This data set contains 4-band natural color and false color infrared imagery from the National Agricultural Imagery Program (NAIP). NAIP acquires digital ortho imagery during the agricultural growing seasons in the continental U.S. A primary goal of the NAIP program is to enable availability of ortho imagery within one year of acquisition. The source files are 1 meter ground sample distance (GSD) ortho imagery rectified to a horizontal accuracy of within +/- 6 meters of reference digital ortho quarter quads (DOQQ's) from the National Digital Ortho Program (NDOP) or from NAIP. The tiling format of NAIP imagery is based on a 3.75' x 3.75' quarter quadrangle with a 300 meter buffer on all four sides. NAIP imagery is formatted to the UTM coordinate system using NAD83. NAIP imagery may contain as much as 10% cloud cover per tile. The natural color county mosaic files downloadable from the USDA NRCS Geospatial Data Gateway were generated by compressing NAIP imagery that cover the county extent. MrSID compression was used. Target values for the compression ratio are (15:1). (Note: The Minnesota Geospatial Information Office (MnGeo) has created this metadata record to describe the entire NAIP 2013 dataset, using information from Farm Service Agency metadata. Each natural color county file available from the USDA NRCS Geospatial Data Gateway is accompanied by the original FSA metadata for that county.)

FEMA Framework Basemap datasets comprise six of the seven FGDC themes of geospatial data that are used by most GIS applications (Note: the seventh framework theme, orthographic imagery, is packaged in a separate NFIP Metadata Profile): cadastral, geodetic control, governmental unit, transportation, general structures, hydrography (water areas & lines. These data include an encoding of the geographic extent of the features and a minimal number of attributes needed to identify and describe the features. (Source: Circular A16, p. 13) This data set contains 3-band natural color imagery from the National Agricultural Imagery Program (NAIP). NAIP acquires digital ortho imagery during the agricultural growing seasons in the continental U.S. A primary goal of the NAIP program is to enable availability of ortho imagery within one year of acquisition. The source files are 1 meter ground sample distance (GSD) ortho imagery rectified to a horizontal accuracy of within +/- 5 meters of reference digital ortho quarter quads (DOQQ's) from the National Digital Ortho Program (NDOP) or from NAIP. The tiling format of NAIP imagery is based on a 3.75' x 3.75' quarter quadrangle with a 300 meter buffer on all four sides. NAIP imagery is formatted to the UTM coordinate system using NAD83. NAIP imagery may contain as much as 10% cloud cover per tile. This file was generated by compressing NAIP imagery that cover the county extent. MrSID compression was used. Target values for the compression ratio are (15:1). (Note: The Minnesota Geospatial Information Office (MnGeo) has created this metadata record to describe the entire NAIP2009 dataset, using information from Farm Service Agency metadata. Each county file is accompanied by the original FSA metadata for that county.)

A high-resolution (1-meter) land cover classification raster dataset was completed for three different geographic areas in Minnesota: Duluth, Rochester, and the seven-county Twin Cities Metropolitan area. This classification was created using high-resolution multispectral National Agriculture Imagery Program (NAIP) leaf-on imagery (2015), spring leaf-off imagery (2011- 2014), Multispectral derived indices, LiDAR data, LiDAR derived products, and other thematic ancillary data including the updated National Wetlands Inventory, LiDAR building footprints, airport, OpenStreetMap roads and railroads centerlines. These data sets were integrated using an Object-Based Image Analysis (OBIA) approach to classify 12 land cover classes: Deciduous Tree Canopy, Coniferous Tree Canopy, Buildings, Bare Soil, other Paved surface, Extraction, Row Crop, Grass/Shrub, Lakes, Rivers, Emergent Wetland, Forest and Shrub Wetland.

We mapped the 12 classes by using an OBIA approach through the creation of customized rule sets for each area. We used the Cognition Network Language (CNL) within the software eCognition Developer to develop the customized rule sets. The eCognition Server was used to execute a batch and parallel processing which greatly reduced the amount of time to produce the classification. The classification results were evaluated for each area using independent stratified randomly generated points. Accuracy assessment estimators included overall accuracies, producers accuracy, users accuracy, and kappa coefficient. The combination of spectral data and LiDAR through an OBIA method helped to improve the overall accuracy results providing more aesthetically pleasing maps of land cover classes with highly accurate results.