Skip to main content
Advanced Search

Filters: Categories: Data (X) > partyWithName: U.S. Geological Survey - ScienceBase (X)

Folders: ROOT > ScienceBase Catalog > National and Regional Climate Adaptation Science Centers > North Central CASC > FY 2012 Projects ( Show direct descendants )

4 results (8ms)   

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
Training points collected in the field between 2012 and 2013 were grouped into 18 classes: Forested Burn (66), Foothill Woodland Steppe Transition (73), Greasewood Flat (73), Greasewood Steppe (239), Greasewood Sage Steppe (277), Great Plains Badlands (166), Great Plains Riparian (255), Low Density Sage Steppe (776), Medium Density Sage Steppe (783), Mixed Grass Prairie (555), Mixed Grass Prairie Burned (278), Ponderosa Pine Woodland and Shrubland (512), Riparian Floodplain (223), Semi-Desert Grassland (103), Sparsely Vegetated Mixed Shrub (252), Silver Sage Flat (70) , Silver Sage Steppe (64), and Water (246). When insufficient field data were available for a class, we augmented it through photointerpretation of...
This code was used in a simulated decision analysis project designed to evaluate the value of different kinds of information with regard to making optimal investments in invasive plant control programs. The code was developed in the R programming environment. The file "sim_code.R" contains the initialization of the parameters and analysis; the file "pop_sim.ccp" is a C++ program that executes the actual simulation and returns the results to R. We developed a hypothetical scenario in which a manager is tasked with control of invasive plants on 100 management units each 100 ha in size. 90 of these units were assumed to be under private management and 10 were assumed to be conservation units (i.e. under public management)....
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.


    map background search result map search result map 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 Training Points Training Points 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