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 721 records · Page 40

NASA/BLM Applications Pilot Test (APT), phase 2. Volume 1: Executive summary

Data from LANDSAT, low altitude color aerial photography, and ground visits were combined and used to produce vegetation cover maps and to estimate productivity of range, woodland, and forest resources in northwestern Arizona. A planning session, two workshops, and four status reviews were held to assist technology transfer from NASA. Computer aided digital classification of LANDSAT data was selected as a major source of input data. An overview is presented of the data processing, data collection, productivity estimation, and map verification techniques used. Cost analysis and digital LANDSAT digital products are also considered.

Source record↗

LANDSAT data for state planning

The results of an effort to generate and apply automated classification of LANDSAT digital data to state of Georgia problems are presented. This phase centers on an analysis of the usefulness of LANDSAT digital data to provide land-use data for transportation planning. Hall County, Georgia was chosen as a test site because it is part of a seventeen county area for which the Georgia Department of Transportation is currently designing a Transportation Planning Land-Use Simulation Model. The land-cover information derived from this study was compared to several other existing sources of land-use data for Hall County and input into this simulation. The results indicate that there is difficulty comparing LANDSAT derived land-cover information with previous land-use information since the LANDSAT data are acquired on an acre by acre grid basis while all previous land-use surveys for Hall County used land-use data on a parcel basis.

Faust, N. L.↗

Texturecam: A Smart Camera for Microscale, Mesoscale, and Deep Space Applications

The TextureCam project is developing a 'smart camera' that can classify geologic surfaces in planetary images. This would allow autonomous spacecraft to collect data opportunisitcally during intervals between communications with Earth, such as during long traverses. Its surface classifications can identify new targets that were not anticipated in advance. The spacecraft might use this information to target these features with high-resolution instruments such as spectrometers nd narrow-field cameras. Classifications could also inform data 'triage' decisions, identifying high value images for prioritized downlink. Finally, the surface classification can serve as compressed maps of image content. Each of these strategies can improve the science data returned at each command cycle and speed reconnaissance during site survey and astrobiology investigation. Our first year of development has completed the image analysis algorithms and validated them in software tests. Here we survey these initial results and explore several application areas relevant to Mars and beyond.

Hyperspectral imagery↗

Mapping of deciduous forest cover using simulated Landsat-D TM data

An evaluation is presented of the supervised vegetation classification images of heavily forested terrain in the eastern US produced from simulated Landsat-D Thematic Mapper data as part of the Joint NASA/Geosat Test Case study of the Lost River, West Virginia, gas field. This investigation utilized data supplied by the NS-001 aircraft multispectral scanner (15 m IFOV) of NASA. The instruments recognized a total of 9 vegetation classes and one soil class. A hybrid parallelepiped-Bayesian maximum likelihood classifier was employed to produce the supervised vegetation classifications. The data were obtained at the height of the fall foliage display for this portion of West Virginia. Results show that both classifications are highly accurate, based on a comparison of assignment of vegetation classes on each of the images with actual ground conditions. It is noted that the anomalous distribution of certain woody species found in the resulting supervised classifications may be related to the microseepage of methane from the gas reservoir.

Rock, B. N.↗

Temporal analysis of multispectral scanner data.

Multispectral scanner reflectance data were sampled for bare soil, cotton, sorghum, corn, and citrus at four dates during a growing season (April, May, June, and July 1969) to develop a time-dependent signature for crop and soil discrimination. Discrimination tests were conducted for single-date and multidate formats using training and test data sets. For classifications containing several crops, the multidate or temporal approach improved discrimination compared with the single-date approach. The multidate approach also preserved recognition accuracy better in going from training fields to test fields than the single-date analysis. The spectral distinctiveness of bare soil versus vegetation resulted in essentially equal discrimination using single-date versus multidate data for those two categories.

Richardson, A. J.↗

Estimation of irrigated land using Landsat digital data

Techniques developed by the University of California and NASA for the utilization of multitemporal Landsat digital data in estimating and mapping irrigated land are presented. Three dates of Landsat were registered to each other and to a USGS 7.5 minute quadrangle map base for approximately 1.9 million acres of land. Other data registered include county boundaries, land use stratification, and digitized ground data. To identify irrigated land, an indicator was used which consisted of the ratio of MSS Band 7 to MSS Band 5 (the 7/5 ratio). A threshold 7/5 irrigated land value was determined for each date, as actively growing land generally has a higher 7/5 ratio than other cover classes. An estimate of irrigated land was determined by Landsat classification with ground data, at a relative standard error of + or - 7.98% at the 95% confidence interval. Mapping evaluation reveals a 94% accuracy, a 7.4% omission rate, and a 6.3% commission rate. In addition, a sample unit size evaluation recommends a 1-1 1/2 square mile sample range.

Brown, C. E.↗

An Iterative Approach to the Feature Selection Problem

The problem dealt with concerns feature selection or reducing the dimension of the data to be processed from n to k. By reducing the dimension of the data from n to k, classification time is generally reduced. Yet the dimension reduction should not be so great that classification accuracy is impaired. Thus, the general problem is considered of classifying an n-dimensional observation vector x into one of m-distinct classes where each class is normally distributed with mean and covariance. It is shown that the probability of misclassification is minimized if a maximum likelihood classification procedure is used to classify the data. The dimension of each observation vector to be processed is conveniently reduced by performing the transformation y = Bx, where B is a K by n matrix of rank k. Thus, the n-dimensional classification problem transforms into a k-dimensional classification problem.

Decell, H. P., Jr.↗

Preprocessing of multispectral data and simulation of ERTS data channels to make computer terrain maps of a Yellowstone National Park test site

The possibility of improving the accuracy of terrain classification by preprocessing spectral data was investigated. Terrain maps were made using the following techniques: 1) preprocessing by scan angle function transformation, using the computer-selected best set of three channels; and 2) preprocessing by ratio transformation, using the specified ERTS data channels, simulated by fitting the spectral response of each of the 12 data channels to the ERTS channels by a set of weighting coefficients. By using a simple technique during printout, the maps were produced in color. The normalized scan angle function transformation resulted in the most accurate classification. The best ratio transformation for the Yellowstone Park data was the ratio of each channel to the sum of all channels. A supervised training program involving maximum likelihood decision for selecting the best spectrometer channels and similar techniques for digitizing the data of the analog magnetic tapes were used. Cloud shadows were recognized in addition to eight classes of terrain. Preprocessing of data resulted in more accurate maps, required fewer training areas (hence less preparation and computer time), and enabled much of the area formerly classified as shadow to be reclassified according to actual terrain type.

Smedes, H. W.↗

First Cosmology Results Using Type Ia Supernovae From the Dark Energy Survey: Survey Overview and Supernova Spectroscopy

We present spectroscopy from the first three seasons of the Dark Energy Survey Supernova Program (DES-SN). We describe the supernova spectroscopic program in full: strategy, observations, data reduction, and classification. We have spectroscopically confirmed 307 supernovae, including 251 type Ia supernovae (SNe Ia) over a redshift range of $0.017 < z < 0.85$. We determine the effective spectroscopic selection function for our sample, and use it to investigate the redshift-dependent bias on the distance moduli of SNe Ia we have classified. We also provide a full overview of the strategy, observations, and data products of DES-SN, which has discovered 12,015 likely supernovae during these first three seasons. The data presented here are used for the first cosmology analysis by DES-SN ('DES-SN3YR'), the results of which are given in DES Collaboration (2018a).

79 ASTRONOMY AND ASTROPHYSICS↗

Deep Multimodal Networks for M-type Star Classification with Paired Spectrum and Photometric Image

Abstract Traditional stellar classification methods include spectral and photometric classification separately. Although satisfactory results can be achieved, the accuracy could be improved. In this paper, we pioneer a novel approach to deeply fuse the spectra and photometric images of the sources in an advanced multimodal network to enhance the model’s discriminatory ability. We use Transformer as the fusion module and apply a spectrum–image contrastive loss function to enhance the consistency of the spectrum and photometric image of the same source in two different feature spaces. We perform M-type stellar subtype classification on two data sets with high and low signal-to-noise ratio (S/N) spectra and corresponding photometric images, and the F1-score achieves 95.65% and 90.84%, respectively. In our experiments, we prove that our model effectively utilizes the information from photometric images and is more accurate than advanced spectrum and photometric image classifiers. Our contributions can be summarized as follows: (1) We propose an innovative idea for stellar classification that allows the model to simultaneously consider information from spectra and photometric images. (2) We discover the challenge of fusing low-S/N spectra and photometric images in the Transformer and provide a solution. (3) The effectiveness of Transformer for spectral classification is discussed for the first time and will inspire more Transformer-based spectral classification models.

Astronomy & Astrophysics↗

An assessment of Landsat data acquisition history on identification and area estimation of corn and soybeans

During the past decade, numerous studies have demonstrated the potential of satellite remote sensing for providing accurate and timely crop area information. This study assessed the impact of Landsat data acquisition history on classification and area estimation accuracy of corn and soybeans. Multitemporally registered Landsat MSS data from four acquisitions during the 1978 growing season were used in classification of eight sample segments in the U.S. Corn Belt. The results illustrate the importance of selecting Landsat acquisitions based on spectral differences in crops at certain growth stages.

Hixson, M. M.↗

When Spectral Modeling Meets Convolutional Networks: A Method for Discovering Reionization-era Lensed Quasars in Multiband Imaging Data

Over the last two decades, around 300 quasars have been discovered at z ≳ 6, yet only one has been identified as being strongly gravitationally lensed. We explore a new approach—enlarging the permitted spectral parameter space, while introducing a new spatial geometry veto criterion—which is implemented via image-based deep learning. We first apply this approach to a systematic search for reionization-era lensed quasars, using data from the Dark Energy Survey, the Visible and Infrared Survey Telescope for Astronomy Hemisphere Survey, and the Wide-field Infrared Survey Explorer. Our search method consists of two main parts: (i) the preselection of the candidates, based on their spectral energy distributions (SEDs), using catalog-level photometry; and (ii) relative probability calculations of the candidates being a lens or some contaminant, utilizing a convolutional neural network (CNN) classification. The training data sets are constructed by painting deflected point-source lights over actual galaxy images, to generate realistic galaxy–quasar lens models, optimized to find systems with small image separations, i.e., Einstein radii of θ E ≤ 1''. Visual inspection is then performed for sources with CNN scores of P lens > 0.1, which leads us to obtain 36 newly selected lens candidates, which are awaiting spectroscopic confirmation. These findings show that automated SED modeling and deep learning pipelines, supported by modest human input, are a promising route for detecting strong lenses from large catalogs, which can overcome the veto limitations of primarily dropout-based SED selection approaches.

High-redshift galaxies↗

FPGA Coprocessor for Accelerated Classification of Images

An effort related to that described in the preceding article focuses on developing a spaceborne processing platform for fast and accurate onboard classification of image data, a critical part of modern satellite image processing. The approach again has been to exploit the versatility of recently developed hybrid Virtex-4FX field-programmable gate array (FPGA) to run diverse science applications on embedded processors while taking advantage of the reconfigurable hardware resources of the FPGAs. In this case, the FPGA serves as a coprocessor that implements legacy C-language support-vector-machine (SVM) image-classification algorithms to detect and identify natural phenomena such as flooding, volcanic eruptions, and sea-ice break-up. The FPGA provides hardware acceleration for increased onboard processing capability than previously demonstrated in software. The original C-language program demonstrated on an imaging instrument aboard the Earth Observing-1 (EO-1) satellite implements a linear-kernel SVM algorithm for classifying parts of the images as snow, water, ice, land, or cloud or unclassified. Current onboard processors, such as on EO-1, have limited computing power, extremely limited active storage capability and are no longer considered state-of-the-art. Using commercially available software that translates C-language programs into hardware description language (HDL) files, the legacy C-language program, and two newly formulated programs for a more capable expanded-linear-kernel and a more accurate polynomial-kernel SVM algorithm, have been implemented in the Virtex-4FX FPGA. In tests, the FPGA implementations have exhibited significant speedups over conventional software implementations running on general-purpose hardware.

Pingree, Paula J.↗

Large Area Crop Inventory Experiment (LACIE). Review of LACIE methodology, a project evaluation of technical acceptability

The author has identified the following significant results. Results indicated that the LANDSAT data and the classification technology can estimate the small grains area within a sample segment accurately and reliably enough to meet the LACIE goals. Overall, the LACIE estimates in a 9 x 11 kilometer segment agree well with ground and aircraft determined area within these segments. The estimated c.v. of the random classification error was acceptably small. These analyses confirmed that bias introduced by various factors, such as LANDSAT spatial resolution, lack of spectral resolution, classifier bias, and repeatability, was not excessive in terms of the required performance criterion. Results of these tests did indicate a difficulty in differentiating wheat from other closely related small grains. However, satisfactory wheat area estimates were obtained through the reduction of the small grain area estimates in accordance with relative amounts of these crops as determined from historic data; these procedures are being further refined.

Source record↗

LANDSAT data from agricultural sites: Crop signature analysis

The LANDSAT multispectral scanner (MSS) data were analyzed with a view toward classification to identify wheat. The notion of spectral signature of a crop, a commonly used basis for classification, was found to be inadequate. Data analysis has revealed that the MSS data from agricultural sites were essentially two dimensional, and that the data from different sites and different acquisition lay on parallel planes in the four dimensional feature space. These results were exploited to gain new insight into the data and to develop alternate models for classification. In particular, it was found that the temporal pattern of change in the spectral response of a crop constitutes its signature and provides a basis for crop classification.

Misra, P. N.↗

On the design of classifiers for crop inventories

Crop proportion estimators that use classifications of satellite data to correct, in an additive way, a given estimate acquired from ground observations are discussed. A linear version of these estimators is optimal, in terms of minimum variance, when the regression of the ground observations onto the satellite observations in linear. When this regression is not linear, but the reverse regression (satellite observations onto ground observations) is linear, the estimator is suboptimal but still has certain appealing variance properties. In this paper expressions are derived for those regressions which relate the intercepts and slopes to conditional classification probabilities. These expressions are then used to discuss the question of classifier designs that can lead to low-variance crop proportion estimates. Variance expressions for these estimates in terms of classifier omission and commission errors are also derived.

Heydorn, R. P.↗

Self-Supervised Cloud Classification

Abstract Low-level marine clouds play a pivotal role in Earth’s weather and climate through their interactions with radiation, heat and moisture transport, and the hydrological cycle. These interactions depend on a range of dynamical and microphysical processes that result in a broad diversity of cloud types and spatial structures, and a comprehensive understanding of cloud morphology is critical for continued improvement of our atmospheric modeling and prediction capabilities moving forward. Deep learning has recently accelerated our ability to study clouds using satellite remote sensing, and machine learning classifiers have enabled detailed studies of cloud morphology. A major limitation of deep learning approaches to this problem, however, is the large number of hand-labeled samples that are required for training. This work applies a recently developed self-supervised learning scheme to train a deep convolutional neural network (CNN) to map marine cloud imagery to vector embeddings that capture information about mesoscale cloud morphology and can be used for satellite image classification. The model is evaluated against existing cloud classification datasets and several use cases are demonstrated, including training cloud classifiers with very few labeled samples, interrogation of the CNN’s learned internal feature representations, cross-instrument application, and resilience against sensor calibration drift and changing scene brightness. The self-supervised approach learns meaningful internal representations of cloud structures and achieves comparable classification accuracy to supervised deep learning methods without the expense of creating large hand-annotated training datasets. Significance Statement Marine clouds heavily influence Earth’s weather and climate, and improved understanding of marine clouds is required to improve our atmospheric modeling capabilities and physical understanding of the atmosphere. Recently, deep learning has emerged as a powerful research tool that can be used to identify and study specific marine cloud types in the vast number of images collected by Earth-observing satellites. While powerful, these approaches require hand-labeling of training data, which is prohibitively time intensive. This study evaluates a recently developed self-supervised deep learning method that does not require human-labeled training data for processing images of clouds. We show that the trained algorithm performs competitively with algorithms trained on hand-labeled data for image classification tasks. We also discuss potential downstream uses and demonstrate some exciting features of the approach including application to multiple satellite instruments, resilience against changing image brightness, and its learned internal representations of cloud types. The self-supervised technique removes one of the major hurdles for applying deep learning to very large atmospheric datasets.

54 ENVIRONMENTAL SCIENCES↗

Integration of historical map and aerial imagery to characterize long-term land-use change and landscape dynamics: An object-based analysis via Random Forests

Tracking Earth’s past helps us to move from hindsight to foresight in seeking landscape sustainability, a pursuit aided by modern mapping capabilities but hindered by a dearth of historical landscape information. To fill the data gap and exemplify the use of old map for land-use change sciences, we combined a paper-based US civil war map and aerial photos to derive land-use history and landscape dynamics at fine scales for a region near Chancellorsville, VA, USA, from 1867 to 2014. We also tested how advanced algorithms—object-based analysis and random forests (RF)—could aid in data processing. Automatic classification of the 1867 map proved difficult, but its manual digitization could benefit from object-based image segmentation. Classifying digital aerial images was more accurate via the object-based than pixel-based method, but only if the images were segmented appropriately. In the object-based classification, spectral-based features were much more important than shape/geometry features, as ranked by RF. During the 147 years, 32% of the region changed in land type. Settlement and roads increased in extent by 1850% and 691%, respectively, and woodland decreased by 19%. These changes fragmented the landscape, altered the hydrological regime, and affected river morphology. The utility of old maps exemplified here provides an impetus for exploring and leveraging extant old maps or historical records to support land-use and global change research. Our study also connotes the importance of geotagging current data, such as photos and videos, that may serve as a baseline to document future landscape change.

Historical map, object-based, Random Forests, old ↗