Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “cloud 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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
NASA NTRS1982

Study of sensor spectral responses and data processing algorithms and architectures for onboard feature identification

A computational model of the deterministic and stochastic processes involved in remote sensing is used to study spectral feature identification techniques for real-time onboard processing of data acquired with advanced earth-resources sensors. Preliminary results indicate that: Narrow spectral responses are advantageous; signal normalization improves mean-square distance (MSD) classification accuracy but tends to degrade maximum-likelihood (MLH) classification accuracy; and MSD classification of normalized signals performs better than the computationally more complex MLH classification when imaging conditions change appreciably from those conditions during which reference data were acquired. The results also indicate that autonomous categorization of TM signals into vegetation, bare land, water, snow and clouds can be accomplished with adequate reliability for many applications over a reasonably wide range of imaging conditions. However, further analysis is required to develop computationally efficient boundary approximation algorithms for such categorization.

Huck, F. O.↗
NASA NTRS2019

Deriving High-Resolution Reservoir Bathymetry from ICESat-2 Prototype Photon-Counting Lidar and Landsat Imagery

Knowledge of reservoir bathymetry is essential for many studies on terrestrial hydrological and biogeochemical processes. However, there are currently no cost-effective approaches to derive reservoir bathymetry at the global scale. This study explores the potential of generating high-resolution global bathymetry using elevation data collected by the 532-nm Advanced Topographic Laser Altimeter System (ATLAS) onboard the Ice, Cloud, and Land Elevation Satellite (ICESat-2). The novel algorithm was developed and tested using the ICESat-2 airborne prototype, the Multiple Altimeter Beam Experimental Lidar (MABEL), with Landsat-based water classifications (from 1982 to 2017). MABEL photon elevations were paired with Landsat water occurrence percentiles to establish the elevation-area (E-A) relationship, which in turn was applied to the percentile image to obtain partial bathymetry over the historic dynamic range of reservoir area. The bathymetry for the central area was projected to achieve the full bathymetry. The bathymetry image was then embedded onto the digital elevation model (DEM). Results were validated over Lake Mead against survey data. Results over four transects show coefficient of determination (R²) values from 0.82 to 0.99 and root-mean-square error (RMSE) values from 1.18 to 2.36 m. In addition, the E-A and elevation-storage (E-S) curves have RMSEs of 1.56 m and 0.08 km³, respectively. Over the entire dynamic reservoir area, the derived bathymetry agrees very well with independent survey data, except for within the highest and lowest percentile bands. With abundant overpassing tracks and high spatial resolution, the newly launched ICESat-2 should enable the derivation of bathymetry over an unprecedented number of reservoirs.

Yao Li↗
NASA NTRS2017

The Earth Observing System (EOS)

The Earth Observing System is a US National Aeronautics and Space Administration (NASA) program consisting of a science segment, a data system, and a space segment made up of a series of polar-orbiting and mid-inclination satellites for long-term monitoring of the Earth as an integrated system, including observations of the land surface, biosphere, atmosphere, cryosphere, and oceans. Initially conceived in the mid-late 1980s, it was implemented as a series of large "flagship" missions and smaller focused satellites, often in partnership with instruments and sometimes spacecraft from other nations. In 1984 NASA formed several instrument panels to develop concepts for “facility instruments” that would provide comprehensive support to the scientific and applications’ communities, each with a supporting science team competitively selected via peer-review. An Announcement of Opportunity was released in 1988 and proposals were solicited for three types of proposals: (i) instrument investigations that would include the provision of instrumentation for flight on a polar platform, including non-Earth science payloads requiring polar orbits (PI instruments), (ii) research facility instrument team member and team leader investigations for facility instruments, and (iii) interdisciplinary science investigations to provide data analysis and modeling, preparing to use data acquired from the space platforms. The initial selections made in 1989 included support for 24 instrument investigations, 6 research facility instrument investigations, and 28 interdisciplinary investigations. Although considerable changes were made over the years in the structure and orbital configuration of the various instruments and platforms, a total of 10 different missions were eventually flown, as shown in Fig. 1. These included three multiinstrument flagship platforms known as Terra (launched in 1999), Aqua (launched in 2002), and Aura (launched in 2004), where the Terra mission emphasis was primarily on land processes, Aqua on the hydrological cycle, and Aura on atmospheric chemistry. In addition to these flagship missions the EOS missions included Landsat 7 (land cover classification and change), QuikScat (wind speed and direction over the oceans), Jason-1 (ocean surface topography and sea level), ACRIMSAT (total solar irradiance (TSI)), SAGE III (stratospheric aerosol and ozone levels), ICESat (ice, cloud, and land elevation), and SORCE (Solar Radiation and Climate Experiment; total and spectral solar irradiance). In addition EOS supported CERES (an Earth radiation budget sensor) and LIS (a lightning sensor), that flew as part of the NASA/JAXA Tropical Rainfall Measuring Mission (1997), and SeaWinds (wind speed and direction), that flew as part of the short-lived ADEOS II (Midori II, 2002) mission of JAXA (Japan Aerospace Exploration Agency). The EOS contributions are too numerous to present in detail in this article, but can be viewed for convenience as a means of obtaining global measurements (with appropriate characteristics) of the 24 variables and variable groups listed in Table 1. This table was created by the EOS community in the late 1990s as a way to succinctly indicate which instruments on the various EOS platforms were expected to contribute to each of the specified variables in primary (bold), secondary (bold italics), or contributing (roman) roles. All of the science data products produced by these space missions are available without charge throughout the world, and are thus highly valued for their many contributions to applications such as air quality, fires, land cover change, and the state of the oceans, as well as for science and monitoring of the state of the Earth system and its changes over time. These and other international satellites have played a crucial role in understanding and documenting global change, including (i) global surface temperature and atmospheric temperature and water vapor profiles, (ii) glacial retreat, (iii) sea ice extent and change, (iv) solar radiation into and out of the Earth-atmosphere system, (v) atmospheric aerosol and cloud properties, (vi) sources and sinks of

ICESat↗
NASA NTRS2020

Leveraging Google Earth Engine User Interface for Semiautomated Wetland Classification in the Great Lakes Basin at 10 m With Optical and Radar Geospatial Datasets

As one of the world’s largest freshwater ecosystems,the Great Lakes Basin houses hundreds of thousands of acres of wetlands that support a variety of crucial ecological and environmental functions at the local, regional, and global levels.Monitoring these wetlands is critical to conservation and restoration efforts, however current methods that rely on field monitoring are labor-intensive, costly, and often outdated. In this study, we present a graphical user interface constructed in Google Earth Engine called the Wetland Extent Tool (WET),which allows semi-automatic wetland classification according to a user-input area of interest and date range. WET composites datasets and conducts multi source, moderate resolution processing utilizing Landsat 8 OLI, Sentinel-2 MSI, Sentinel-1 C-SAR, and Shuttle Radar Topography Mission (SRTM) datasets to classify wetlands in the entire Great Lakes Basin. We evaluated classification results of wetlands, uplands, and open water from May-September 2019, and tested whether SRTM elevation, slope,or the Dynamic Surface Water Extent produced the most accurate results in each Great Lake Basin in conjunction with optical indices and radar composites. We found that elevation produced the most accurate classification in Lake Erie, Michigan,and Ontario, while slope performed best in Lake Huron and Superior. Lake Erie, Michigan, Ontario, and Huron achieved high overall accuracy and identification of wetlands. WET leverages cloud-computing for multi source processing of moderate resolution remote sensing data, and employs a user interface in Google Earth Engine that wetland managers and conservationists can use to monitor wetland extent in the Great Lakes Basin in near real-time.

Vanessa L Valenti↗
NASA NTRS2012

Submillimetric Spectroscopic Observations of Volatiles in Comet C-2004 Q2 (Machholz)

Submillimeter spectroscopic observations of comets provide an important tool for understanding their chemical composition and enable a taxonomic classification. Aims. We aim to determine the production rates of several parent- and product volatiles and the C-12/C-13 isotopic carbon ratio in the long-period comet C/2004 Q2 (Machholz), which is likely to originate from the Oort Cloud. Methods. The line emission from several molecules in the coma was measured with high signal-to-noise ratio in January 2005 at heliocentric distance of 1.2 AU by means of high-resolution spectroscopic observations using the Submillimeter Telescope (SMT) at the Arizona Radio Observatory (ARO). Results. We have obtained production rates of several volatiles (CH3OH, HCN, H(sup 13)CN, HNC, H2CO, CO, and CS) by comparing the observed and simulated line-integrated intensities. We calculated the synthetic profiles using a radiative transfer code that includes collisions between neutrals and electrons, and the effects of radiative pumping of the fundamental vibrational levels by solar infrared radiation. Furthermore, multiline observations of the CH3OH J = 7-6 series allow us to estimate the rotational temperature using the rotation diagram technique. We find that the CH3OH population distribution of the levels sampled by these lines can be described by a rotational temperature of 40 +/- 3 K. Derived mixing ratios relative to hydrogen cyanide are CO/CH3OH/H2CO/CS/HNC/HC-13N/HCN= 30.9/24.6/4.8/0.57/0.031/0.013/1 assuming a pointing offset of 8" due to the uncertain ephemeris at the time of the observations and the telescope pointing error. Conclusions. The measured relative molecular abundances in C/2004 Q2 (Machholz) are between low- to typical values of those obtained in Oort Cloud comets, suggesting that it has visited the inner solar system previously and undergone thermal processing. The HNC/HCN abundance ratio of approx 3.1% is comparable to that found in other comets, accounting for the dependence on the heliocentric distance, and could possibly be explained by ion-molecule chemical processes in the low-temperature atmosphere. From a tentative HC-13N detection, the measured value of 97 +/- 30 for the HC-12N/HC-13N isotopologue pair is consistent with a telluric value. The outgassing variability observed in the HCN production rates over a period of two hours is consistent with the rotation of the nucleus derived using different observational techniques.

chemical composition↗
NASA NTRS1997

Surface-Based Observations of Contrail Occurrence Over the US, Apr. 1993 to Apr. 1994

Surface observers stationed at 19 U.S. Air Force Bases and Army Air Stations recorded the daytime occurrence of contrails and cloud fraction on an hourly basis for the period April 1993 through April 1994. Each observation uses one of four main categories to report contrails as unobserved, non-persistent, persistent, and indeterminate. Additional classification includes the co-occurrence of cirrus with each report. The data cover much of the continental U.S. including locations near major commercial air routes. The mean annual frequency of occurrence in unobstructed viewing conditions is 13 percent for these sites. Contrail occurrence varied substantially with location and season. Most contrails occurred during the winter months and least during the summer with a pronounced minimum during July. Although nocturnal observations are not available, it appears that the contrails have a diurnal variation that peaks during mid morning over most areas. Contrails were most often observed in areas near major commercial air corridors and least often over areas far removed from the heaviest air traffic. A significant correlation exists between mean contrail frequency and aircraft fuel usage above 7 km suggesting predictive potential for assessing future contrail effects on climate.

Minnis, Patrick↗
NASA NTRS2016

How We Can Constrain Aerosol Type Globally

In addition to aerosol number concentration, aerosol size and composition are essential attributes needed to adequately represent aerosol-cloud interactions (ACI) in models. As the nature of ACI varies enormously with environmental conditions, global-scale constraints on particle properties are indicated. And although advanced satellite remote-sensing instruments can provide categorical aerosol-type classification globally, detailed particle microphysical properties are unobtainable from space with currently available or planned technologies. For the foreseeable future, only in situ measurements can constrain particle properties at the level-of-detail required for ACI, as well as to reduce uncertainties in regional-to-global-scale direct aerosol radiative forcing (DARF). The limitation of in situ measurements for this application is sampling. However, there is a simplifying factor: for a given aerosol source, in a given season, particle microphysical properties tend to be repeatable, even if the amount varies from day-to-day and year-to-year, because the physical nature of the particles is determined primarily by the regional environment. So, if the PDFs of particle properties from major aerosol sources can be adequately characterized, they can be used to add the missing microphysical detail the better sampled satellite aerosol-type maps. This calls for Systematic Aircraft Measurements to Characterize Aerosol Air Masses (SAM-CAAM). We are defining a relatively modest and readily deployable, operational aircraft payload capable of measuring key aerosol absorption, scattering, and chemical properties in situ, and a program for characterizing statistically these properties for the major aerosol air mass types, at a level-of-detail unobtainable from space. It is aimed at: (1) enhancing satellite aerosol-type retrieval products with better aerosol climatology assumptions, and (2) improving the translation between satellite-retrieved aerosol optical properties and species-specific aerosol mass and size that are tracked in aerosol transport and climate models used to assess aerosol forcing and its anthropogenic components. This presentation will summarize where we stand on the development of the SAM-CAAM concept.

DARF↗
NASA NTRS2009

Small Negative Cloud-to-Ground Lightning Reports at the KSC-ER

'1he NASA Kennedy Space Center (KSC) and Air Force Eastern Range (ER) use data from two cloud-to-ground (CG) lightning detection networks, the CGLSS and the NLDN, and a volumetric lightning mapping array, LDAR, to monitor and characterize lightning that is potentially hazardous to ground or launch operations. Data obtained from these systems during June-August 2006 have been examined to check the classification of small, negative CGLSS reports that have an estimated peak current, [I(sup p)] less than 7 kA, and to determine the smallest values of I(sup p), that are produced by first strokes, by subsequent strokes that create a new ground contact (NGC), and by subsequent strokes that remain in a pre-existing channel (PEC). The results show that within 20 km of the KSC-ER, 21% of the low-amplitude negative CGLSS reports were produced by first strokes, with a minimum I(sup p) of-2.9 kA; 31% were by NGCs, with a minimum I(sup p) of-2.0 kA; and 14% were by PECs, with a minimum I(sup p) of -2.2 kA. The remaining 34% were produced by cloud pulses or lightning events that we were not able to classify.

Wilson, Jennifer G.↗
NASA NTRS1976

Effects of the atmosphere on remote sensing

The interaction between electromagnetic radiation and the earth's atmosphere is considered, taking into account windows in the electromagnetic spectrum, solar and terrestrial radiation, physical properties of the atmosphere, and clouds. The characteristics of upwelling radiation in the visible wavelengths are discussed along with infrared radiation and microwaves. Attention is given to radiant emittance, radiance, contrast, effects of atmospheric turbulence, ocean color, and questions concerning the classification of surface features with the aid of computers.

Fraser, R. S.↗
NASA NTRS1990

Observations of Sk-69 deg 203 and the interstellar extinction towards SN 1987A

Optical and UV spectroscopic observations of the Large Magellanic Cloud (LMC) star Sk-69 deg 203 are discussed. The optical data reveal Sk-69 deg 203 to be a BO.7 Ia supergiant with a moderate nitrogen enhancement, and its UV spectrum is consistent with this classification. UV interstellar extinction curves were constructed for the star using, as flux standards, two lightly reddened LMS supergiants, which bracket Sk-69 deg 203's spectral type. The resultant extinction curves are consistent with the extinction law derived previously for the 30 Doradus region, and the results for Sk-69 deg 203 suggest that the general 30 Doradus extinction law is appropriate for dereddening the observed fluxes of SN 1987A. Published H I 21 observations place SN 1987A in a region with a strong E-W gradient in the total hydrogen content. Comparison with the H I column density implied by the reddening indicates that the supernova is imbedded approximately in the middle of the main H I complex.

Fitzpatrick, Edward L.↗
NASA NTRS1995

The polarization and ultraviolet spectrum of Markarian 231

Ultraviolet spectropolarimetry acquired with the Hubble Space Telescope (HST) of the peculiar Seyfert galaxy Mrk 231 is combined with new high-quality ground-based measurements to provide the first, nearly complete, record of its linear polarization from 1575 to 7900 A. The accompanying ultraviolet spectrum portrays the heavily extinguished emission-line spectrum of the active nucleus plus the emergence of a blue continuum shortward of approximately 2400 A. In addition, absorption features due to He I lambda 3188, Mg I lambda 2853, Mg II lambda 2798, and especially several resonance multiplets of Fe II are identified with a well-known optical absorption system blueshifted approximately 4600 km/s with respect to emission lines. The continuum is attributed to approximately 10(exp 5) hot, young stars surrounding the nucleus. This component dilutes the polarized nuclear light, implying that the intrinsic polarization of the active galactic nucleus (AGN) spectrum approaches 20% at 2800 A. The rapid decline in degree of polarization toward longer wavelengths is best explained by the strongly frequency-dependent scattering cross section of dust grains coupled with modest starlight dilution. Peculiar S-shaped inflections in both the degree and position angle of polarization through H alpha and other major emission lines are interpreted as effects of scattering from two regions offset in velocity by several hundred km/s. A third source of (weakly) polarized flux is required to explain a nearly 40 deg rotation in position angle between 3200 and 1800 A. The displaced absorption features, polarimetry, and optical/infrared properties of Mrk 231 all point to its classification as a low-ionization, or Mg II broad absorption line quasar, in which most, if not all, lines of sight to the active nucleus are heavily obscured by dust and low-ionization gas clouds.

Smith, Paul S.↗
NASA NTRS2022

Deriving Severe Hail Likelihood from Satellite Observations and Model Reanalysis Parameters using a Deep Neural Network

Geostationary satellite imagers, such as those of the Geostationary Operational Environmental Satellite (GOES) series, have been observing severe convection at 15–60-minute intervals for over 40 years. When properly assessed, such a data record can be valuable in efforts of estimating severe storm risk throughout the diurnal cycle based on automated detection of patterns consistently found atop severe storms. Furthermore, environmental conditions favorable for severe weather are well-known and are thought to be represented well by modern reanalysis products. Promoting resilience against such hazards on local and global scales is a chief goal the NASA Disasters program, which seeks to encourage use of satellite observations to mitigate risk. For instance, hail is the costliest severe weather hazard across the globe in terms of insured loss, but reporting inconsistencies for hail events globally make it difficult to develop models that can quantify the risk. Satellite observation and model reanalysis taken together have the potential to, with reasonable skill and specificity, characterize environmental conditions that are favorable for hazardous weather, and thereby enable creation of hazard climatologie. Such climatologies are particularly useful over regions without extensive radar networks or storm reporting. By mapping the multivariate combination of observed cloud features and reanalysis environmental parameters/indices to United States Next Generation Weather Radar (NEXRAD) radar-estimated Maximum Expected Size of Hail (MESH) by way of a deep neural network (DNN), estimates of likelihood for potentially severe hail can be produced. Such estimates are of greater complexity and efficiency than could be performed with previous multivariate or logistic regression analyses for observed points within convective systems. Statistical distributions of convective parameters from satellite and reanalysis are shown to highlight non-severe/severe class separation for well-known hailstorm predictors, e.g., overshooting cloud top characteristics, deep-layer wind shear, mid-level stability, helicity, and convective inhibition. These complex, multivariate predictor relationships are exploited within a DNN, which can efficiently produce a quantitative hail risk metric with better than 70% detection rate and under 30% false alarms. These hail classifications can then be aggregated across the satellite record to yield a hazard climatology for hail frequency and severity – knowledge of which is of particular interest to those who manage risk (e.g., insurers) and are seeking opportunities to identify hail-prone regions, particularly in developing nations. This NASA study uses satellite observations and model parameters in a DNN to perform climatological hailstorm analysis in support of catastrophe model development, with the hope of promoting risk resilience particularly in regions without adequate weather radar coverage.

Passive Remote Sensing↗
NASA NTRS1982

Antarctic sea ice concentrations inferred from Nimbus 5 ESMR and Landsat imagery

Landsat Multispectral Scanner near-infrared band images (MSS-7) are used to calculate Antarctic ice concentration values and these results are quantitatively compared to those derived from Nimbus 5 electrically scanning microwave radiometer (ESMR) brightness temperature data. The set of images includes regions near the ice edge and near the continental boundary during late winter or spring. The percentage of ice cover is derived from the microwave data, using an algorithm that incorporates the brightness temperature emissivity and interpolated climatological physical temperatures and that is not dependent on spatial resolution. Cloud-free Landsat images are used to provide an alternative determination of large-scale ice concentrations, but this method is limited in its ability to resolve individual ice flows, especially near the ice edge. A proportional classification procedure is applied to Landsat data based on observed reflection and the results are correlated with similarly-derived ESMR ice concentration values. The corresponding ice concentration values are found to agree to + or - 15%, with the largest uncertainties occurring in regions of low ice concentration.

Comiso, J. C.↗
NASA NTRS1987

Spectroscopy of the extranuclear line-emitting regions associated with the gravitational lens system 2016 + 112

Moderate-resolution slit spectroscopy of the extended emission-line objects A1 and B1 located within 5 arcsec of the triple radio source 2016 + 112 shows that at least one is physically associated with the z = 3.273 quasar thought to be multiply imaged by a foreground galaxy. The data and theoretical models unanimously favor the identification of A1 and B1 with two separate clouds of ionized gas that lie within a few kiloparsecs of the primary A/B QSO and radio source. The available evidence does not support the view that they are multiple images of a single object or their classification as separate (companion) galaxies.

Schneider, D. P.↗
NASA NTRS1980

An evaluation of satellite data for estimating the area of small forestland in the southern lower peninsula of Michigan

A winter black and white band 5, a winter color, a fall color, and a diazo color composite of the fall scene were used to assess the use and potential of LANDSAT images for mapping and estimating acreage of small scattered forest tracts in Barry County, Michigan. Forests as small as 2.5 acres were mapped from each LANDSAT data source. The maps for each image were compared with an available forest-type map. Mapping errors detected were categorized as boundary and identification errors. The most frequently misclassified areas were agriculture lands, treed-bogs, brushlands and lowland and mixed hardwood stands. Stocking level affected interpretation more than stand size. The overall level of the interpretation performance was expressed through the estimation of classification, interpretation, and mapping accuracies. These accuracies ranged from 74 between 74% and 98%. Considering errors, accuracy, and cost, winter color imagery is the best LANDSAT alternative for mapping small forest tracts. However, since the availability of cloud-free winter images of the study area is significantly lower than images for other seasons, a diazo enhanced image of a fall scene is recommended as the best next best alternative.

Karteris, M. A.↗
NASA NTRS1984

High-sensitivity IRAS observations of the Chamaeleon I dark cloud

Very sensitive IRAS observations of a region of 0.8 sq deg in the Chamaeleon I cloud have revealed 70 compact sources. Hot sources are field stars; warm sources are associated with pre-main-sequence (PMS) stars in the cloud center; others may be in an even earlier phase of gravitational collapse. Cool sources, detected only at the long wavelengths, surround the main cloud and appear to be associated with small globules. Only a small fraction (less than 20 percent) of the total luminosity of the known PMS objects is emitted in the IRAS bands. This has important implications for the classification of the newly discovered embedded objects.

Baud, B.↗
NASA NTRS2012

Contribution of National near Real Time MODIS Forest Maximum Percentage NDVI Change Products to the U.S. ForWarn System

This presentation reviews the development, integration, and testing of Near Real Time (NRT) MODIS forest % maximum NDVI change products resident to the USDA Forest Service (USFS) ForWarn System. ForWarn is an Early Warning System (EWS) tool for detection and tracking of regionally evident forest change, which includes the U.S. Forest Change Assessment Viewer (FCAV) (a publically available on-line geospatial data viewer for visualizing and assessing the context of this apparent forest change). NASA Stennis Space Center (SSC) is working collaboratively with the USFS, ORNL, and USGS to contribute MODIS forest change products to ForWarn. These change products compare current NDVI derived from expedited eMODIS data, to historical NDVI products derived from MODIS MOD13 data. A new suite of forest change products are computed every 8 days and posted to the ForWarn system; this includes three different forest change products computed using three different historical baselines: 1) previous year; 2) previous three years; and 3) all previous years in the MODIS record going back to 2000. The change product inputs are maximum value NDVI that are composited across a 24 day interval and refreshed every 8 days so that resulting images for the conterminous U.S. are predominantly cloud-free yet still retain temporally relevant fresh information on changes in forest canopy greenness. These forest change products are computed at the native nominal resolution of the input reflectance bands at 231.66 meters, which equates to approx 5.4 hectares or 13.3 acres per pixel. The Time Series Product Tool, a MATLAB-based software package developed at NASA SSC, is used to temporally process, fuse, reduce noise, interpolate data voids, and re-aggregate the historical NDVI into 24 day composites, and then custom MATLAB scripts are used to temporally process the eMODIS NDVIs so that they are in synch with the historical NDVI products. Prior to posting, an in-house snow mask classification product is computed for the current compositing period and integrated into the change images to account for snow related NDVI drops. The supplemental snow classification product was needed because other available QA cloud/snow mask typically underestimates snow cover. MODIS true and false color composites were also computed from eMODIS reflectance data and the true color RGBs are also posted on ForWarn?s FCAV; this data is used for assessing apparent occasional quality issues on the change products due to residual unmasked cloud cover. New forest change products are posted with typical latencies of 1-2 days after the last input eMODIS data collection date for a given 24 day compositing period.

Spruce, Joseph P.↗
NASA NTRS2018

NeMO-Net - The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment

In the past decade, coral reefs worldwide have experienced unprecedented stresses due to climate change, ocean acidification, and anthropomorphic pressures, instigating massive bleaching and die-off of these fragile and diverse ecosystems. Furthermore, remote sensing of these shallow marine habitats is hindered by ocean wave distortion, refraction and optical attenuation, leading invariably to data products that are often of low resolution and signal-to-noise (SNR) ratio. However, recent advances in UAV and Fluid Lensing technology have allowed us to capture multispectral 3D imagery of these systems at sub-cm scales from above the water surface, giving us an unprecedented view of their growth and decay. By combining spatial and spectral information from varying resolutions, we seek to augment and improve the classification accuracy of previously low-resolution datasets at large temporal scales.NeMO-Net, the first open-source deep convolutional neural network (CNN) and interactive learning and training software, currently being developed at NASA Ames, is aimed at assessing the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology. The latest iteration uses fully convolutional networks to segment and identify coral imagery taken by UAVs and satellites, including WorldView-2 and Sentinel. We present results taken from the Indian Ocean where classification accuracy has exceeded 91% for 24 geomorphological classes given ample training data. In addition, we utilize deep Laplacian Pyramid Super-Resolution Networks (LapSRN) to reconstruct high resolution information from low resolution imagery, trained from various UAV and satellite datasets. Finally, in the case of insufficient training data, we have developed an interactive online platform that allows users to easily segment and submit their classifications, which has been integrated with the current NeMO-Net workflow. Specifically, we present results from the Fiji islands in which preliminary user data has allowed for the accurate identification of 9 separate classes, despite issues such as cloud shadowing and spectral variation. The project is being supported by NASA's Earth Science Technology Office (ESTO) Advanced Information Systems Technology (AIST-16) Program.

Neural↗