2021 Irrigated Lands for the Eastern Snake Plain Aquifer: Machine Learning Generated

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.