Places of Use (POU) represent where water is used from live flow, either surface water or groundwater (e.g., springs, stream or a well), and put to beneficial use under a water right. A water right (WR) must have at least one use, and may have many uses. Uses may be consumptive, such as irrigation or domestic, or non-consumptive, such as power or instream flow. The WRURL attribute links to the water right report. For each WR, any or all points of diversion (POD) can serve any or all uses. Shapes for POUs were initially developed from GCDB as QQ or QQQ polygons based on the POU legal description. Over time, better locational information updates the POU shapes.A water right (WR) can be in one or more of six processes orstages:Application for a new WR or transfer.Permit for applicant to develop the water use.License through which IDWR has approved final configuration and amounts.Claim is a WR or Beneficial Use which has been claimed in an adjudication. Recommendation is what IDWR recommends to the court during an adjudication. A recommendation, when approved by the court, is decreed and supersedes its License, if one previously existed.Transfer of a portion of the WR or claim. Generally through a change of ownership, or change in one or more elements of the WR or claim.

This data represents the general service area of the place of use for organizations with water rights who qualify as municipalities or municipal providers under I.C. Title 42 or the 1996 Municipal Water Rights Act and who have a municipal water right on file at IDWR. The service area is for illustrative purposes. This data does not necessarily represent the boundary of city limits. Drainage Districts and Tribal boundaries are not represented in this data.This dataset is derived from the following queries of IDWR water right and recommendation databases: Status = Active, LPOU = Yes, And (WaterUse = Municipal or WaterUse = Municipal From Storage). A Large POU (LPOU) is a water right place of use for which the delivery of water is described with a digital boundary as defined by I.C. Section 42-202B(2) and authorized pursuant to I.C. Section 42-1411(2)(h). If a specific owner has multiple rights represented by different PlaceOfUseIDs, the PlaceofUseID representing the largest area is used. If there is significant divergence in location between different PlaceofUseIDs, the shapes are merged and PlaceofUseID of -999 is assigned.

This raster file represents land within the ESPA classified as either “irrigated” with a cell value of 1 or “non-irrigated” with a cell value of 0 at a 10-meter spatial resolution. These classifications were 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 “learns” the characteristics that correlate to each label based on manually classified data points, also known as training data.A variety of data can be supplied as input to the Random Forest model for it to use in making its classification determinations. Irrigation produces distinct signals in observational data that can be identified by machine learning algorithms. Additionally, datasets that provide the model with information on landscape characteristics that often influence whether irrigation is present are also useful. This dataset was classified by the Random Forest model using U.S. Geological Survey (USGS) Landsat Level 2, Collection 2, Tier 1 data from Landsat 7 and Landsat 8, Sentinel-2 MSI: MultiSpectral Instrument Level-1C data, Mapping Evapotranspiration with Internalized Calibration (METRIC) data (where available) produced by IDWR, USGS National Elevation Dataset (USGS NED) data, Height Above Nearest Drainage (HAND) data, and the U.S. Fish and Wildlife Service’s National Wetlands Inventory (FWS NWI) data. Landsat 7, Landsat 8, and HAND data are at a 30-meter spatial resolution, and the Sentinel-2, USGS NED, and FWS NWI data are at a 10-meter spatial resolution. The Cropland Data Layer (CDL) from the U.S. Department of Agriculture National Agricultural Statistics Service (USDA NASS), Active Water Rights Place of Use (POU) data from IDWR, and National Agriculture Imagery Program (NAIP) data from the USDA Farm Service Agency (FSA) were also used in determining irrigation status for the manually classified training data points but were not used for the machine learning model predictions. The final model results were manually reviewed prior to release, however, no extensive ground truthing process was implemented. A wetlands mask was applied using FWS NWI data for areas without overlapping irrigation POUs or locations manually determined to have potential irrigation. “Speckling”, or small areas of incorrectly classified pixels, was reduced by using the Boundary Clean smoothing tool in ArcGIS with a descending sorting type. A limited number of manual corrections were also made to improve the accuracy of the results in areas the model struggled with.Due to the large size of the ESPA, imagery had to be processed and input to the Random Forest model in 6 separate “sub-regions” (see Processing Steps). The availability of images varied by sub-region and is outlined for each data source in Processing Steps.

This raster file represents land within the ESPA classified as either “irrigated” with a cell value of 1 or “non-irrigated” with a cell value of 0 at a 10-meter spatial resolution. These classifications were 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 “learns” the characteristics that correlate to each label based on manually classified data points, also known as training data.A variety of data can be supplied as input to the Random Forest model for it to use in making its classification determinations. Irrigation produces distinct signals in observational data that can be identified by machine learning algorithms. Additionally, datasets that provide the model with information on landscape characteristics that often influence whether irrigation is present are also useful. This dataset was classified by the Random Forest model using U.S. Geological Survey (USGS) Landsat Level 2, Collection 2, Tier 1 data from Landsat 7 and Landsat 8, Sentinel-2 MSI: MultiSpectral Instrument Level-1C data, Mapping Evapotranspiration with Internalized Calibration (METRIC) data (where available) produced by IDWR, USGS National Elevation Dataset (USGS NED) data, Height Above Nearest Drainage (HAND) data, and the U.S. Fish and Wildlife Service’s National Wetlands Inventory (FWS NWI) data. Landsat 7, Landsat 8, and HAND data are at a 30-meter spatial resolution, and the Sentinel-2, USGS NED, and FWS NWI data are at a 10-meter spatial resolution. The Cropland Data Layer (CDL) from the U.S. Department of Agriculture National Agricultural Statistics Service (USDA NASS), Active Water Rights Place of Use (POU) data from IDWR, and National Agriculture Imagery Program (NAIP) data from the USDA Farm Service Agency (FSA) were also used in determining irrigation status for the manually classified training data points but were not used for the machine learning model predictions. The final model results were manually reviewed prior to release, however, no extensive ground truthing process was implemented. A wetlands mask was applied using FWS NWI data for areas without overlapping irrigation POUs or locations manually determined to have potential irrigation. “Speckling”, or small areas of incorrectly classified pixels, was reduced by using the Boundary Clean smoothing tool in ArcGIS with a descending sorting type. A limited number of manual corrections were also made to improve the accuracy of the results in areas the model struggled with.Due to the large size of the ESPA, imagery had to be processed and input to the Random Forest model in 6 separate “sub-regions” (see Processing Steps). The availability of images varied by sub-region and is outlined for each data source in Processing Steps.

This raster file represents land within the Mountain Home Study Area classified as either “irrigated” with a cell value of 1 or “non-irrigated” with a cell value of 0 at a 30-meter spatial resolution. These classifications were 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 “learns” the characteristics that correlate to each label based on manually classified data points, also known as training data.A variety of data can be supplied as input to the Random Forest model for it to use in making its classification determinations. Irrigation produces distinct signals in observational data that can be identified by machine learning algorithms. Additionally, datasets that provide the model with information on landscape characteristics that often influence whether irrigation is present are also useful. This dataset was classified by the Random Forest model using Collection 1 Tier 1 top-of-atmosphere reflectance data from Landsat 5 and Landsat 7, United States Geological Survey National Elevation Dataset (USGS NED) data, and Height Above Nearest Drainage (HAND) data. Landsat 5, Landsat 7, and HAND data are at a 30-meter spatial resolution, and the USGS NED data are at a 10-meter spatial resolution. The Cropland Data Layer (CDL) from the United States Department of Agriculture National Agricultural Statistics Service (USDA NASS), Active Water Rights Place of Use (POU) data from IDWR, and National Agriculture Imagery Program (NAIP) data from the USDA Farm Service Agency (FSA) were also used in determining irrigation status for the manually classified training data points but were not used for the machine learning model predictions. The final model results were manually reviewed prior to release, however, no extensive ground truthing process was implemented. A wetlands mask was applied using Fish and Wildlife Service’s National Wetlands Inventory (FWS NWI) data for areas without overlapping irrigation place of use areas or locations manually determined to have potential irrigation. “Speckling”, or small areas of incorrectly classified pixels, was reduced by a majority filter smoothing technique using a kernel of 8 nearest neighbors. A limited number of manual corrections were made to correct for missing data due to Landsat 7 ETM+ Scan Line Corrector gaps (https://www.usgs.gov/faqs/what-landsat-7-etm-slc-data). These data have also been snapped to same grid used with IDWR’s Mapping EvapoTranspiration using high Resolution and Internalized Calibration (METRIC) evapotranspiration data. Information regarding Landsat imagery:Landsat 5 and Landsat 7 Collection 1 Tier 1 top-of-atmosphere reflectance images that overlapped the area of interest were used in this analysis. Images were filtered to exclude those that were more than 70% cloud covered, resulting in 35 Landsat 5 and 35 Landsat 7 images for the analysis period of 2010-03-01 to 2010-10-27. Normalized Difference Vegetation Index (NDVI), Band 1 (Blue) and Band 7 (SWIR2) values were interpolated for the following dates: 2010-04-15, 2010-05-15, 2010-06-14, 2010-07-14, 2010-08-13, and 2010-09-12 using image values from up to 45 days before and after each interpolation date.