High resolution landcover for the Western Gulf Coastal Plain of Louisiana.

Dataset Identification:

Resource Abstract:
description: The dataset includes Land Use/Land Cover types throughout the Chenier Eco-Region in Southwest Louisiana. Using the 2015 NAIP dataset (1m) as the basemap, E-Cognition image objects were derived from the multiresolution segmentation algorithm at 75 and 250 segments. Attempts to refine the data training methods using E-cognition, to extrapolate automating categories of this information to the entire map resulted with exceedingly low accuracy. Therefore, a raster was produced by piecing together several data resources, which provide reliable data for specific LULC categories. This process involved stitching together more reliable sources for specific categories to apply to higher resolution (75) segmentation product. Reference datasets include; 12,000 aerial points assigned to image objects derived from 75 segmentation settings (previously used to develop scripts for data training), mask created from NWI 2008 including water, wetland forested, upland forested and scrub/shrub categories, BOEM marsh classes, NLCD urban areas, and CDL data. The raster produced from this process was applied to the vector image objects derived from the 250 segmentation settings, using a majority filter (greater than 50 percent). The series of draft shapefiles were manually edited and merged, resulting in the final dataset.; abstract: The dataset includes Land Use/Land Cover types throughout the Chenier Eco-Region in Southwest Louisiana. Using the 2015 NAIP dataset (1m) as the basemap, E-Cognition image objects were derived from the multiresolution segmentation algorithm at 75 and 250 segments. Attempts to refine the data training methods using E-cognition, to extrapolate automating categories of this information to the entire map resulted with exceedingly low accuracy. Therefore, a raster was produced by piecing together several data resources, which provide reliable data for specific LULC categories. This process involved stitching together more reliable sources for specific categories to apply to higher resolution (75) segmentation product. Reference datasets include; 12,000 aerial points assigned to image objects derived from 75 segmentation settings (previously used to develop scripts for data training), mask created from NWI 2008 including water, wetland forested, upland forested and scrub/shrub categories, BOEM marsh classes, NLCD urban areas, and CDL data. The raster produced from this process was applied to the vector image objects derived from the 250 segmentation settings, using a majority filter (greater than 50 percent). The series of draft shapefiles were manually edited and merged, resulting in the final dataset.
Citation
Title High resolution landcover for the Western Gulf Coastal Plain of Louisiana.
creation  Date   2018-05-21T09:59:00.840174
Resource language: 
Processing environment:  
Back to top:

Resource distribution information

Digital Transfer Options
Linkage for online resource
name Dublin Core references URL
URL: https://doi.org/10.5066/F7QN658M
protocol WWW:LINK-1.0-http--link
link function information
Description URL provided in Dublin Core references element.
Linkage for online resource
name Dublin Core references URL
URL: https://doi.org/10.5066/F7QN658M
protocol WWW:LINK-1.0-http--link
link function information
Description URL provided in Dublin Core references element.

Metadata data stamp:  2018-08-06T23:08:41Z
Resource Maintenance Information
maintenance or update frequency: 
notes: This metadata record was generated by an xslt transformation from a dc metadata record; Transform by Stephen M. Richard, based on a transform by Damian Ulbricht. Run on 2018-08-06T23:08:41Z
Metadata contact - pointOfContact
organisation Name  CINERGI Metadata catalog
Contact information
Address
electronic Mail Address cinergi@sdsc.edu
Metadata language  eng
Metadata character set encoding:   utf8
Metadata standard for this record:  ISO 19139 Geographic Information - Metadata - Implementation Specification
standard version:  2007
Metadata record identifier:  urn:dciso:metadataabout:ca48137d-90fd-4bef-b8ec-0303c8a62276

Metadata record format is ISO19139 XML (MD_Metadata)