Tim S. McKinney 2012 vector digital data Reston, VA U.S. Geological Survey http://water.usgs.gov/lookup/getspatial?ds697_SWPA_NO3_As_training David W. Anning Angela P. Paul Tim S. McKinney Jena M. Huntington Laura M. Bexfield Susan A. Thiros 2012 U.S. Geological Survey Scientific Investigations Report SIR-2012-5065 Tucson, AZ U.S. Geological Survey http://pubs.usgs.gov/ds/697/ This product "Observed, predicted, and misclassification error data for observations in the training dataset for nitrate and arsenic concentrations in basin-fill aquifers in the Southwest Principal Aquifers study" is a 1:250,000-scale point dataset and was developed as part of a regional Southwest Principal Aquifers (SWPA) study. The study examined the vulnerability of basin-fill aquifers in the southwestern United States to nitrate contamination and arsenic enrichment. Statistical models were developed by using the random forest classifier algorithm to predict concentrations of nitrate and arsenic across a model grid that represents local- and basin-scale measures of source, aquifer susceptibility, and geochemical conditions. Separate classifiers were developed for nitrate and arsenic because each constituent was expected to be affected by a different set of factors, and each factor could have a different magnitude or directional influence (increase/decrease) on concentration. For each constituent, two different classifiers were developed; a prediction classifier and a confirmatory classifier. The prediction classifiers were developed specifically to predict nitrate and arsenic concentrations in basin-fill aquifers across the SWPA study area and were based on explanatory variables representing source and susceptibility conditions. These explanatory variables were available throughout the entire SWPA study area and, therefore, did not pose a limitation for using the classifiers to predict concentrations. The confirmatory classifiers were developed to supplement the prediction classifiers in the evaluation of the conceptual model. The name, "confirmatory," reflects the classifier's purpose for evaluation of a-priori hypotheses and contrasts other general types of statistical models, such as those used for prediction or exploratory purposes. The confirmatory classifiers included the explanatory variables used in the prediction classifiers, as well as additional variables representing geochemical conditions and basin groundwater budget components. The inclusion of the geochemical and basin groundwater budget variables in the confirmatory classifiers allowed for further evaluation of the conceptual models, which was not possible with the prediction classifiers alone. The geochemical data, however, were only available at specific well locations, and consistent water-budget data were not available for every basin in the study area. The limited availability of the data for these variables constrained the confirmatory classifiers to observations from 16 case-study basins and precluded use of the confirmatory classifier for predicting concentrations across the SWPA study area. To contrast the scope of the two classifiers, the confirmatory classifiers were developed by using all available explanatory variables but with observations restricted to the 16 case-study basins, whereas the prediction classifiers were unrestricted with respect to spatial extent because these were developed by using a subset of the explanatory variables that were available throughout the study area. This dataset was developed as part of a regional Southwest Principal Aquifers (SWPA) study and for the National Water-Quality Assessment (NAWQA) Program. The dataset represents observed nitrate and arsenic concentrations that were used to train the confirmatory and prediction classifiers. The nitrate and arsenic observations, predictions, and misclassification error data for observations are part of a larger dataset of explanatory variables and model input data. Those data are archived in tabular form along with the model report. The explanatory data may be joined to this dataset via the site identifier. For more information on the development of the explanatory variables, see "Compilation and Processing of Explanatory Variables" in the "Approach and Methods" section of SIR2012_5065. 1980 2009 2012 ground condition Complete None planned -124.889549 -104.566268 44.627454 29.300033 ISO 19115 Topic Category geoscientificInformation inlandWaters environment utilitiesCommunication None Water quality Nitrate concentration Arsenic concentration Basin-fill aquifer Groundwater Groundwater contamination Groundwater susceptibility National Water-Quality Assessment Program NAWQA None Southwest United States California Utah Colorado New Mexico Arizona Nevada None These data are not intended to be used as a survey product and are for reference purposes only. Southwestern US only. Although this Federal Geographic Data Committee (FGDC) compliant metadata file is intended to document the data set in nonproprietary form, as well as ArcGIS format, this metadata file may include some ArcGIS-specific terminology. Acknowledgment of the U.S. Geological Survey would be appreciated in products derived from these data. U.S. Geological Survey Center Director mailing and physical address

Arizona Water Science Center

520 N. Park Avenue, Suite 221

Tucson Arizona 85719-5035 USA (520) 670-6671 (520) 670-5592 7:30 a.m. to 4:00 p.m. Mountain Time http://water.usgs.gov/GIS/browse/ds2012-697_SWPA_NO3_As_training.jpg Illlustration of data set jpg Microsoft Windows XP Version 5.1 (Build 2600) Service Pack 3; ESRI ArcCatalog 9.3.1.4000 Tim S. McKinney 2008 raster digital data Reston, Virginia U.S. Geological Survey http://water.usgs.gov/lookup/getspatial?sir2008-5239_swpa_agir_wu_2000 Tim S. McKinney 2008 vector digital data http://water.usgs.gov/lookup/getspatial?sir2008-5239_swpa_basin_stats Tim S. McKinney 2008 raster digital data http://water.usgs.gov/lookup/getspatial?sir2008-5239_swpa_geo Tim S. McKinney 2008 raster digital data http://water.usgs.gov/lookup/getspatial?sir2008-5239_swpa_hga Tim S. McKinney 2008 raster digital data http://water.usgs.gov/lookup/getspatial?sir2008-5239_swpa_public_supply_wu_2005 Tim S. McKinney 2012 vector digital data http://water.usgs.gov/lookup/getspatial?ds698_SWPA_NO3_As_prediction Training observations classifications summary for the prediction and confimattory random forest classifiers of nitrate and arsenic concentrations in basin-fill aquifers of the Southwest Principal Aquifers study area. Nitrate prediction classifier: Percent of observations classified in correct class, 42.3% Percent of observations classified in correct class, one class above, or one class below, 72.5 Arsenic prediction classifier: Percent of observations classified in correct class, 34.4% Percent of observations classified in correct class, one class above, or one class below, 70.2% Nitrate confirmatory classifier Percent of observations classified in correct class, 48.6% Percent of observations classified in correct class, one class above, or one class below, 80.4% Arsenic confirmatory classifier Percent of observations classified in correct class, 36.7% Percent of observations classified in correct class, one class above, or one class below, 75.0% For more information see the Nitrate and Arsenic Classifiers and Predicted Concentrations section and tables 7 and 13 of SIR-2012-5065. Tests of valid values were spot checked with input datasets. No inconsistencies were observed Complete for the basin-fill aquifers of the Southwest U.S. Not for use at scales greater than 1:250,000 None David W. Anning 2012 Reston, Virginia U.S. Geological Survey For a complete list of model input data and sources, please see SIR-2012-5065 and: Appendix 2_PedictionSet.xlsx, Appendix 1_TrainingSet.xlsx, and Table 3_List of explanatory variables.xlsx Anning and Others, 2012 2012 U.S. Geological Survey Scientific Investigations Report SIR-2012-5065 Tucson, AZ U.S. Geological Survey tabular data 1980 2009 2012 ground condition TrainingData Provided nitrate and arsenic prediction and confimatory values for training model sites. Tim S. McKinney Unpublished Material NWIS groundwater site vector digital data 2012 2012 TrainingSite Vector NWIS point locations of training model sites. Joined model prediction and training data to training sites. TrainingData TrainingSites 20100826 swpa_N03_As_training_data Vector Entity point 6234 Albers Conical Equal Area 29.500000 45.500000 -96.000000 23.000000 0.000000 0.000000 coordinate pair 1.0 1.0 meters North American Datum of 1983 Geodetic Reference System 80 6378137.000000 298.257222 ds2012-697_SWPA_NO3_As_training.shp Point feature class ESRI FID Internal feature number. ESRI Sequential unique whole numbers that are automatically generated. Shape Feature geometry. ESRI Coordinates defining the features. site_id National Water Inventory System (NWIS) site identifier USGS Unique value used to identify a well. site_lat Latitude of well in decimal degrees, NAD83. USGS 31.34538 41.998808 site_lon Longitude of well in decimal degrees, NAD83. USGS -124.251917 -105.415845 cell_id Grid cell identifier USGS Unique value used to identify a model grid cell basin_id Alluvial basin identifier USGS Unique value used to identify an alluvial basin bsn_name Alluvial basin name USGS Hydrogeologic Areas of the Southwest Principal Aquifer (SWPA) study USGS aq_name Principal aquifer name USGS U.S. Geological Survey National Atlas USGS NO3_ob_cls Nitrate observed class USGS 1 <0.50 mg/L USGS 2 0.50-0.99 mg/L USGS 3 1.0-1.9 mg/L USGS 4 2.0-4.9 mg/L USGS 5 5.0-9.9 mg/L USGS 6 >=10 mg/L USGS -999999 NoData USGS NO3_ob_mgL Nitrate observed concentration USGS <0.50 mg/L >=25 mg/L NO3_pd_cc Nitrate observed class for confimatory classifier. USGS 1 <0.50 mg/L USGS 2 0.50-0.99 mg/L USGS 3 1.0-1.9 mg/L USGS 4 2.0-4.9 mg/L USGS 5 5.0-9.9 mg/L USGS 6 >=10 USGS -999999 NoData USGS NO3_cc_mgL Nitrate observed concentration for confimatory classifier. USGS <0.50 mg/L >=25 mg/L NO3_mc_cc Nitrate misclassification error for confirmatory classifier. USGS -5 5 No units NO3_pd_pc Nitrate predicted class for predicition classifier. USGS 1 <0.50 mg/L USGS 2 0.50-0.99 mg/L USGS 3 1.0-1.9 mg/L USGS 4 2.0-4.9 mg/L USGS 5 5.0-9.9 mg/L USGS 6 >=10 mg/L USGS -999999 NoData USGS NO3_pc_mgL Nitrate predicted concentration for predicition classifier. USGS <0.50 >=10 Milligrams per liter NO3_mc_pc Nitrate misclassification error for predicition classifier. USGS -5 5 No units As_ob_cls Arsenic observed class USGS 1 <1.0 ug/L USGS 2 1.0-1.9 ug/L USGS 3 2.0-2.9 ug/L USGS 4 3.0-4.9 ug/L USGS 5 5.0-9.9 ug/L USGS 6 10-24 ug/L USGS 7 >=25 ug/L USGS -999999 NoData USGS As_ob_ugL Arsenic observed concentration USGS <1.0 >=25 Micrograms per liter As_pd_cc Arsenic predicted class for confirmatory classifier. USGS 1 <1.0 ug/L USGS 2 1.0-1.9 ug/L USGS 3 2.0-2.9 ug/L USGS 4 3.0-4.9 ug/L USGS 5 5.0-9.9 ug/L USGS 6 10-24 ug/L USGS 7 >=25 ug/L USGS -999999 NoData USGS As_cc_ugL Arsenic predicted concentration for confimatory classifier USGS <1.0 >=25 Micrograms per liter As_mc_cc Arsenic misclassification error for prediction classifier USGS -6 6 No units As_pd_pc Arsenic predicted class for prediction classifier USGS 1 <1.0 ug/L USGS 2 1.0-1.9 ug/L USGS 3 2.0-2.9 ug/L USGS 4 3.0-4.9 ug/L USGS 5 5.0-9.9 ug/L USGS 6 10-24 ug/L USGS 7 >=25 ug/L USGS -999999 NoData USGS As_pc_mgL Arsenic predicted concentration for prediction classifier USGS <1.0 >=25 Micrograms per Liter As_mc_pc Arsenic misclassification error fo prediction classifier. USGS -6 6 No units U.S. Geological Survey Ask USGS -- Water Webserver Team mailing address

445 National Center

Reston VA 20192 USA 1-888-275-8747 (1-888-ASK-USGS) http://water.usgs.gov/user_feedback_form.html Downloadable Data Although these data have been used by the U.S. Geological Survey, U.S. Department of the Interior, no warranty expressed or implied is made by the U.S. Geological Survey as to the accuracy of the data. The act of distribution shall not constitute any such warranty, and no responsibility is assumed by the U.S. Geological Survey in the use of these data, software, or related materials. The use of firm, trade, or brand names in this report is for identification purposes only and does not constitute endorsement by the U.S. Geological Survey. The names mentioned in this document may be trademarks or registered trademarks of their respective trademark owners. ESRI Shapefile Spatial and attribute information Winzip 1000 http://water.usgs.gov/GIS/dsdl/ds2012-697_SWPA_NO3_As_training.zip None. This dataset is provided by USGS as a public service. 20120205 U.S. Geological Survey Ask USGS -- Water Webserver Team mailing address

445 National Center

Reston VA 20192 USA 1-888-275-8747 (1-888-ASK-USGS) http://answers.usgs.gov/cgi-bin/gsanswers?pemail=h2oteam&subject=GIS+Datase+ds697_SWPA_NO3_As_training FGDC Content Standards for Digital Geospatial Metadata FGDC-STD-001-1998