James A. Kingsbury Katherine J. Knierim Connor J. Haugh 20200922 tabular digital data https://doi.org/10.5066/P9CXX7LN James A Kingsbury Katherine J Knierim Connor J Haugh 2020 publication USGS ScienceBase USGS ScienceBase https://doi.org/10.5066/P9CXX7LN Groundwater is a vital resource to the Mississippi embayment region of the central United States. Regional and integrated assessments of water availability that link physical flow models and water quality in principal aquifer systems provide context for the long-term availability of these water resources. An innovative approach using machine learning was employed to predict groundwater pH across drinking water aquifers of the Mississippi embayment. The region includes two principal regional aquifer systems; the Mississippi River Valley alluvial (MRVA) aquifer and the Mississippi embayment aquifer system that includes several regional aquifers and confining units. Based on the distribution of groundwater use for drinking water, the modeling effort was focused on the MRVA, Middle Claiborne aquifer (MCAQ), and Lower Claiborne aquifer (LCAQ)of the Mississippi embayment aquifer system. Boosted regression tree (BRT) models (Elith and others, 2008; Kuhn and Johnson, 2013) were used to predict pH to 1-km raster grid cells of the National Hydrologic Grid (Clark and others, 2018). Predictions were made for 7 aquifer layers (1 MRVA, 4 MCAQ, 2 LCAQ) following the hydrogeologic framework used in a regional groundwater flow model (Hart and others, 2008). Explanatory variables for the BRT models included attributes associated with well position and construction, surficial variables, and variables extracted from a MODFLOW groundwater flow model for the MISE (Haugh and others, 2020a,b). For a full description of modeling workflow see Knierim and others (2020). The machine-learning model predictions and groundwater quality rasters support the SIM by Kingsbury and others (2020). Clark, B.R., Barlow, P.M., Peterson, S.M., Hughes, J.D., Reeves, H.W., and Viger, R., 2018, National-Scale Grid to Support Regional Groundwater Availability Studies and a National Hydrogeologic Framework: U.S. Geological Survey Data Release, https://doi.org/10.5066/F7P84B24. Elith, J., Leathwick, J.R., and Hastie, T., 2008, A working guide to boosted regression trees: Journal of Animal Ecology, v. 77, no. 4, p. 802–813. Hart, R.M., Clark, B.R., and Bolyard, S.E., 2008, Digital Surfaces and Thicknesses of Selected Hydrogeologic Units within the Mississippi Embayment Regional Aquifer Study (MERAS): U.S Geological Survey Scientific Investigations Report 2008–5098. Haugh, C.J., Killian, C.D., and Barlow, J.R.B., 2020a, MODFLOW-2005 model used to evaluate water-management scenarios for the Mississippi Delta: U.S. Geological Survey Data Release, https://doi.org/10.5066/P9906VM5. Haugh, C.J., Killian, C.D., and Barlow, J.R.B., 2020b, Simulation of water-management scenarios for the Mississippi Delta: U.S. Geological Survey Scientific Investigations Report 2019–5116, http://pubs.er.usgs.gov/publication/sir20195116. Knierim, K.J., Kingsbury, J.A., Haugh, C.J., and Ransom, K.M. 2020, Using boosted regression tree models to predict salinity in Mississippi embayment aquifers, Journal of the American Water Resources Association. Kuhn, M., and Johnson, K., 2013, Applied Predictive Modeling: Springer, New York, New York, 595 p. Ransom, K.M., Nolan, B.T., Traum, A.J., Faunt, C.C., Bell, A.M., Gronberg, J.A.M., Wheeler, D.C., Rosecrans, C.Z., Jurgens, B., Schwarz, G.E., Belitz, K., Eberts, S.M., Kourakos, G., and Harter, T., 2017, A hybrid machine learning model to predict and visualize nitrate concentration throughout the Central Valley aquifer, California, USA: Science of The Total Environment, v. 601–602, p. 1160–1172, https://doi.org/10.1016/j.scitotenv.2017.05.192. 19600101 20190101 observed Complete None planned -94.1084 -86.7600 37.4605 31.1998 Marine Realms Information Bank (MRIB) keywords aquifer USGS Thesaurus groundwater mathematical modeling groundwater quality None machine learning boosted regression tree USGS Metadata Identifier USGS:5d77ee28e4b0c4f70d020b78 Common geographic areas Arkansas Mississippi Louisiana Tennessee Kentucky Alabama None. Please see 'Distribution Info' for details. 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 this data, software, or related materials. Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government. This dataset may be redistributed if it is not edited and is properly referenced. Although USGS intends to make this server available 24 hours a day, seven days a week, timely delivery of data and products from this server through the Internet is not guaranteed. James A Kingsbury U.S. Geological Survey, Southeast Region Hydrologist mailing address

640 Grassmere Park, Suite 100

Nashville TN 37211 United States 615-837-4700 jakingsb@usgs.gov The root mean square errors of raster cell predictions are available in the companion Scientific Investigations Map (Kingsbury and others 2020). Rasters were checked for correct missing data values (-9999). Text and comma separated values files were checked for consistent variable names and definitions. Raster predictions for pH—for model layers corresponding to the Mississippi River Valley alluvial aquifer (MRVA), middle Claiborne aquifer (MCAQ), and lower Claiborne aquifer (LCAQ) are considered complete for this publication. Groundwater quality samples used to model the predictions were collected from 1960 to 2018. Horizontal accuracy (or location accuracy) of source data (groundwater well samples) varies by well but can range from plus or minus 0.01 second to 1 minute or be unknown. Most wells were accurate between 1 and 10 seconds. Groundwater quality samples at wells were used in machine-learning models to make continuous predictions of pH to raster cells of the 1-kilometer resolution national hydrologic grid (NHG) for the extent of MRVA, MCAQ, and LCAQ model layers. Depth of groundwater quality predictions was calculated by subtracting the midpoint of the groundwater flow model layer (from Haugh 2019) from land surface altitude extracted from 10-meter Digital Elevation Model data (U.S. Geological Survey, 2014) with an accuracy of 10 feet. Model layer altitude was in feet above North American Vertical Datum of 1988 (NAVD 1988). See source data for further details of vertical accuracy. Kenneth Belitz Richard B. Moore Terri L. Arnold Jennifer B. Sharpe J. J. Starn 2019 publication Washington, D.C. American Geophysical Union (AGU) https://doi.org/10.1029/2019WR025908 Digital and/or Hardcopy 2019 publication date Belitz and others (2019) Multi-order Hydrologic Position Brian R. Clark Rheannon M. Hart 2009 vector digital data Reston, VA U.S. Geological Survey http://pubs.er.usgs.gov/publication/sir20095172 Digital and/or Hardcopy 2009 publication date Clark and Hart (2009) faults Joseph S. Duval John M. Carson Peter B. Holman Arthur G. Darnley 2005 raster digital data Reston, VA U.S. Geological Survey http://pubs.er.usgs.gov/publication/ofr20051413 Digital and/or Hardcopy 2005 publication date Duval and others (2005) National Uranium Resource Evaluation James A. Falcone 2015 raster digital data Reston, VA US Geological Survey https://doi.org/10.3133/ds948 Digital and/or Hardcopy 1974 observed Falcone (2015) land use/land cover, 1974 James A. Falcone 2016 raster digital data https://www.sciencebase.gov U.S. Geological Survey https://doi.org/10.5066/f74j0c6m Digital and/or Hardcopy 1990 ground condition Falcone (2016) Population Rheannon M. Hart Brian R. Clark Susan E. Bolyard 2008 raster digital data Reston, VA U.S. Geological Survey http://pubs.er.usgs.gov/publication/sir20085098 Digital and/or Hardcopy 2008 publication date Hart and others (2008) hydrogeologic framework Connor J. Haugh Courtney D. Killian Jeannie R.B. Barlow 2020 application/service U.S. Geological Survey Data Release -- Reston, VA U.S. Geological Survey https://doi.org/10.5066/P9906VM5 Digital and/or Hardcopy 2020 publication date Haugh and others (2020a) MODFLOW groundwater-flow model explanatory variables Connor J. Haugh Courtney D. Killian Jeannie R.B. Barlow 2020 application/service U.S. Geological Survey Scientific Investigations Report 2019–5116 Reston, VA U.S. Geological Survey https://doi.org/10.3133/sir20195116 Digital and/or Hardcopy 2020 publication date Haugh and others (2020b) Simulation of water-management scenarios Connor J. Haugh James A. Kingsbury Katherine J. Knierim 2020 raster digital data Digital and/or Hardcopy 2020 publication date Haugh and others (2020) groundwater flow model, age derived from particle tracks Katherine J Knierim James A Kingsbury Connor J Haugh 2019 raster digital data https://www.sciencebase.gov U.S. Geological Survey https://doi.org/10.5066/p9fzv4ed Digital and/or Hardcopy 2019 publication date Knierim and others (2019) Well depth and altitude Md Shahriar Pervez Jesslyn F. Brown 2010 publication Remote Sensing vol. 2, issue 10 Reston, VA MDPI AG p. 2388-2412 https://doi.org/10.3390/rs2102388 Digital and/or Hardcopy 2002 2012 observed Pervez and Brown (2010) MIrAD-US Jeffrey D. Phillips Joseph S. Duval Russell A. Ambroziak 1993 raster digital data Reston, VA U.S. Geological Survey http://pubs.er.usgs.gov/publication/ds9 Digital and/or Hardcopy 1993 publication date Phillips and others (1993) Bouguer gravity M. Reitz W.E. Sanford G.B. Senay J. Cazenas 2017 raster digital data JAWRA Journal of the American Water Resources Association vol. 53, issue 4 n/a Wiley p. 961-983 https://doi.org/10.1111/1752-1688.12546 Digital and/or Hardcopy 2017 publication date Reitz and others (2017) empirical water balance David B. Smith William F. Cannon Laurel G. Woodruff Federico Solano James E. Kilburn David L. Fey 2014 raster digital data Reston, VA U.S. Geological Survey http://pubs.er.usgs.gov/publication/ds801 Digital and/or Hardcopy 2014 publication date Smith and others (2014) soil geochemistry Soil Survey Staff 2016 tabular digital data https://gdg.sc.egov.usda.gov/ Digital and/or Hardcopy 2016 publication date Soil Survey Staff (2016) soil geochemistry (pH) U.S. Geological Survey 2016 raster digital data https://viewer.nationalmap.gov/basic/?basemap=b1&category=ned,nedsrc&title=3DEP%20View Digital and/or Hardcopy 2016 publication date U.S. Geological Survey (2016) Surface elevation U.S. Geological Survey 2017 tabular digital data Reston, VA U.S. Geological Survey https://doi.org/10.5066/f7p55kjn Digital and/or Hardcopy 1960 2019 observed NWIS (2017) water-quality data Samantha Renee Wacaster Jimmy M. Clark D.A. Westerman Wade Kress 2018 vector digital data https://www.sciencebase.gov U.S. Geological Survey https://doi.org/10.5066/f7n878qn Digital and/or Hardcopy 2018 publication date Wacaster and others (2018) Saucier geomorphology Michael Wieczorek 2014 publication Reston, VA US Geological Survey https://doi.org/10.3133/ds866 Digital and/or Hardcopy 2014 publication date Wieczorek (2014) soil physical properties David M. Wolock 2003 raster digital data Reston, VA U.S. Geological Survey https://water.usgs.gov/GIS/metadata/usgswrd/XML/rech48grd.xml Digital and/or Hardcopy 2003 publication date Wolock (2003) recharge from base-flow index R. K. Zimmerman 1992 publication Houston, Texas Gulf Coast Association of Geological Societies 42 http://archives.datapages.com/data/gcags/data/042/042001/0401.htm Digital and/or Hardcopy 1992 publication date Zimmerman (1992) faults For a full explanation of machine-learning modeling steps see the article Knierim and others 2020. 20191001 Albers Conical Equal Area 29.5 45.5 -96.0 23.0 0.0 0.0 coordinate pair 0.6096 0.6096 meters WGS_1984 WGS_84 6378137.0 298.257223563 North American Vertical Datum of 1988 1 feet Implicit coordinate modelgeoref.txt text file of model corners Producer Defined File contents Related publication and data release citations and projection information Producer defined File provides the corners of the model coordinates in the USA Continguous Albers Equal Area Conic USGS WGS 1984 projection. BRT_pH.R R script to produce model output Producer Defined ExpVars.csv Comma-separated-value (CSV) file of explanatory variable names, descriptions, and units. Use for definitions in Inputwells_WQ.txt and rasstack_WQ_XXXX.csv files (where 'WQ' is the water-quality parameter and 'XXXX' is the model layer). Producer Defined VarName Name of explanatory variable Producer Defined explanatory variable short names Dataset Dataset grouping of explanatory variable Producer Defined Bouguer gravity variables extracted from Bouger gravity Producer defined empirical water balance variables extracted from an empirical water balance Producer defined groundwater flow model, age derived from particle tracks variables extracted from groundwater age Producer defined hydrogeologic framework variables related to hydrogeologic framework for the Mississippi embayment Producer defined land use/land cover, 1974 variables extracted from land use/land cover 1974 Producer defined MIrAD-US variables extracted from MODIS irrigated lands Producer defined MODFLOW groundwater flow model variables extracted from a MODFLOW groundwater flow model Producer defined multi-order hydrologic position variables extracted from multi-order hydrologic position Producer defined NURE variables extracted from National Uranium Resource Evaluation Producer defined Population variables extracted from population in 1990 Producer defined recharge variables extracted from base-flow index recharge Producer defined Saucier geomorphology variables extracted from Saucier's geomorphic regions of the Mississippi River alluvial plain Producer defined soil geochemistry variables extracted from soil geochemistry dataset Producer defined soil physical properties variables extracted from soil physical properties Producer defined well geometry variables related to well position within aquifer system Producer defined Description Detailed description of explanatory variable Producer Defined descriptive names for explanatory variables Units Units of explanatory variable Producer Defined Units of measure for explanatory variables Used in final model Flag indicating variable used in the final pH model Producer Defined x used in model Producer defined Source In-text citation for explanatory variable source, see "Citation Info" in this metadata xml file for full reference Producer Defined Sources of data for the explanatory variables README.txt Read me file describing folder organization for model archive Producer Defined File contents Related information and metadata for file structure associated with data release and model archive Producer defined File provides description of folder structure, files, and instructions for reproducing model output This data release includes groundwater quality prediction rasters for pH which was predicted using Boosted Regression Tree (BRT) machine-learning models. Rasters were produced for 7 model layers following the hydrogeologic framework for the MODFLOW groundwater flow model of the Mississippi Embayment from Clark and Hart (2009): 1 for Mississippi River Valley Alluvial aquifer (MRVA), 4 for Middle Claiborne aquifer (MCAQ), and 2 for Lower Claiborne aquifer (LCAQ). Depth of groundwater quality predictions vary for each layer and corresponding depth rasters are also included. For a full explanation of methods, see the journal article Knierim and others (2020) that uses the same methods to predict specific conductance and chloride for the same model layers. See README.txt for explanation of file folder structure and how to run the BRT_pH.R script. Kingsbury, J.A., Knierim, K.J., and Haugh, C.J., 2020, Prediction grids of pH for the Mississippi River Valley Alluvial and Claiborne Aquifers: U.S. Geological Survey data release, https://doi.org/10.5066/P9CXX7LN. GS ScienceBase U.S. Geological Survey mailing address

Denver Federal Center, Building 810, Mail Stop 302

Denver CO 80225 United States 1-888-275-8747 sciencebase@usgs.gov Unless otherwise stated, all data, metadata and related materials are considered to satisfy the quality standards relative to the purpose for which the data were collected. Although these data and associated metadata have been reviewed for accuracy and completeness and approved for release by the U.S. Geological Survey (USGS), no warranty expressed or implied is made regarding the display or utility of the data on any other system or for general or scientific purposes, nor shall the act of distribution constitute any such warranty. Digital Data https://doi.org/10.5066/P9CXX7LN None 20200922 James A Kingsbury U.S. Geological Survey, Southeast Region Hydrologist mailing address

640 Grassmere Park

Nashville TN 37211 United States 615-837-4762 615-837-4799 jakingsb@usgs.gov FGDC Content Standard for Digital Geospatial Metadata FGDC-STD-001-1998