2010 Irrigated Lands for the Mountain Home Plateau: Machine Learning Generated

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.