20191025084000001.0FGDC CSDGM MetadataFALSEnlcd_2016_prusvi_treecanopy_20191017.imgfile://\\166.2.127.149\tcc_ak\PRUSVI\TCC2016_PRUSVI\Final_Products\Cartographic_NLCD\nlcd_2016_prusvi_treecanopy_20191017.imgLocal Area Network2890755.0000003591885.000000-219375.000000189555.0000001002ProjectedGCS_North_American_1983Linear Unit: Meter (1.000000)Albers_Conical_Equal_Area<ProjectedCoordinateSystem xsi:type='typens:ProjectedCoordinateSystem' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance' xmlns:xs='http://www.w3.org/2001/XMLSchema' xmlns:typens='http://www.esri.com/schemas/ArcGIS/10.5'><WKT>PROJCS["Albers_Conical_Equal_Area",GEOGCS["GCS_North_American_1983",DATUM["D_North_American_1983",SPHEROID["GRS_1980",6378137.0,298.257222101]],PRIMEM["Greenwich",0.0],UNIT["Degree",0.0174532925199433]],PROJECTION["Albers"],PARAMETER["false_easting",0.0],PARAMETER["false_northing",0.0],PARAMETER["central_meridian",-96.0],PARAMETER["standard_parallel_1",29.5],PARAMETER["standard_parallel_2",45.5],PARAMETER["latitude_of_origin",23.0],UNIT["Meter",1.0]]</WKT><XOrigin>-16901100</XOrigin><YOrigin>-6972200</YOrigin><XYScale>266467840.99085236</XYScale><ZOrigin>-100000</ZOrigin><ZScale>10000</ZScale><MOrigin>-100000</MOrigin><MScale>10000</MScale><XYTolerance>0.001</XYTolerance><ZTolerance>0.001</ZTolerance><MTolerance>0.001</MTolerance><HighPrecision>true</HighPrecision></ProjectedCoordinateSystem>8TRUERLE1IMAGINE ImageTRUEdiscreteunsigned integer201911151536090020191115153637001500000005000FGDCU.S. Geological Survey47914 252nd StreetSioux FallsSD57198-0001custserv@usgs.govUS605-594-6151605-594-6589605-594-6933Hours_of_Service: 0800 - 1600 CT, M - F (-6h CST/-5h CDT GMT)The USGS point of contact is for questions relating to the data display and download from this web site. For questions regarding data content and quality, email: mrlc@usgs.govU.S. Geological SurveyCustomer Services RepresentativeU.S. Geological Survey20191115ArcGIS Metadata1.0U.S. Geological Survey47914 252nd StreetSioux FallsSD57198-0001custserv@usgs.govUS605-594-6151605-594-6589605-594-6933Hours_of_Service: 0800 - 1600 CT, M - F (-6h CST/-5h CDT GMT)The USGS point of contact is for questions relating to the data display and download from this web site. For questions regarding data content and quality, email: mrlc@usgs.govU.S. Geological SurveyCustomer Services RepresentativeU.S. Geological SurveyRaster DatasetNLCD 2016 Percent Tree Canopy (Puerto Rico and the US Virgin Islands)2019-10-18T00:00:00raster digital datanonenoneU.S. Geological Survey47914 252nd StreetSioux FallsSD57198-0001custserv@usgs.govUS605-594-6151605-594-6589605-594-6933Hours_of_Service: 0800 - 1600 CT, M - F (-6h CST/-5h CDT GMT)The USGS point of contact is for questions relating to the data display and download from this web site. For questions regarding data content and quality, email: mrlc@usgs.govU.S. Geological SurveyCustomer Services Representative<DIV STYLE="text-align:Left;"><DIV><DIV><P STYLE="margin:0 0 0 0;"><SPAN><SPAN>The USDA Forest Service (USFS) builds multiple versions of percent tree canopy cover data, in order to serve needs of multiple user communities. These datasets encompass CONUS, Coastal Alaska, Hawaii, U.S. Virgin Islands and </SPAN></SPAN><SPAN /><SPAN /><SPAN><SPAN>Puerto Rico. There are three versions of data within the 2016 TCC Product Suite, which include:</SPAN></SPAN></P><UL><LI><P><SPAN><SPAN>The initial model outputs referred to as the Analytical data;</SPAN></SPAN></P></LI></UL><UL><LI><P><SPAN><SPAN>A masked version of the initial output referred to as Cartographic data;</SPAN></SPAN></P></LI></UL><UL><LI><P><SPAN><SPAN>And a modified version built for the National Land Cover Database and referred to as NLCD data, which includes a canopy cover change dataset derived from subtraction of datasets for the nominal years of 2011 and 2016.</SPAN></SPAN></P></LI></UL><P STYLE="margin:0 0 0 0;"><SPAN><SPAN>The Analytical data are the initial model outputs generated in the production workflow. These data are best suited for users who will carry out their own detailed statistical and uncertainty analyses on the dataset and place lower priority on the visual appearance of the dataset for cartographic purposes. Datasets for the nominal years of 2011 and 2016 are available. </SPAN></SPAN></P><P><SPAN><SPAN>The Cartographic products mask the initial model outputs to improve the visual appearance of the datasets. These data are best suited for users who prioritize visual appearance of the data for cartographic and illustrative purposes. Datasets for the nominal years of 2011 and 2016 are available. </SPAN></SPAN></P><P STYLE="margin:0 0 0 0;"><SPAN><SPAN>The NLCD data are the result of further processing of the masked data. The goal was to generate three coordinated components. The components are (1) a dataset for the nominal year of 2011, (2) a dataset for the nominal year of 2016, and (3) a dataset that captures the change in canopy cover between the two nominal years of 2011 and 2016. For the NLCD data, the three components meet the criterion of “2011 TCC + change in TCC = 2016 TCC”. These NLCD data are best suited for users who require a coordinated three-component data stack where each pixel’s values meet the criterion of “2011 TCC + change in TCC = 2016 TCC”. Datasets for the nominal years of 2011 and 2016 are available, as well as a dataset that captures the change (loss or gain) in canopy cover between those two nominal years of 2011 and 2016, in areas where change was identified.</SPAN></SPAN></P><P STYLE="margin:0 0 0 0;"><SPAN /><SPAN /></P><P STYLE="margin:0 0 0 0;"><SPAN><SPAN>These tree canopy cover data are accessible for multiple user communities, through multiple channels and platforms, as listed below:</SPAN></SPAN></P><P><SPAN STYLE="font-weight:bold;">Analytical</SPAN></P><UL><LI><P><A href="https://data.fs.usda.gov/geodata/rastergateway/treecanopycover/"><SPAN>USFS Tree Canopy Cover Datasets</SPAN></A><SPAN>(Download)</SPAN></P></LI><LI><P><A href="https://apps.fs.usda.gov/fsgisx01/rest/services/RDW_LandscapeAndWildlife"><SPAN>USFS Enterprise Data Warehouse</SPAN></A><SPAN>(Image Service)</SPAN></P></LI></UL><P><SPAN STYLE="font-weight:bold;">Cartographic</SPAN></P><UL><LI><P><A href="https://data.fs.usda.gov/geodata/rastergateway/treecanopycover/"><SPAN>USFS Tree Canopy Cover Datasets</SPAN></A><SPAN>(Download)</SPAN></P></LI><LI><P><A href="https://apps.fs.usda.gov/arcx/rest/services/RDW_LandscapeAndWildlife"><SPAN>USFS Enterprise Data Warehouse</SPAN></A><SPAN>(Map Service)</SPAN></P></LI></UL><P><SPAN STYLE="font-weight:bold;">NLCD</SPAN></P><UL><LI><P><A href="https://www.mrlc.gov/data"><SPAN>Multi-Resolution Land Characteristics (MRLC) Consortium</SPAN></A><SPAN>(Download)</SPAN></P></LI><LI><P><A href="https://apps.fs.usda.gov/fsgisx01/rest/services/RDW_LandscapeAndWildlife"><SPAN>USFS Enterprise Data Warehouse</SPAN></A><SPAN>(Image Service)</SPAN></P></LI></UL><P><SPAN><SPAN>The </SPAN></SPAN><SPAN>Puerto Rico and the US Virgin Islands TCC 2016 NLCD dataset is comprised of a single layer. The pixel values range from 0 to 99 percent. The background is represented by the value 255. The dataset has data gaps due to consistent clouds/shadows in the Landsat images used for modeling. These data gaps are represented by the value 127.</SPAN></P></DIV></DIV></DIV>The goal of this project is to provide the Nation with complete, current and consistent public domain information on its tree canopy cover.Funding for this project was provided by the U.S. Forest Service (USFS). RedCastle Resources, Inc. produced the dataset under contract to the USFS Geospatial Technology and Applications Center.U.S. Department of Commerce, 1995, Countries, dependencies, areas of special sovereignty, and their principal administrative divisions, Federal Information Processing Standard 10-4: Washington, D.C., National Institute of Standards and TechnologyU.S.Puerto RicoU.S. Virgin IslandsUSAUnited States of AmericaPRUSUnited StatesUSVIU.S.A.ISO 19115 CategoryEarth CoversImageryBase MapGISPercent Tree CanopyUSFSTree Canopy CoverRemote SensingContinuousDigital Spatial DataU.S. Forest ServiceU.S.Puerto RicoU.S. Virgin IslandsEarth CoversGISUSAUnited States of AmericaPRUSVIPercent Tree CanopyImageryUSFSUSTree Canopy CoverRemote SensingUnited StatesContinuousBase MapHIU.S.A.Digital Spatial DataU.S. Forest ServiceSee access and use constraints information.<DIV STYLE="text-align:Left;"><DIV><DIV><P><SPAN>These data were collected using funding from the U.S. Government and can be used without additional permissions or fees. If you use these data in a publication, presentation, or other research product please use the following citation: </SPAN></P><P STYLE="text-indent:20;margin:7 0 7 0;"><SPAN>U.S. Forest Service. 2019. NLCD 2016 Percent Tree Canopy (Puerto Rico and the US Virgin Islands). Salt Lake City, UT.</SPAN></P><P><SPAN>Appropriate use includes regional to national assessments of tree cover, total extent of tree cover, and aggregated summaries of tree cover</SPAN></P></DIV></DIV></DIV>-160.324461-154.72024818.83450122.291669Ground condition at time of imagery capture2016-01-02T00:00:002017-09-17T00:00:00Corner Coordinates (center of pixel, meters): upper left: -345945 (X), 2132415 (Y); lower right: 237225 (X), 1753875 (Y).U.S. Geological Survey47914 252nd StreetSioux FallsSD57198-0001custserv@usgs.govUS605-594-6151605-594-6589605-594-6933Hours_of_Service: 0800 - 1600 CT, M - F (-6h CST/-5h CDT GMT)The USGS point of contact is for questions relating to the data display and download from this web site. For questions regarding data content and quality, email: mrlc@usgs.govU.S. Geological SurveyCustomer Services RepresentativeU.S. Geological SurveyU.S. Geological Survey Version 6.2 (Build 9200) ; Esri ArcGIS 10.5.1.73331-69.628175-62.42248120.87120015.177592Data is for Puerto Rico and the US Virgin Islands only.No formal, independent accuracy assessment of this product has been made at the time of publication. However, an assessment is planned. Users should check at https://data.fs.usda.gov/geodata/rastergateway/treecanopycover/ or send an inquiry to the metadata contact to inquire if new accuracy information is available.
The random forests regression algorithm (R Core Team 2017; Cutler et al. 2007; Breiman 2001) employed in creating this product calculates the mean of squared residuals along with percent variability explained by the model for assessing prediction reliability. The random forests models consisted of 500 decision trees, which were used to determine the final response value. The response of each tree depended on a randomly chosen subset of predictor variables chosen independently (with replacement) for evaluation by that tree. The responses of the trees were averaged to obtain an estimate of the dependent variable. Because the random forests bias correction option was used, it was possible to obtain estimates less than 0 or greater than 100. These estimates were reset to either 0 or 100. The estimates were also rounded to the nearest integer. The standard error is the square root of the variance of the estimates given by all trees.
References
Breiman, L. 2001. Random forests. Machine Learning 45:15-32.
Cutler, R.D.; Edwards, T.C.; Beard, K.H.; Cutler, A.; Hess, K.T.; Gibson, J.; Lawler, J.J. 2007. Random forests for classification in ecology. Ecology 88 (11):2783-2792.
R Core Team. 2017. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL www.R-project.orgcanopy cover estimate (training/validation)Photointerpreted Canopy CoverPI_CCUSDA Forest Service Geospatial Technology and Applications Centervector digital dataspectral informationLandsat 8 Harmonic Regression Coefficients (2016-2017)L8HRt2Oregon State University--Department of Forest Ecosystems and Societyraster digital dataspectral informationLandsat 8 Operational Land ImagerL8OLIU.S. Geological SurveySioux Falls, SDraster digital dataspectral informationLandsat 8 OLI Composite ImageryUSDA Forest Service Geospatial Technology and Applications Centerraster digital dataL8OLICompelevation informationPuerto Rico Coastal Digital Elevation Model2007-06-22T00:00:00National Geophysical Data Center, NESDIS, NOAA, U.S. Department of Commerceraster digital dataDEMprPhotointerpretation of Sample Plots. Response data used to train the computer models is made by photographic interpretation of sample plots. Each FIA plot representing approximately 2,400 hectares is part of a national hexagonal grid which covers all land types and is considered an equal probability sample for the total surface area (McRoberts et al., 1999). A total of 1,224 plots were used for modeling Puerto Rico and the US Virgin Islands. A circle with a radius of 43.9 m (144 ft) was placed over each plot center. Each circle contained a 109-dot grid, which was oriented 15 degrees east of true north, with each dot separated by 8 m. Photo-interpreters evaluated each dot as being either tree or not tree. For each plot, percent tree canopy cover was calculated from these dot counts. The imagery upon which the photo interpreters based their observations was accessed through the DigitalGlobe Web Map Service –Daily Take. The Daily Take service, with an archive that goes back to 2011, is populated with the most current imagery for an area of interest from Worldview1-3 as well as GeoEye-1. The imagery is pan-sharpened RGB though not all imagery is acquired at nadir. The imagery was accessed through the DigitalGlobe Image Connect Add-in for ESRI ArcMap, downloaded from the DigitalGlobe EnhancedView Web Hosting Service (EWHS), https://rdog.digitalglobe.com/myDigitalGlobe.
References:
McRoberts, Ronald E.; Hansen, Mark H. 1999. Annual forest inventories for the north central region of the United States. Journal of Agricultural, Biological, and Environmental Statistics. 4(4): 361–371.PI_CCelevation informationDigital Elevation Models of the U.S. Virgin IslandsDEMusvi2015-02-01T00:00:00National Geophysical Data Center, NESDIS, NOAA, U.S. Department of Commerceraster digital dataclimate informationMapping the climate of Puerto Rico, Vieques and CulebraPrecip2003-08-06T00:00:00raster digital dataOregon State University Spatial Climate Analysis Service and International Institute of Tropical ForestryCreation of Landsat OLI composite. Multiple Landsat 8 scenes were selected and processed for each WRS-2 path/row. Selected scenes were acquired between 2016 and 2017. The selection process favored scenes with minimal cloud cover. An automated cloud masking algorithm, Fmask, (Zhu and Woodcock 2012) was used to remove clouds from each scene. Eight spectral bands (OLI bands 1-7 and 9) within each scene were transformed to surface reflectance. A median value was calculated using all available pixel values for each geolocation (Ruefenacht 2016). These median values were combined to create the composite image.
References:
Ruefenacht, B. 2016. Comparison of three Landsat TM compositing methods: a case study using modeled tree canopy cover. Photogrammetric Engineering & Remote Sensing 82(3):199-211.
Zhu, Z.; Woodcock, C.E. 2012. Object-based cloud and cloud shadow detection in Landsat imagery. Remote Sensing of Environment. 118(2012): 83-94.2015-06-17T00:00:00L8OLIL8OLICompCreation of Landsat OLI derivatives. Spectral derivative images were calculated from the Landsat OLI composite image. NDMI (normalized difference moisture index), NDVI (normalized difference vegetation index), and the 3-band tasseled cap transformation (Baig et al. 2014) were calculated following industry standards.
References:
Baig, M.H.A.; Zhang, L.; Shuai, T.; Tong, Q. 2014 Derivation of a tasselled cap transformation based on Landsat 8 at-satellite reflectance, Remote Sensing Letters 5(5):423-431NDMI, NDVI, TasCap2018-05-16T00:00:00L8OLICompCreation of percent tree canopy cover dataset (main process). The FS Analytical 2011 percent tree canopy cover for Puerto Rico and the US Virgin Islands dataset was created as a single unit using six Landsat WRS-2 path/rows. Seven major steps were employed to map tree canopy cover: collection of reference data, acquisition and/or creation of predictor layers, calibration of random forests regression models using reference data and predictor layers, application of those models to predict per-pixel tree canopy cover across Puerto Rico and the US Virgin Islands, development of a threshold for filtering pixels with high uncertainty, resetting canopy estimate to 0 to 100 if needed, and data stack preparation. The methodology is described further below and in Coulston et al. (2012) and Ruefenacht (2016).
Step 1: Reference data, consisting of estimated tree canopy cover at each of 1,224 FIA plot locations, were generated via photographic interpretation (PI_CC) of high spatial resolution images, as described in the Photointerpretation of Sample Plots process step. The spatial distribution of the sample points follows the FIA quasi-systematic grid (Brand et al. 2000).
Step 2: Predictor layers included Landsat 8 OLI composite imagery and spectral derivatives thereof (NDMI, NDVI, and tasseled cap); elevation data; precipitation data; EWMA (exponentially weighted moving average) data, provided by and generated by Oregon State University through an implementation of a harmonic regression-based algorithm (Brooks et al. 2012) built by Virginia Polytechnic University. The processes for creating the derived layers are described separately (see related Process Steps).
Step 3: Modeling was carried out using the random forests regression algorithm (R Core Team 2017; Breiman 2001) as outlined in the Attribute Accuracy Report above.
Step 4: The random forest model trained from the PI points was applied to the median composite image for each Landsat WRS-2 path/row included within Puerto Rico and the US Virgin Islands producing a 2-layered image. The first layer was the random forest regression estimate of percent tree canopy cover and the second layer was the standard error, which is the per-pixel square root of the variance of the random forest regression estimates from the individual trees.
Step 5: Threshold values were determined using data from 100,000 runs of random forests regression algorithm on bootstrap samples where 200 random data samples were witheld from each run. Using the observed data (the withheld random data samples) and the randomForest predicted values, t-test values were calculated using the formula (predicted - observed) / SE. SE is the standard error generated from the 500 randomForest trees used for each prediction. The t-test value at the 93rd, 95th, and 97th interval were evaluated with the 93rd interval selected as the threshold value. For each pixel, the product of the threshold value and the pixel standard error was compared to the pixel percent tree canopy value and if this product was greater than the pixel percent tree canopy, the percent tree canopy value for that pixel was set to zero; otherwise, the percent tree canopy of the pixel was left unchanged.
Step 6: Due to the use of the bias correction option in the random forests modeling, estimates could be outside the range of 0 to 100. These estimates were reset to either 0 or 100. Estimates were also rounded to the nearest integer.
Step 7: The NLCD-TCC production workflow included a step after the production of the “FS-Analytical” and “FS-Cartographic” TCC products in order to integrate three layers (2011 NLCD TCC, 2016 NLCD TCC, and a TCC change layer) into a common data stack. In this three-layer data stack, all pixels with valid TCC values (0 to 100%) in both years (2011 and 2016) met the criterion of “Time 1 TCC + change = Time 2 TCC”. To satisfy that criterion, pixels were first identified as changed or not based on analysis of disturbance data from the USFS Forest Inventory and Analysis (FIA) program and standard error values in the “FS-Analytical” TCC product. For pixels identified as changed, the pixel value in the 2016 NLCD TCC layer was taken from the 2016 “FS-Cartographic” TCC product. For pixels in which confidence in actual change was low or non-existent, the pixel value in the 2016 NLCD TCC product was set to an average of the TCC values from the 2011 and 2016 “FS-Cartographic” TCC products. Spatial filtering was also applied to clean up noise and speckle. While the integrated data stack was achieved, minor visual artifacts (e.g., very small islands of “No Change” surrounded by pixels identified as change) may still be present within the tree canopy cover products included in the overall 2016 NLCD Product Suite.
References:
Brand, G.J.; Nelson, M.D.; Wendt, D.G.; Nimerfro, K.K. 2000. The hexagon/panel system for selecting FIA plots under an annual inventory. In: McRoberts, R.E.; Reams, G.A.; Van Deusen, P.C., eds. Proceedings of the First Annual Forest Inventory and Analysis Symposium; Gen. Tech. Rep. NC-213. St. Paul, MN: U.S. Department of Agriculture, Forest Service, North Central Research Station: 8-13.
Breiman, L. 2001. Random forests. Machine Learning 45:15-32.
Brooks, E.B.; Thomas, V.A.; Wynne, R.H.; Coulston, J.W. 2012. Fitting the multitemporal curve: a fourier series approach to the missing data problem in remote sensing analysis. IEEE Transactions on Geoscience and Remote Sensing 50(9):3340-3353.
Coulston, J.W.; Moisen, G.G.; Wilson, B.T.; Finco, M.V.; Cohen, W.B.; Brewer, C.K. 2012. Modeling percent tree canopy cover: a pilot study. Photogrammetric Engineering & Remote Sensing 78(7): 715-727.
R Core Team. 2017. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL www.R-project.org.
Ruefenacht, B. 2016. Comparison of three Landsat TM compositing methods: a case study using modeled tree canopy cover. Photogrammetric Engineering & Remote Sensing 82(3):199-211.2019-10-01T00:00:00PI_CC, L8OLI, NDMI, NDVI, TasCap, DEMpr,DEMusvi, L8HRt2, Precip1363130.0000002337130.0000002102890755.000000 -219375.0000002890755.000000 189555.0000003591885.000000 189555.0000003591885.000000 -219375.0000003241320.000000 -14910.000000Layer_1255.0000000.0000008nlcd_2016_prusvi_treecanopy_20191017.img.vatTable256OIDOIDInternal feature number.ESRIOID400Sequential unique whole numbers that are automatically generated.ValueValuePercent tree canopy coverInteger000099Percent127 = No data available 255 = BackgroundCountCountDouble000RedRedInteger000GreenGreenInteger000BlueBlueInteger000OpacityOpacityInteger000dataset