SEARCH · Engineering Papers

Results for “Image 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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,009 records · Page 56

All sources NASA NTRS DOE OSTI

NASA NTRS2018

NASA NeMO-Net

We present preliminary results from NASA NeMO-Net, the first neural multi-modal observation and training network for global coral reef assessment. NeMO-Net is an open-source deep convolutional neural network (CNN) and interactive active learning training software in development which will assess the present and past dynamics of coral reef ecosystems. NeMO-Net exploits active learning and data fusion of mm-scale remotely sensed 3D images of coral reefs captured using fluid lensing with the NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as hyperspectral airborne remote sensing data from the ongoing NASA CORAL mission and lower-resolution satellite data to determine coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. Aquatic ecosystems, particularly coral reefs, remain quantitatively misrepresented by low- resolution remote sensing as a result of refractive distortion from ocean waves, optical attenuation, and remoteness. Machine learning classification of coral reefs using FluidCam mm-scale 3D data show that present satellite and airborne remote sensing techniques poorly characterize coral reef percent living cover, morphology type, and species breakdown at the mm, cm, and meter scales. Indeed, current global assessments of coral reef cover and morphology classification based on km-scale satellite data alone can suffer from segmentation errors greater than 40%, capable of change detection only on yearly temporal scales and decameter spatial scales, significantly hindering our understanding of patterns and processes in marine biodiversity at a time when these ecosystems are experiencing unprecedented anthropogenic pressures, ocean acidification, and sea surface temperature rise. NeMO-Net leverages our augmented machine learning algorithm that demonstrates data fusion of regional FluidCam (mm, cm-scale) airborne remote sensing with global low-resolution (m, km-scale) airborne and spaceborne imagery to reduce classification errors up to 80% over regional scales. Such technologies can substantially enhance our ability to assess coral reef ecosystems dynamics.

NASA↗

NASA NTRS2019

Predictive Modeling for Differential Diagnosis and Mortality Risk Assessment

The prevalence of electronic health record (EHR) systems has brought prodigious biomedical informatics opportunity. Automated machine learning methods can effectively utilize such data and have become common tools for healthcare predictive modeling. Researches in medical informatics have explored the potential of deep learning and classical models in emergent care scenarios. In particular, predicting differential diagnoses for admissions have proven useful in decreasing unnecessary lab tests and improving inpatient triage decision-making. Moreover, identification of high-risk patients for in-hospital mortality is vitally important to maximize allocation of medical resources.The Medical Information Mart for Intensive Care (MIMIC-III) database, containing de-identified critical care inpatient was used in our study. This data set captures hospital patient laboratory measurements, pharmacologic prescriptions, diagnostic data and procedure event recordings. When considering adult patients and discounting admissions with ICU length of stay less than 24 hours, there were 37,787 unique admissions and 30,414 total patients. We examined the top 25 most prevalent ICD-9 group-level disease specificities in MIMIC-III using a multi-label classification model. In-hospital mortality was modeled as binary classification with 4,155 (13%) adult patients that expired, of which 3,138 (75.5%) were in the ICU setting. The metrics AUC, F1 score, sensitivity and specificity values calculated for each disease label measured prediction performance.The usage of ICD-9 group codes reduced feature dimension from 14,567 to 942 and greatly improved distribution of patient diagnostic categories. Disease temporal patterns were captured by considering the most frequently sampled 6 vital signs and 13 laboratory values. Missing data were imputed at each time-stamp. Time-series raw hourly average values were converted into 5 summary features (mean, standard deviation, number of observations, min & max values). Patient demographic variables such as age, gender, marital status and ethnicity were also factored into the modeling. Choi et al showed that contextual embedding of medical data, diagnostic and procedural codes alone can predict future diagnoses with sensitivity as high as 0.79. We utilized an embedding technique called word2vec which allowed sparse representations of medical history to be transformed into dense word vectors. The mappings captured contextual information by treating each admission as a sentence and learning the most likely neighboring words in a sliding window fashion. Binary and multi-label classification was achieved via collapse models, which do not consider temporal information, as well as recurrent neural networks with regularization, Softmax output layer activation together with categorical cross-entropy as the loss function.

US Army collaboration↗

NASA NTRS2022

Mapping invasive alien species in grassland ecosystems using airborne imaging spectroscopy and remotely observable vegetation functional traits

Lespedeza cuneata (sericea lespedeza; hereafter “sericea”) is an invasive species brought to the U.S. from East Asia in the 1890s to be used as forage. However, it has now become a growing ecological and economic threat in grasslands of several states in the U.S. southern Great Plains including Oklahoma, Kansas, Missouri, and Nebraska. Here, we demonstrate the capability of airborne imaging spectroscopy to map sericea in a large natural grassland within the Tallgrass Prairie Preserve, the largest protected tallgrass prairie in the world, located in northeastern Oklahoma. Through this research, we investigated which remotely observable vegetation functional traits (referring to biochemical, physiological, and structural traits) contribute to distinguishing sericea from cooccurring native species and whether we can detect sericea remotely through quantifying these functional traits using imaging spectroscopic data (also known as hyperspectral data). To achieve these objectives, full-range airborne hyperspectral data with spatial resolution of 1 m were collected from the study area in August 2020. In addition, a total of 12 vegetation functional traits were measured through field sampling for model development. We first identified functional traits that contributed to separating sericea from other species, and then used them in a classification model to detect sericea in our study site. We found total carotenoids (sum of neoxanthin, violaxanthin, antheraxanthin, zeaxanthin, and lutein), chlorophyll a + b (sum of chlorophyll a and chlorophyll b), total nitrogen, canopy height, potassium, and magnesium as the main functional traits contributing to the detection of sericea; an overall classification accuracy of approximately 94% was reported. However, the proposed approach overestimated sericea cover in species-rich plant communities. Overall, our findings demonstrated an essential role for airborne remote sensing in 1) direct mapping of invasive plants and 2) quantifying functional traits associated with success strategies of invasive species. Eventually, experiments like ours can aid in developing large-scale and science-driven management practices to both identify the current extent, and to control the spread of invasive species in grasslands and similar short-stature environments. This will not only improve management practices but will have major societal and economic benefits.

Hamed Gholizadeh↗

NASA NTRS1973

Effective use of ERTS multisensor data in the Great Plains

The author has identified the following significant results. In the case of rangelands, manipulation of the digitized material from photographic recordings revealed that the mode-seeking program using only one vegetation group gave the best output map. Efficient mapping of this imagery will possibly require the use of narrow band filters. In the case of cropland, the results obtained with the K-class classifier are shown. Using one feature, the highest percent correct classification was obtained using band 6. Using two features, best results were obtained using bands 4 and 6 and 5 and 6. Specific results obtained with various bands are discussed. In the case of land systems, the eroded shale soils located along the Missouri River reservoirs in South Dakota above the Fort Randall and Big Bend Dams are clearly visible on the IR bands of ERTS scene 17 August, 1972, image description number 1025-16551. The appearance of various types of soil formations is described.

Myers, V. I.↗

NASA NTRS1974

Application of ecological, geological and oceanographic ERTS-1 imagery to Delaware's coastal resources management

The author has identified the following significant results. Data from twelve successful ERTS-1 passes over Delaware Bay have been analyzed with special emphasis on coastal vegetation, land use, current circulation, water turbidity and pollution dispersion. Secchi depth, suspended sediment concentration and transmissivity as measured from helicopters and boats were correlated with ERTS-1 image radiance. Multispectral signatures of acid disposal plumes, sediment plumes and slick were investigated. Ten vegetative cover and water discrimination classes were selected for mapping: (1) forest-land; (2) Phragmites communis; (3) Spartina patens and Distichlis spicata; (4) Spartina alterniflora; (5) cropland; (6) plowed cropland; (7) sand and bare sandy soil; (8) bare mud; (9) deep water; and (10) sediment-laden and shallow water. Canonical analysis predicted good classification accuracies for most categories. The actual classification accuracies were very close to the predicted values with 8 of 10 categories classified with greater than 90% accuracy indicating that representative training sets had been selected.

Klemas, V.↗

NASA NTRS1976

Interdisciplinary applications and interpretations of EREP data within the Susquehanna River Basin

The author has identified the following significant results. Photography from the S190A and S190B sensors was compared, for terrain analysis. The S190B photographs were used for terrain mapping of three test areas selected as being representative of major physiographic regions in Pennsylvania. Skylab photography was superior to both LANDSAT imagery and high altitude aircraft photography for purposes of accurate location of lineaments. Analysis of Skylab imagery has shown that long lineaments originally plotted on LANDSAT images are actually made up of shorter segments. Correlation of lineaments with ore deposits was determined following the preparation of a Pennsylvania mineral deposit map. Digital wave number analysis (spatial filtering) was attempted to determine if it can be used to enhance certain subtle features, and in particular, to locate and verify lineaments. Various spectral bands and channels of the MSS digital data were evaluated for their value in the classification and thematic mapping.

Mcmurtry, G. J.↗

NASA NTRS1994

Amazon Rain Forest Classification Using J-ERS-1 SAR Data

The Amazon rain forest is a region of the earth that is undergoing rapid change. Man-made disturbance, such as clear cutting for agriculture or mining, is altering the rain forest ecosystem. For many parts of the rain forest, seasonal changes from the wet to the dry season are also significant. Changes in the seasonal cycle of flooding and draining can cause significant alterations in the forest ecosystem.Because much of the Amazon basin is regularly covered by thick clouds, optical and infrared coverage from the LANDSAT and SPOT satellites is sporadic. Imaging radar offers a much better potential for regular monitoring of changes in this region. In particular, the J-ERS-1 satellite carries an L-band HH SAR system, which via an on-board tape recorder, can collect data from almost anywhere on the globe at any time of year.In this paper, we show how J-ERS-1 radar images can be used to accurately classify different forest types (i.e., forest, hill forest, flooded forest), disturbed areas such as clear cuts and urban areas, and river courses in the Amazon basin. J-ERS-1 data has also shown significant differences between the dry and wet season, indicating a strong potential for monitoring seasonal change. The algorithm used to classify J-ERS-1 data is a standard maximum-likelihood classifier, using the radar image local mean and standard deviation of texture as input. Rivers and clear cuts are detected using edge detection and region-growing algorithms. Since this classifier is intended to operate successfully on data taken over the entire Amazon, several options are available to enable the user to modify the algorithm to suit a particular image.

J-ERS-1↗

NASA NTRS2018

NeMO-Net & Fluid Lensing: The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment Using Fluid Lensing Augmentation of NASA EOS Data

We present preliminary results from NASA NeMO-Net, the first neural multi-modal observation and training network for global coral reef assessment. NeMO-Net is an open-source deep convolutional neural network (CNN) and interactive active learning training software in development which will assess the present and past dynamics of coral reef ecosystems. NeMO-Net exploits active learning and data fusion of mm-scale remotely sensed 3D images of coral reefs captured using fluid lensing with the NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as hyperspectral airborne remote sensing data from the ongoing NASA CORAL mission and lower-resolution satellite data to determine coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. Aquatic ecosystems, particularly coral reefs, remain quantitatively misrepresented by low-resolution remote sensing as a result of refractive distortion from ocean waves, optical attenuation, and remoteness. Machine learning classification of coral reefs using FluidCam mm-scale 3D data show that present satellite and airborne remote sensing techniques poorly characterize coral reef percent living cover, morphology type, and species breakdown at the mm, cm, and meter scales. Indeed, current global assessments of coral reef cover and morphology classification based on km-scale satellite data alone can suffer from segmentation errors greater than 40%, capable of change detection only on yearly temporal scales and decameter spatial scales, significantly hindering our understanding of patterns and processes in marine biodiversity at a time when these ecosystems are experiencing unprecedented anthropogenic pressures, ocean acidification, and sea surface temperature rise. NeMO-Net leverages our augmented machine learning algorithm that demonstrates data fusion of regional FluidCam (mm, cm-scale) airborne remote sensing with global low-resolution (m, km-scale) airborne and spaceborne imagery to reduce classification errors up to 80% over regional scales. Such technologies can substantially enhance our ability to assess coral reef ecosystems dynamics.

satellite data↗

NASA NTRS2024

Jefferson County Ecological Conservation: Quantifying the Effects of Hydrologic Restoration in the Camas National Wildlife Refuge and Mud Lake Wildlife Management Area

Wetlands in the Camas National Wildlife Refuge and Mud Lake Wildlife Management Area, a rare landscape feature in the Intermountain West, are crucial for migratory birds along the Pacific Flyway, yet these wetlands have experienced a noticeable decline in extent and inundation over the last 40+ years. Partners at the U.S. Fish and Wildlife Service and Idaho Department of Fish and Game have ongoing restoration efforts that are yet to be quantified. To assist these partners, we used NASA Earth observations to quantify change in wetland extent and determine if the restoration projects met the intended impact. The QA_PIXEL band from Landsat 5 Thematic Mapper (TM) and Landsat 8 Operational Land Imager (OLI) was used to identify water. Landsat 8 OLI imagery was also used for classifying landcover in ArcGIS Pro for 2016 and 2020 and to forecast landcover in 2060 using TerrSet’s Land Change Modeler. We also compared lidar data from 2011 and 2019 to detect changes in vegetation height, ground elevation, and surface water levels, and Sentinel-2 Multispectral Instrument (MSI) imagery to detect changes in vegetation health. Classification results indicated overall accuracies over 84% and Kappa indices above 0.80, well surpassing random classification performance. From 2016 to 2020 our classifications showed an 825 acre increase in wetland extent, and our forecasted 2060 model showed a 2795 acre decrease. Combining our partners’ knowledge of the area with our analyses, we created a remote sensing workflow to enhance future monitoring and decision-making. This study demonstrated the feasibility of NASA Earth observations in quantifying wetlands, informing restoration projects, and supporting avian conservation.

Cassidy Bromka↗

NASA NTRS1980

Composite model of a 3-D image

This paper presents a composite model of a moving (3-D) image especially useful for the sequential image processing and encoding. A non-linear predictor based on the composite model is described. The performance of this predictor is used as a measure of the validity of the model for a real image source. The minimization of a total mean square prediction error provides an inequality which determines a condition for the profitable use of the composite model and can serve as a decision device for the selection of the number of subsources within the model. The paper also describes statistical properties of the prediction error and contains results of computer simulation of two non-linear predictors in the case of perfect classification between subsources.

Dukhovich, I. J.↗

NASA NTRSDate not supplied

Application of Support Vector Regression to Derive Crater Depth/Diameter From Satellite Images

Through the study of impact crater shapes, one can draw important conclusions about the nature and evolution of planetary surfaces [e.g., 1-4].In particular, studying the depth (d) to diameter (D)ratio (d/D) of a population of impact craters, in combination with crater count statistics, can yield valuable insights regarding rates of erosion and burial[5]. Motivated by the great abundance of available planetary surface image data, the goal of this project is to develop an efficient way to estimate d/D from satellite images of impact craters for which stereo information is not available [6]. We set out to develop and train a machine learning algorithm to extract d/D from a dataset of synthetic impact crater images for which model d/D is known. The applications of machine learning to planetary science are numerous and diverse [7], including automatic planetary surface mapping [8] and the detection of impact craters [9]. Our algorithm makes use of Support Vector Regression (SVR), which is a type of Support Vector Machine (SVM) [10, 11].SVMs are a branch of supervised machine learning valued for their straightforward implementation and versatility in solving both classification and regression problems. In regression analysis, an SVR algorithm produces a hyperplane function to fit the training data points, as well as an ε-tube that surrounds the hyperplane. Tunable hyperparameters include the width of the ε-tube (ε) and the amount an algorithm is penalized for points which fall outside the ε-tube.

L R Chin↗

NASA NTRS1973

Land Use and Mapping

From the standpoint of technology, the most encouraging thing about ERTS has been the level of land-use identification. Land-use detail has exceeded the expectations of the Interagency Steering Committee and the requirements of land-use classification proposed by the Department of Interior. Whereas in the latter instance it was anticipated that only nine classes of land use would probably be identifiable, in fact some 14 to 18 classes have been identified. The success in the level of land-use identification results primarily from the various attributes of the ERTS system. These include the ability to provide repetitive coverage, and in particular seasonal coverage; the ability to image in four bands of the electromagnetic spectrum (green, red, and two near-infrared), which allows for manipulation of various combinations of bands; and the provision by the ERTS system of computer-compatible tapes for machine processing of data. Furthermore, the resolution of ERTS imagery has been better than expected. Although there is some question as to its exact resolving power, it is safe to say objects as small as 100 meters (300 feet) in diameter have been identified. Linear features as narrow as 16 meters (50 feet) can be detected (Figure 1).

Lindgren, D. T.↗

NASA NTRS1978

Sensor needs for agricultural applications

The peculiarities of agricultural remotely sensed data requirements evoke special sensor requirements. Vegetative species do not possess significantly different spectral signature at given phases of their development cycle. Hence, the key to their discriminability is the phasing of the phenologic cycle of the subject species. Significant improvements in classification can be obtained by consistently employing multi-temporal observations taken at specific times during the year. The present approach to agricultural data processing results in extracted data equal to approximately .05% of the acquired data. This paper discusses the derivation of agricultural peculiar requirements and the benefits to the end-to-end processing system by judicial utilization and placement of key editing functions such as sample segment extraction, cloudy image removal, sample registration and the elimination of redundant data.

Golden, H.↗

NASA NTRS1984

Investigation of SIR-B images for lithologic mapping

It is immediately apparent from the examination of almost any synthetic aperture radar (SAR) data that the radar return is primarily a function of the topographic relief. Yet radar reflectance is dependent on both surface roughness and the dielectric constant of the surface material. These two parameters can in many cases be related to lithologic units. Thus, if the first-order terrain effects due to topographic relief could (in essence) be removed from the radar image, the SAR data might well be used for lithologic discrimination. Such an approach is evaluated. Landsat Thematic Mapper data along with ground truth are used to define training cells that characterize the various lithologic units in the area. By aggregating the radar data for these cells, curves of radar reflectance versus local incidence are estimated. The curves are then used to classify the test area. The results are compared with lithologic classification based upon multi-spectral (visible and infrared) data.

Parr, J. T.↗

NASA NTRS2015

Analyses of Magnetic Resonance Imaging of Cerebrospinal Fluid Dynamics Pre and Post Short and Long-Duration Space Flights

Preliminary results are based on analyses of data from 17 crewmembers. The initial analysis compares pre to post-flight changes in total cerebral blood flow (CBF) and craniospinal CSF flow volume. Total CBF is obtained by summation of the mean flow rates through the 4 blood vessels supplying the brain (right and left internal carotid and vertebral arteries). Volumetric flow rates were obtained using an automated lumen segmentation technique shown to have 3-4-fold improved reproducibility and accuracy over manual lumen segmentation (6). Two cohorts, 5 short-duration and 8 long-duration crewmembers, who were scanned within 3 to 8 days post landing were included (4 short-duration crewmembers with MRI scans occurring beyond 10 days post flight were excluded). The VIIP Clinical Practice Guideline (CPG) classification is being used initially as a measure for VIIP syndrome severity. Median CPG scores of the short and long-duration cohorts were similar, 2. Mean preflight total CBF for the short and long-duration cohorts were similar, 863+/-144 and 747+/-119 mL/min, respectively. Percentage CBF changes for all short duration crewmembers were 11% or lower, within the range of normal physiological fluctuations in healthy individuals. In contrast, in 4 of the 8 long-duration crewmembers, the change in CBF exceeded the range of normal physiological fluctuation. In 3 of the 4 subjects an increase in CBF was measured. Large pre to post-flight changes in the craniospinal CSF flow volume were found in 6 of the 8 long-duration crewmembers. Box-Whisker plots of the CPG and the percent CBF and CSF flow changes for the two cohorts are shown in Figure 4. Examples of CSF flow waveforms for a short and two long-duration (CPG 0 and 3) are shown in Figure 5. Changes in CBF and CSF flow dynamics larger than normal physiological fluctuations were observed in the long-duration crewmembers. Changes in CSF flow were more pronounced than changes in CBF. Decreased CSF flow dynamics were observed in a subject with VIIP signs. Study limitations include a slightly longer landing-to-MRI scan period for the short-duration cohort and limited sensitivity of the subjective discrete ordinal CPG scale. This limitation can be overcome by using imaging based parametric measures of VIIP severity such as globe deformation measures.

Alperin, Noam↗

NASA NTRS2020

Mangrove Mapping With the Freeman-Durden Polarimetric Decomposition and InSAR Coherence From ALOS-2

We map mangrove extents in Pongara National Park, Gabon using the Freeman-Durden Decomposition and InSAR Coherence derived from ALOS-2 imagery. Specifically, we obtain a land cover map derived from both this polarimetric decomposition and a 14-day repeat-pass coherence. Our classification model and results are highly interpretable based on a depth 2 decision tree. We further illustrate the correlation between InSAR coherence and height obtaining rough mangrove height estimates from TanDEM-X data. From our results, we observe that repeat-pass interferometric coherence provides invaluable information about mangrove extents and coastal forests. The clear identification of mangrove extents presents a significant opportunity for NISAR, which will provide 12-day repeat pass images over coastal areas globally.

Thomas, Nathan↗

NASA NTRS1981

Verification of land cover maps from LANDSAT data

The application of cluster sampling to verifying the accuracy of maps derived from digital data is discussed. Variants of the cluster sampling technique were used in large scale assessments for areas in excess of one million hectares. Three types of classification errors are possible: commission errors, omission errors, and overall error classification. Commission errors for a particular cover type occur when pixels are classified as that cover type but are found to be some other cover type when the field is checked. Omission errors occur when pixels of fields already visited and known to be of a particular cover type, are classified as some other cover type. Overall error is the proportion of pixels incorrectly classified, without regard to omission or commission. Since the classified image represents the sampling frame, sampling for accuracy assessment was designed to estimate commission error. However, the sample can also provide useful estimates of omission and overall error. Assessment for Alaska, Arizona, and Oklahoma are presented.

Linden, D. S.↗

NASA NTRS1985

Andrean examples of mega-geomorphology themes

Geomorphic (or physiographic) provinces have been a well known and useful method of regional landform classification for a century. Every earth scientist will recognize a phrase such as Appalachian Plateau or Southern Rocky Mountains as defining a discrete region of consistent geologic structure that has experienced a similar interval of erosion by a similar process or set of processes. The geomorphic provinces formalized in the United States by Fenneman in the 1920's continue to be highly satisfactory even though some boundaries were only vaguely drawn. Mosaics of LANDSAT images illustrate better than any earlier maps the validity and coherence of Fenneman's provinces. The concept of geomorphic provinces has been used subconsciously or intuitively, to describe the relief of the ocean floor and the topography of the Moon and other planets.

Bloom, A. L.↗