{"accessLevel": "public", "bureauCode": ["010:12"], "contactPoint": {"@type": "vcard:Contact", "fn": "Arizona Water Science Center", "hasEmail": "mailto:jpmacy@usgs.gov"}, "description": "This product \"Observed, predicted, and misclassification error data for observations in the \ntraining dataset for nitrate and arsenic   concentrations in basin-fill aquifers in the Southwest \nPrincipal Aquifers study\" is a 1:250,000-scale point dataset and was developed as part of a \nregional Southwest Principal Aquifers (SWPA) study. The study examined the vulnerability \nof basin-fill aquifers in the southwestern United States to nitrate contamination and arsenic \nenrichment. Statistical models were developed by using the random forest classifier algorithm  \nto predict concentrations of nitrate and arsenic across a model grid that represents local- and \nbasin-scale measures of source, aquifer susceptibility, and geochemical conditions.\n\t\t\nSeparate classifiers   were developed for nitrate and arsenic because each constituent was \nexpected to be affected by a different set of factors, and each factor could have a different \nmagnitude or directional influence (increase/decrease) on concentration. For each constituent, \ntwo different classifiers were developed; a prediction classifier and a confirmatory classifier. \nThe prediction classifiers were developed specifically to predict nitrate and arsenic \nconcentrations in basin-fill aquifers across the SWPA study area and were based on \nexplanatory variables representing source and susceptibility conditions. These explanatory \nvariables were available throughout the entire SWPA study area and, therefore, did not pose \na limitation for using the classifiers to predict concentrations.\n\t\t\nThe confirmatory classifiers were developed to supplement the prediction classifiers in the \nevaluation of the conceptual model. The name, \"confirmatory,\" reflects the classifier's purpose \nfor evaluation of a-priori hypotheses and contrasts other general types of statistical models, \nsuch as those used for prediction or exploratory purposes. The  confirmatory classifiers \nincluded the explanatory variables used in the prediction classifiers, as well as additional \nvariables representing geochemical conditions and basin groundwater budget components. \nThe inclusion of the geochemical and basin groundwater budget variables in the confirmatory \nclassifiers allowed for further evaluation of the conceptual models, which was not possible \nwith the prediction classifiers alone. The geochemical data, however, were only available at \nspecific well locations, and consistent water-budget data were not available for every basin \nin the study area. The limited availability of the data for these variables constrained the \nconfirmatory classifiers to observations from 16 case-study basins and precluded use of \nthe confirmatory classifier for predicting concentrations across the SWPA study area. To \ncontrast the scope of the two classifiers, the confirmatory classifiers were developed by \nusing all available explanatory variables but with observations restricted to the 16 case-study \nbasins, whereas the prediction classifiers were unrestricted with respect to spatial extent \nbecause these were developed by using a subset of the explanatory variables that were \navailable throughout the study area.", "distribution": [{"@type": "dcat:Distribution", "accessURL": "https://doi.org/10.5066/P9H5EAVZ", "description": "Landing page for access to the data", "format": "XML", "mediaType": "application/http", "title": "Digital Data"}, {"@type": "dcat:Distribution", "description": "The metadata original format", "downloadURL": "https://data.usgs.gov/datacatalog/metadata/USGS.1d589b73-af80-4229-bd58-c62dd4192bc4.xml", "format": "XML", "mediaType": "text/xml", "title": "Original Metadata"}], "identifier": "http://datainventory.doi.gov/id/dataset/USGS_1d589b73-af80-4229-bd58-c62dd4192bc4", "keyword": ["Nitrate concentration", "inlandWaters", "Colorado", "environment", "Utah", "Basin-fill aquifer", "Southwest United States", "utilitiesCommunication", "Arsenic concentration", "Water quality", "Arizona", "NAWQA", "geoscientificInformation", "California", "Groundwater", "Groundwater susceptibility", "National Water-Quality Assessment Program", "Nevada", "Groundwater contamination", "New Mexico", "USGS:1d589b73-af80-4229-bd58-c62dd4192bc4"], "modified": "2020-11-17T00:00:00Z", "publisher": {"@type": "org:Organization", "name": "U.S. Geological Survey"}, "spatial": "-124.889549, 29.300033, -104.566268, 44.627454", "theme": ["geospatial"], "title": "Observed, predicted, and  misclassification error data for observations in the training datset for nitrate and arsenic concentrations in basin-fill aquifers in the Southwest Principal Aquifers study."}