2015 Irrigated Lands for the Mountain Home Plateau: Machine Learning Generated

Mountain Home Irrigated Lands 2015 was created for use in water budget studies in Mountain Home. The area of interest was determined by Hydrology Section staff at IDWR, and a study boundary was given to GIS staff and used to clip the model output. The random forest (RF) model is a type of supervised machine learning algorithm requiring GIS staff to provide manually labeled training data. GIS staff also provide the RF model with several input features, typically raster datasets that help distinguish characteristics of irrigated lands. Mountain Home Irrigated Lands 2015 used the following as input features: • Landsat 8 [2] and Landsat 7 [3] averaged surface reflectance imagery (bands: SWIR 2, NIR, Blue, and calculated NDVI) • 10-meter digital elevation model [4] (including slope and aspect) • Height Above Nearest Drainage (HAND) [5] • PRISM Climate Dataset [6] (800 m resolution; parameters: precipitation, mean temperature, dewpoint temperature, maximum vapor pressure deficit) • OpenET METRIC Evapotranspiration [7] For additional information on the interpolation process for Landsat imagery, please see below. Additional datasets used only for labeling training data include IDWR-provided Active Water Rights Place of Use and National Agriculture Imagery Program (NAIP) [8] aerial imagery for 2015 [7]. The accuracy of Mountain Home Irrigated Lands 2015 dataset was verified by several methods. Firstly, a validation test is done by withholding a subset of the training data to evaluate how well the model classifies unseen information. Second, GIS staff will run several iterations of the model with variations of training data, with the goal of improving classification for areas consistently misclassified. This process requires GIS staff knowledge, aided by supplementary datasets, to review the area and make decisions. Once a model iteration is determined as ‘final’, a manual mask is created to correct any remaining misclassification in the dataset. Misclassification within the Mountain Home Irrigated Lands 2015 dataset was minimal, occurring primarily in the southern areas near the Snake River, as well as around reservoirs and stream channels. GIS staff manually reviewed potential misclassifications by examining Landsat 8 and Landsat 7 imagery, NAIP aerial imagery, and IDWR Active Irrigation Water Rights. References: [1] https://developers.google.com/earth-engine/apidocs/ee-classifier-smilerandomforest [2] https://developers.google.com/earth-engine/datasets/catalog/LANDSAT_LC08_C02_T1_L2 [3] https://developers.google.com/earth-engine/datasets/catalog/LANDSAT_LE07_C02_T1_L2 [4] https://developers.google.com/earth-engine/datasets/catalog/USGS_3DEP_10m [5] Donchyts, G., Winsemius, H., Schellekens, J., Erickson, T., Gao, H., Savenije, H., & van de Giesen, N. (2016). Global 30m height above the nearest drainage (HAND). Geophysical Research Abstracts, 18, EGU2016-17445-3. EGU General Assembly 2016. [6] Daly, C., Halbleib, M., Smith, J.I., Gibson, W.P., Doggett, M.K., Taylor, G.H., Curtis, J. & Pasteris, P.A. (2008). Physiographically sensitive mapping of climatological temperature and precipitation across the conterminous United States. International Journal of Climatology, 28, 2031-2064. [doi:10.1002/joc.1688] (https://doi.org/10.1002/joc.1688) [7] https://developers.google.com/earth-engine/datasets/catalog/OpenET_EEMETRIC_CONUS_GRIDMET_MONTHLY_v2_0 [8] U.S. Department of Agriculture, Farm Service Agency. (2015). National Agriculture Imagery Program (NAIP) imagery [Digital image]. U.S. Department of Agriculture. https://www.fsa.usda.gov/programs-and-services/aerial-photography/imagery-programs/naip-imagery/ Information interpolated imagery: GIS staff prepared averaged Landsat images to reduce missing data from cloud cover. Images were averaged across four periods: March 1–May 1, May 1–July 1, July 1–September 1, and September 1–November 1. These same periods were also used to average PRISM climate data. The temporal extent of other input features was filtered to March 1–November 30, 2015, where applicable.