Skip to main content
Advanced Search

Filters: Tags: landcover (X) > Types: Citation (X)

14 results (66ms)   

Filters
Date Range
Extensions
Types
Contacts
Categories
Tag Types
Tag Schemes
View Results as: JSON ATOM CSV
thumbnail
This landcover raster was generated through a Random Forest predictive model developed in R using a combination of image-derived and ancillary variables, and field-derived training points grouped into 18 classes. Overall accuracy, generated internally through bootstrapping, was 75.5%. A series of post-modeling steps brought the final number of land cover classes to 28.
thumbnail
The dataset includes Land Use/Land Cover types throughout the Chenier Eco-Region in Southwest Louisiana. Using the 2015 National Aerial Imagery Program (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 LandUse/LandCover (LULC) categories. This process involved stitching together more reliable sources for specific categories to...
thumbnail
The Missouri Resource Assessment Partnership (MoRAP) of the University of Missouri, in conjunction with the Oklahoma Biological Survey of the University of Oklahoma, produced a vegetation and landcover GIS data layer for the eastern portions of Oklahoma. This effort was accomplished with direction and funding from the Oklahoma Department of Wildlife Conservation and state and federal partners (particularly the Gulf Coast Prairie and Great Plains Landscape Conservation Cooperatives of the U. S. Fish and Wildlife Service). The legend for the layer is based on NatureServe’s Ecological System Classification, with finer thematic units derived from land cover and abiotic modifiers of the System unit. Data for development...
thumbnail
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....
thumbnail
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....
thumbnail
This dataset represents vegetation and landcover for Ruby Lake NWR. It was produced by the U.S. Fish and Wildlife Service, with field data collection provided by the University of Nevada, Reno. The process was iterative and took place over two calendar years and two field seasons. Additional data points were acquired in order to validate the map product and to develop a product that met a minimal accuracy level of 80%. The final classification is based on 2013 National Agricultural Imagery Program (NAIP) orthophotography, produced by the U.S. Department of Agriculture but additional datasets were also utilized, including a digital elevation model. The classification methodology uses a hybrid approach of pixel-based...
thumbnail
This layer represents land cover classes mapped within the Modoc Wildlife Refuge. Mapping was completed using a combination of field data, object-based image analysis using Feature Analyst, and photo interpretation. Source data included 2005 CIR NAIP digital aerial photography, and Modoc National Wildlife Refuge data layers. Field data was collected by USFWS staff in May and June of 2007.
thumbnail
This dataset shows the Land-Use/ Land-Cover of the Crown of the Continent with a 50km buffer.This dataset was developed by the Crown Managers Partnership, as part of a transboundary collaborative management initiative for the Crown of the Continent Ecosystem, based on commonly identified management priorities that are relevant at the landscape scale. The CMP is collaborative group of land managers, scientists, and stakeholder in the CCE. For more information on the CMP and its collaborators, programs, and projects please visit: http://crownmanagers.org/The optimal land cover products available for the CCE are the Canadian land cover distributed by GeoBase and MSDI Montana Land Use/Land Cover Datadistributed by...
thumbnail
Potential pollinator habitat was derived by ranking land use classifications and grassland quality based on ground truthing and remotely sensed features indicative of remnant prairie. High resolution (10m) land use data served as the basemap (Hartley et al 2017) from which most categories were identified. All known prairie remnants, prairie plantings, and clusters of mima mounds were delineated. Mima mounds were detected by deriving a slope at 1m scale with greater than 5% from high resolution LiDar data (3m). Mima mounds are indicative of areas in which the topsoil has not been significantly disturbed, and therefore have a higher potential to contain native prairie vegetation. Based on an in-depth literature review...
thumbnail
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....
This study addressed the potential ability to link landscape indices to stream water quality in a predominately agricultural landscape located in the Mississinewa River watershed, East-Central Indiana. A methodology for developing and analyzing landscape indices using a GIS and remotely sensed and geospatial data was applied to 30 Hydrologic Unit Code (HUC) 14-digit subwatersheds. Six indices, three representing natural area extent characteristics and three representing natural area disturbance characteristics were developed. The resulting indices were then tested to determine if they could be linked to water quality variables (Total Phosphorus, Nitrate, E.COLI, and macroinvertebrate [EPT/C] Ephemeroptera, Plecoptera,...
thumbnail
This landcover raster was generated through a Random Forest predictive model developed in R using a combination of image-derived and ancillary variables, and field-derived training points grouped into 18 classes. Overall accuracy, generated internally through bootstrapping, was 72.7%. A series of post-modeling steps brought the final number of land cover classes to 28.
thumbnail
The dataset includes Land Use/Land Cover types throughout the Chenier Eco-Region in Southwest Louisiana. Using the 2015 National Aerial Imagery Program (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 LandUse/LandCover (LULC) categories. This process involved stitching together more reliable sources for specific categories to...
thumbnail
This dataset depicts vegetation and landcover at a broad scale for Tule Lake National Wildlife Refuge. It was created through interpretation of aerial imagery (NAIP orthophotography) acquired in August 2014 by the USDA. Ecognition software was then used to create segments of the imagery and those segments were manually classified by a GIS Analyst with the help of refuge biologists and staff with expert knowledge of the local conditions. The GIS Analyst also made a reconnaissance trip to the area in the fall of 2014 to assist with image interpretation. No systematically collected field data were available to create a classification at a finer level, such as the Alliance or Associate level and so this product does...


    map background search result map search result map Oklahoma Ecological System Mapping Vegetation and Landcover, Tule Lake NWR Landcover and Vegetation, Ruby Lake NWR Land Cover, Modoc National Wildlife Refuge Charles M. Russell National Wildlife Refuge Spot Landcover Classification in Relation to Greater Sage Grouse Charles M. Russell National Wildlife Refuge Landsat 8 Landcover Classification in Relation to Greater Sage Grouse Land Use and Land Cover of the Crown of the Continent c 2015 High resolution landcover for the Western Gulf Coastal Plain of Louisiana Grassland priority rankings model for the Western Gulf Coastal Plain of Louisiana Grassland quality and pollinator habitat potential in Southwest Louisiana High resolution landcover for the Western Gulf Coastal Plain of Louisiana Grassland priority rankings model for the Western Gulf Coastal Plain of Louisiana High resolution landcover for the Western Gulf Coastal Plain of Louisiana Land Cover, Modoc National Wildlife Refuge Landcover and Vegetation, Ruby Lake NWR Vegetation and Landcover, Tule Lake NWR Grassland priority rankings model for the Western Gulf Coastal Plain of Louisiana High resolution landcover for the Western Gulf Coastal Plain of Louisiana Grassland quality and pollinator habitat potential in Southwest Louisiana Grassland priority rankings model for the Western Gulf Coastal Plain of Louisiana High resolution landcover for the Western Gulf Coastal Plain of Louisiana High resolution landcover for the Western Gulf Coastal Plain of Louisiana Charles M. Russell National Wildlife Refuge Landsat 8 Landcover Classification in Relation to Greater Sage Grouse Charles M. Russell National Wildlife Refuge Spot Landcover Classification in Relation to Greater Sage Grouse Land Use and Land Cover of the Crown of the Continent c 2015 Oklahoma Ecological System Mapping