{
 "culture": "en-US",
 "name": "",
 "guid": "",
 "catalogPath": "",
 "snippet": "This dataset represents the footprints for Irrigated Lands raster and vector data for Southern Idaho. \n\nThe raster data is a two-class land classification (either irrigated or non-irrigated) determined at the pixel level by a Random Forest supervised machine learning methodology. Random Forest models are often used to classify large datasets accurately and efficiently by assigning each pixel to one of a pre-determined set of labels or groups. The model works by using decision trees that split the data based on characteristics that make the resulting groups as different from each other as possible. The model \u201clearns\u201d the characteristics that correlate to each label based on manually classified data points, also known as training data.\n\nThe vector data is a three-class land classification (irrigated, non-irrigated, or semi-irrigated) generated from manual image interpretation of aerial photos and satellite imagery. Determination of irrigation status relies primarily on IDWR's water right place of use and IDWR's water rights database. Many of the hand digitized products are produced to support water budget studies and groundwater flow models.",
 "description": "<DIV STYLE=\"text-align:Left;\"><DIV><DIV><P><SPAN>The raster data may be downloaded as a zip file from ArcGIS Online or IDWR's Data Hub. The vector data may be loaded as a map image service into a geographic information system. Links to access the data are provided in the pop-up of the dataset. <\/SPAN><\/P><\/DIV><\/DIV><\/DIV>",
 "summary": "This dataset represents the footprints for Irrigated Lands raster and vector data for Southern Idaho. \n\nThe raster data is a two-class land classification (either irrigated or non-irrigated) determined at the pixel level by a Random Forest supervised machine learning methodology. Random Forest models are often used to classify large datasets accurately and efficiently by assigning each pixel to one of a pre-determined set of labels or groups. The model works by using decision trees that split the data based on characteristics that make the resulting groups as different from each other as possible. The model \u201clearns\u201d the characteristics that correlate to each label based on manually classified data points, also known as training data.\n\nThe vector data is a three-class land classification (irrigated, non-irrigated, or semi-irrigated) generated from manual image interpretation of aerial photos and satellite imagery. Determination of irrigation status relies primarily on IDWR's water right place of use and IDWR's water rights database. Many of the hand digitized products are produced to support water budget studies and groundwater flow models.",
 "title": "Footprint Index for Irrigated Lands Data - Raster and Vector",
 "tags": [
  "Supervised Land Classification",
  "Hand Digitizing",
  "Machine Learning",
  "Random Forest",
  "Water Budget",
  "Monitoring",
  "Hydrology",
  "Groundwater",
  "Surface Water",
  "Irrigated Areas",
  "Irrigation",
  "Irrigated",
  "Non-Irrigated",
  "Regulatory",
  "Farming",
  "Idaho",
  "ID",
  "Water",
  "Water Use"
 ],
 "type": "",
 "typeKeywords": [],
 "thumbnail": "",
 "url": "",
 "minScale": 150000000,
 "maxScale": 5000,
 "spatialReference": "",
 "accessInformation": "Idaho Department of Water Resources (IDWR)",
 "licenseInfo": "",
 "portalUrl": ""
}