increase of 258% (919 km2) in water and 291% (7,188 km2) in cultivated areas, while experiencing a 9% (2,761 km2) decrease in natural vegetation and 19% (5,346 km2) bare ground. There was an increase in water and cultivated land and a decrease in natural vegetation and bare ground in unprotected areas and all protected areas. However, protected areas maintained natural vegetation better than unprotected areas and only experienced a 1% (59 km2) loss compared to a 10% (2,701 km2) loss in unprotected areas.

Food Security & Agriculture↗
NASA NTRS2020

Lower Omo Food Security & Agriculture: Mapping Land Cover Change in Unprotected and Protected Areas in the Lower Omo River Valley, Ethiopia

Ethiopia is home to unique wildlife, biodiversity, and ecosystem services and, like much of the world, is undergoing population growth, development, and land use change. As a result, some biodiverse regions may be at risk of being urbanized, cultivated as agricultural plots, or losing access to water bodies that are essential for maintaining both terrestrial and aquatic life. The DEVELOP team partnered with the Ethiopian Wildlife Conservation Authority to quantify the land cover change between the years 1994, 2010, and 2018. The team utilized Ethiopia’s dry season (January to May) for training point development which was crucial in differentiating the level of greenness between the four land cover classes: water, natural vegetation, cultivated land, and bare ground. The study area covered 62,000 sq.km of the Lower Omo River Valley and includes eight protected areas. We used Landsat 5 Thematic Mapper, Landsat 7 Enhanced Thematic Mapper Plus, Landsat 8 Operational Land Imager, and Shuttle Radar Topography Mission imagery within Google Earth Engine to employ a Random Forest Classifier and identify these four distinct classes. For each of our supervised classifications, overall model accuracy was between 83% (2018) and 89% (1994). Between 1994 and 2018, the Lower Omo Valley experienced an overall increase of 258.57% in water bodies and 291.23% in cultivated areas, while experiencing an 8.91% decrease in natural vegetation and 18.76% bare ground. There was an increase in water bodies and cultivated land and a decrease in natural vegetation and bare ground in unprotected areas and all protected areas. However, protected areas disproportionately experienced an increase in land cover change, including Tama Community Conservation Area which saw a 17,272.33% increase between 1994 and 2018.

Food Security & Agriculture↗
DOE OSTI2025

Multiclass Classification Using Bayesian Multivariate Adaptive Regression Splines

We present a new Bayesian model for the problem of multiclass classification. In this model, the probabilities of class membership of a given observation are determined by the mean of a latent Gaussian distribution. The mean functions of this latent distribution consist of combinations of highly flexible basis functions of the inputs: multivariate adaptive regression splines (MARS), first developed for multiple regression. We use reversible jump Markov chain Monte Carlo to make inference on the classification model, including the number of basis functions. We compare the probabilistic classification performance of our proposed approach to existing methods on simulated and benchmark data, and compare uncertainty estimates on simulated data. Our proposed method compares favorably with existing Bayesian and frequentist multiclass classification methods in out-of-sample probabilistic classification, and uncertainty estimation of these probabilistic classifications. We examine the fit of the proposed method to a data set of hurricane storm surge levels near Delaware Bay, US, and conclude that sea level rise is a key contributor to damage delivered by storm surge.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1984

Use of Landsat-derived profile features for spring small-grains classification

The present model for the temporal behavior of agricultural greenness is applied to the extraction of Landsat-derived profile features, distinguishing small from large grain crops. An additional feature derivable from the temporal behavior of the ratio of greenness to brightness is noted which aids in the separation of crops from other vegetation. A limited training set of 20 pure pixels/class, obtained from ground data, is subjected to the Ho-Kashyap (1965) linear classifier. The initial correct classification value for pure pixels of about 85 percent drops to 75 percent for all Landsat pixels.

Badhwar, G. D.↗
NASA NTRS1982

Use of Landsat-derived temporal profiles for corn-soybean feature extraction and classification

A physical model is presented, which has been derived from multitemporal-multispectral data acquired by Landsat satellites to describe the behavior and new features that are crop specific. A feasibility study over 40 sites was performed to classify the segment pixels into those of corn, soybeans, and others using the new features and a linear classifier. Results agree well with other existing methods, and it is shown the multitemporal-multispectral scanner data can be transformed into two parameters that are closely related to the target of interest and thus can be used in classification. The approach is less time intensive than other techniques and requires labeling of only pure pixels.

Badhwar, G. D.↗
DOE OSTI2021

CyBERT: Cybersecurity Claim Classification by Fine-Tuning the BERT Language Model

We introduce CyBERT, a cybersecurity feature claims classifier based on bidirectional encoder representations from transformers and a key component in our semi-automated cybersecurity vetting for industrial control systems (ICS). To train CyBERT, we created a corpus of labeled sequences from ICS device documentation collected across a wide range of vendors and devices. This corpus provides the foundation for fine-tuning BERT’s language model, including a prediction-guided relabeling process. We propose an approach to obtain optimal hyperparameters, including the learning rate, the number of dense layers, and their configuration, to increase the accuracy of our classifier. Fine-tuning all hyperparameters of the resulting model led to an increase in classification accuracy from 76% obtained with BertForSequenceClassification’s original architecture to 94.4% obtained with CyBERT. Furthermore, we evaluated CyBERT for the impact of randomness in the initialization, training, and data-sampling phases. CyBERT demonstrated a standard deviation of ±0.6% during validation across 100 random seed values. Finally, we also compared the performance of CyBERT to other well-established language models including GPT2, ULMFiT, and ELMo, as well as neural network models such as CNN, LSTM, and BiLSTM. The results showed that CyBERT outperforms these models on the validation accuracy and the F1 score, validating CyBERT’s robustness and accuracy as a cybersecurity feature claims classifier.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1991

Spatio-temporal contextual classification based on Markov random field model

A contextural classifier based on a Markov random field model, which can utilize both spatial and temporal contexts, is investigated. Spatial and temporal neighbors are defined, and the class assignment of each pixel is assumed to be dependent only on the measurement vectors of itself and those of its spatial and temporal neighbors according to the Markov random field property. Only interpixel class dependency context is used in the classification. The joint prior probability of the classes of each pixel and its spatial and temporal neighbors are modeled by a Gibbs random field. The classification is performed in a recursive manner. Experiments with multi-temporal Thematic Mapper data show promising results.

Jeon, Byeungwoo↗
DOE OSTI2020

Video Summarization Using Deep Action Recognition Features and Robust Principal Components Analysis

In an instance where desired pre-defined actions, behaviors, or other categories are known a priori, various video classification and recognition models can be trained to discover those classifications and their location within the video. Absent that information, one might still be tasked with identifying interesting portions within a video, a process which—if done manually—is onerous and time-consuming as it requires manual inspection of the video itself. Recognizing high-level interesting segments within a whole video has been a general area of interest due to the ubiquity of video data. However the size of the data makes storage, retrieval, and inspection of large collections of videos cumbersome. This problem motivates the task of generating shortened clips highlighting the primary content of a video, relieving the burden of having to watch the entire video. This paper presents an unsupervised method of creating shortened clips of videos, enabling the rapid review of the most interesting content within a video. Our method uses features extracted from pre-trained action recognition models as input to online moving window robust principal component analysis to generate summaries. The procedure is tested on a publicly available video summarization dataset and demonstrates comparable performance to state-of-the-art in an un-augmented setting while requiring no training.

Claborne, Daniel M.↗
DOE OSTI2024

Catalytic Resonance Theory: Forecasting the Flow of Programmable Catalytic Loops

Chemical transformations on catalyst surfaces occur through series and parallel reaction pathways. These complex networks and their behavior can be most simply evaluated through a three-species surface reaction loop (A* to B* to C* to A*) that is internal to the overall chemical reaction. Application of an oscillating dynamic catalyst to this reactive loop has been shown to exhibit one of three types of behavior: (1) a positive net flux of molecules about the loop in the clockwise direction, (2) a negative net flux of molecules about the loop in the counterclockwise direction, or (3) negligible flux of molecules about the loop at the limit cycle of reaction. Three-species surface loops were simulated with microkinetic modeling to assess the reaction loop behavior resulting from a catalytic surface oscillating between two or more catalyst surface energy states. Selected input parameters for the simulations spanned an 11-dimensional parameter space using 127 688 different parameter combinations. Their converged limit cycle solutions were analyzed for their loop turnover frequencies, the majority of which were found to be approximately zero. Classification and regression machine learning models were trained to predict the sign and magnitude of the loop turnover frequency and successfully performed above accessible baselines. Notably, the classification models exhibited a baseline weighted F1 score of 0.49, whereas trained models achieved weighted F1 scores of 0.94 and 0.96 when trained on the parameters used to define the simulations and derived rate constants, respectively. The trained models successfully predicted catalytic loop behavior, and interpretation of these models revealed all input parameters to be important for the prediction and performance of each model.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Machine Learning Correlation of Electron Micrographs and ToF-SIMS for the Analysis of Organic Biomarkers in Mudstone

The spatial distribution of organics in geological samples can be used to determine when and how these organics were incorporated into the host rock. Mass spectrometry (MS) imaging can rapidly collect a large amount of data, but ions produced are mixed without discrimination, resulting in complex mass spectra that can be difficult to interpret. Here, we apply unsupervised and supervised machine learning (ML) to help interpret spectra from time-of-flight-secondary ion mass spectrometry (ToF-SIMS) of an organic-carbon-rich mudstone of the Middle Jurassic of England (UK). It was previously shown that the presence of sterane molecular biomarkers in this sample can be detected via ToF-SIMS (Pasterski, M. J. et al., Astrobiology 2023, 23, 936). We use unsupervised ML on scanning electron microscopy–electron dispersive spectroscopy (SEM-EDS) measurements to define compositional categories based on differences in elemental abundances. We then test the ability of four ML algorithms─k-nearest neighbors (KNN), recursive partitioning and regressive trees (RPART), eXtreme gradient boost (XGBoost), and random forest (RF)─to classify the ToF-SIM spectra using (1) the categories assigned via SEM-EDS, (2) organic and inorganic labels assigned via SEM-EDS, and (3) the presence or absence of detectable steranes in ToF-SIMS spectra. In terms of predictive accuracy and balanced accuracy, KNN was the best performing model and RPART the worst. The feature importance, or the specific features of the ToF-SIM spectra used by the models to make classifications, cannot be determined for KNN, preventing posthoc model interpretation. Nevertheless, the feature importance extracted from the other models was useful for interpreting spectra. In conclusion, we determined that some of the organic ions used to classify biomarker containing spectra may be fragment ions derived from kerogen which is abundant in this mudstone sample.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Training dataset and results for geothermal exploration artificial intelligence, applied to Brady Hot Springs and Desert Peak

The submission includes the labeled datasets, as ESRI Grid files (.gri, .grd) used for training and classification results for our machine leaning model: - brady_som_output.gri, brady_som_output.grd, brady_som_output.* - desert_som_output.gri, desert_som_output.grd, desert_som_output.* The data corresponds to two sites: Brady Hot Springs and Desert Peak, both located near Fallon, NV. Input layers include: - Geothermal: Labeled data (0: Non-geothermal; 1: Geothermal) - Minerals: Hydrothermal mineral alterations, as a result of spectral analysis using Chalcedony, Kaolinite, Gypsum, Hematite and Epsomite - Temperature: Land surface temperature (% of times a pixel was classified as "Hot" by K-Means) - Faults: Fault density with a 300mradius - Subsidence: PSInSAR results showing subsidence displacement of more than 5mm - Uplift: PSInSAR results showing subsidence displacement of more than 5mm Also, the results of the classification using Brady and Desert Peak to build 2 Convolutional Neural Networks. These were applied to the training site as well as the other site, the results are in GeoTiff format. - brady_classification: Results of classification of the Brady-trained model - desert_classification: Results of classification of the Desert Peak-trained model - b2d_classification: Results of classification of Desert Peak using the Brady-trained model - d2b_classification: Results of classification of Brady using the Desert Peak-trained model

15 GEOTHERMAL ENERGY↗