William H. Asquith Courtney D. Killian Taylor L. Watson (Contractor) Maxwell A. Lindaman 20251222 raster digital data Suggested citation: Watson, T.L., Asquith, W.H., Killian, C.D., and Lindaman, M.A., 2025, Statistical predictions of typical well depths and related spatial diagnostics for two hydrogeologic frameworks through blending cubist and generalized additive models for the Chicot aquifer system, southwestern Louisiana, from the covCHICOTla statistical research software: U.S. Geological Survey data release, https://doi.org/10.5066/P14WFPF5. https://doi.org/10.5066/P14WFPF5 William H. Asquith Courtney D. Killian 2025 software Asquith, W.H., and Killian, C.D., 2025, covCHICOTla—Source code for construction of covariates bound to monthly groundwater levels for statistical modeling of water levels in the Chicot aquifer system, southwestern Louisiana: U.S. Geological Survey software release, https://doi.org/10.5066/P14N9J9C. [Software home page located at https://code.usgs.gov/map/gw/levs/altaqfrs/chicot/covCHICOTla] https://doi.org/10.5066/P14N9J9C This data release provides gridded predictions of “typical” well depth for the hydrogeologically complex Chicot aquifer system, southwestern Louisiana. These predictions were made using an applied statistical prediction modeling workflow named welldepmod_make.R (Asquith and Lindaman, 2025) to estimate groundwater well depths for two custom bundles (classifications) of local aquifer codes for many thousands of wells. Local aquifer codes represent a coding scheme used by the U.S. Geological Survey (USGS) National Water Information System (NWIS). Asquith and Lindaman (2025) provide comprehensive citations, data sources, data filtering decisions, and other details leading to wells being classified into either CHCTLYR1 or CHCTLYR2 classes suitable for statistical production of typical well-depth geospatial products provided in this data release. The CHCTLYR1 (combination of USGS NWIS local aquifer codes 112CHCTU, 11202LC, 112ACFL, 112CHCT, and 112UPTC) represents comparatively "shallow" Chicot aquifer system conditions and effectively includes the entire horizontal expanse of the aquifer. The CHCTLYR2 (combination of USGS NWIS local aquifer codes 112CHCTL, 11205LC, and 11207LC) represents comparatively "deep" aquifer conditions and is applicable for only part of the Chicot aquifer system expanse; this area is defined by a computational hull corresponding to the data availability of wells assigned the local aquifer codes associated with CHCTLYR2. The modeling implemented support vector machine classification review to make relatively minor adjustments in the CHCTLYR1 or CHCTLYR2 classification by well using probabilistic estimates using four predictor variables or covariates: (1) horizontal well position, (2) Chicot aquifer system bottom altitudes, (3) Chicot aquifer system top altitudes, and (4) mean depth to water for the period record of the wells. The total number of wells was 8,291 with 7,106 being classified as CHCTLYR1 and 1,185 being classified as CHCTLYR2. Using these wells, the modeling then implemented cubist and generalized additive statistical model learning for prediction of typical well depth. The well-depth predictions were made at the 1-kilometer grid scale using the National Hydrogeologic Grid (Clark and others, 2018). The predictions of typical well depth are intended to provide a first-order and general estimate of groundwater wells for purposes of having continuous gridded data for derivative scientific statistical research including groundwater levels, water quality, and hydrogeologic characteristics. Lastly, the computational "hull" for CHCTLYR2 also is provided for cartographic purposes and is based substantially on heuristic decisions made during operation of the script welldepmod_make.R (Asquith and Lindaman, 2025); this hull might have usefulness in derivative scientific software endeavors. Note: The authors are aware that some commercial geospatial software report warnings or encounter difficulties related to the coordinate reference system inherited from Clark and others (2018) digital files within the well-depth model workflow as it produced the geopackage-formatted (.gpkg) polygon representation of the computational hull. The authors have tested reading the geopackage file into Python, R, and other open-source software and writing or exporting said geospatial data into the so-called "shapefile" format (.shp) for which use of this format is expected to abate the aforementioned warnings and difficulties in some commercial software. Predictions of typical well depth are intended to provide a first-order general estimate of hypothetical groundwater wells for purposes of having continuous gridded data for derivative scientific and statistical research including groundwater levels, water quality, and hydrogeologic characteristics. Computational "hulls" for CHCTLYR1 and CHCTLYR2 classes are provided and are based substantially on heuristic decisions made during operation of the script "welldepmod_make.R" (see technical note, Asquith and Lindaman, 2025); these hulls might have usefulness in many other software endeavors. For full description of dataset workflow see Asquith and Lindaman, 2025 (technical note). 2025 publication date Complete None planned -93.9370 -91.4507 31.3820 29.5288 ISO 19115 Topic Category geoscientificInformation USGS Thesaurus well depth groundwater mathematical modeling aquifer U.S. Geological Survey machine learning hydrogeology hydrology Hydrogeology Chicot aquifer system USGS Metadata Identifier USGS:684b2ddfd4be020b699d9a11 None Louisiana Coastal Louisiana United States None. Please see 'Distribution Info' for details. Although these data have been used by the U.S. Geological Survey (USGS), U.S. Department of the Interior, no warranty expressed or implied is made by the USGS as to the accuracy of the data. The act of distribution shall not constitute any such warranty, and no responsibility is assumed by the USGS 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. Taylor Watson (Contractor) U.S. Geological Survey Researcher mailing and physical

700 W. Research Center Blvd.

Fayetteville AR 72701 United States 479-841-7567 twatson@contractor.usgs.gov In cooperation with the Louisiana Department of Transportation and Development (LaDOT) Raster data are provided as multi-banded GeoTIFF files. Vector data are provided as geopackage-formatted (.gpkg) polygons. Metadata files are provided as extensible markup language (xml) files. William H. Asquith Courtney D. Killian 2025 software Asquith, W.H., and Killian, C.D., 2025, covCHICOTla—Source code for construction of covariates bound to monthly groundwater levels for statistical modeling of water levels in the Chicot aquifer system, southwestern Louisiana: U.S. Geological Survey software release, https://doi.org/10.5066/P14N9J9C. [Software home page located at https://code.usgs.gov/map/gw/levs/altaqfrs/chicot/covCHICOTla] https://doi.org/10.5066/P14N9J9C William H. Asquith Maxwell A. Lindaman 2025 publication Asquith, W.H., and Lindaman, M.A., 2025, Research software technical note and source code for creation of statistical models for prediction of typical well depths and related spatial diagnostics for the Chicot aquifer system, southwestern Louisiana: U.S. Geological Survey software release at https://doi.org/10.5066/P1UEMKYK [Software home page located at https://code.usgs.gov/map/gw/levs/altaqfrs/chicot/covCHICOTla/-/tree/main/covar/welldepmod/] in Asquith, W.H., and Killian, C.D., 2025, covCHICOTla—Source code for construction of covariates bound to monthly groundwater levels for statistical modeling of water levels in the Chicot aquifer system, southwestern Louisiana: U.S. Geological Survey software release, software home page located at https://code.usgs.gov/map/gw/levs/altaqfrs/chicot/covCHICOTla. https://doi.org/10.5066/P1UEMKYK Accuracy of typical well depth predictions by the blended cubist and generalized additive statistical model predictions is measured by a root mean square error that are approximately 70 feet for the CHCTLYR1 classification and 93 feet for CHCTLYR2 classification. In preprocessing the source data, the following records were rejected: records with missing well depths and/or missing aquifer bottom (aquifer presence); records before a MINIMUM_YEAR set by heuristic choice; records having local aquifer codes that do not make logical sense for the study (112MRVA, 112RRVA, and 112RRVAC); records with local aquifer codes that are more closely associated with the Chicot aquifer system than those listed previously (112CHCTC and 112CHCTS), which are associated with the surficial confining clay and interspersed minor sands within the larger clay unit; and records indicating a water-level altitude above the land surface. The extents of the typical well depth predictions for the CHCTLYR1 classification (well_depth_ft_CHCTLYR1.tif) are bound by the Chicot aquifer system extent (Bussell and Killian, 2021). The extents of the typical well depth predictions for the CHCTLYR2 classification (well_depth_ft_CHCTLYR1.tif) are spatially bound by the computational hull corresponding to the data availability of wells that were assigned local aquifer codes associated with CHCTLYR2 included as raster (well_depth_hull_CHCTLYR2.tif) and vector (well_depth_hull_CHCTLYR2.gpkg) files. A formal accuracy assessment of the horizontal positional information in the data set has not been conducted. Horizontal accuracy (or location accuracy) of source data (well depths) varies by well but can range from plus or minus 0.01 second to 1 minute of latitude and longitude or be unknown. Well depths were used to make predictions of typical well depths at the 1-kilometer resolution national hydrogeologic grid (NHG) (Clark and others, 2018) across the Chicot aquifer system extent (Bussell and Killian, 2021). A formal accuracy assessment of the vertical positional information in the data set has not been conducted. Vertical accuracy (or depth accuracy) of source data (well depths) is not recorded in the NWIS database, and the source of depth data varies by well. William H Asquith Courtney D Killian 2025 software Suggested Repository Citation: Asquith, W.H., and Killian, C.D., 2025, covCHICOTla—Source code for construction of covariates bound to monthly groundwater levels for statistical modeling of water levels in the Chicot aquifer system, southwestern Louisiana: U.S. Geological Survey software release, https://doi.org/10.5066/P14N9J9C. [Software home page located at https://code.usgs.gov/map/gw/levs/altaqfrs/chicot/covCHICOTla] https://doi.org/10.5066/P14N9J9C Digital and/or Hardcopy 2025 publication date Asquith and Killian, 2025 Software, classification of aquifer codes, construction of Cubist and Generalized Additive statistical models for typical well depth prediction in the Chicot aquifer. United States Geological Survey 1994 dataset https://www.sciencebase.gov U.S. Geological Survey https://doi.org/10.5066/f7p55kjn Digital and/or Hardcopy 1994 publication date NWIS Well depth, well completion, and spatial location variables, national and local and aquifer coding schemes. Brian R. Clark Paul M. Barlow Steven M. Peterson Joseph D. Hughes Howard W. Reeves Roland Viger 2018 dataset https://www.sciencebase.gov U.S. Geological Survey https://doi.org/10.5066/f7p84b24 Digital and/or Hardcopy 2018 publication date Clark and others, 2018 Covariate, national hydrogeologic grid Alexandros Karatzoglou David Meyer Kurt Hornik 20060406 publication https://doi.org/10.18637/jss.v015.i09 Digital and/or Hardcopy 20060406 publication date Karatzoglou and others, 2006 SVM source Max Kuhn Kjell Johnson 2016 publication https://doi.org/10.1007/978-1-4614-6849-3 Digital and/or Hardcopy 2016 publication date Kuhn and Johnson, 2016 Machine learning model source Kristi L. Hill Wade Kress Maxwell A. Lindaman 20220407 dataset https://www.sciencebase.gov U.S. Geological Survey Hill, K.L., Kress, W.H., and Lindaman, M.A., 2022, Thickness of the Chicot aquifer system of southwestern Louisiana's surficial confining unit and shallow sand lenses, southwestern Louisiana: U.S. Geological Survey data release, https://doi.org/10.5066/P9W2SKSY. https://doi.org/10.5066/p9w2sksy Digital and/or Hardcopy 1900 2004 observed Hill and others, 2022 Predictor variable in SVM Maxwell A. Lindaman 20230726 dataset https://www.sciencebase.gov U.S. Geological Survey https://doi.org/10.3133/sir20235004 Digital and/or Hardcopy 20230726 publication date Lindaman, 2023a Source referenced in development of SVM cost parameter Maxwell A. Lindaman 20230726 dataset https://www.sciencebase.gov U.S. Geological Survey https://doi.org/10.5066/p9olqlpp Digital and/or Hardcopy 20230726 publication date Lindaman, 2023b Predictor variable in SVM Max Kuhn Steve Weston Chris Keefer Nathan Coulter Ross Quinlan Rulequest Research Pty Ltd. 20250403 application/service https://doi.org/10.32614/CRAN.package.Cubist Digital and/or Hardcopy 20250403 publication date Kuhn and others, 2025 Cubist model source code Simon Wood 2006 publication https://doi.org/10.1201/9781315370279 Digital and/or Hardcopy 2006 publication date Wood, 2006 Generalized additive model source Simon Wood 20250404 application/service https://doi.org/10.32614/CRAN.package.mgcv Digital and/or Hardcopy 20250404 publication date Wood, 2025 Generalized additive model source code. Ashley M Bussell Courtney D Killian 2021 dataset https://www.sciencebase.gov U.S. Geological Survey Chicot aquifer system extent, boundary of CHCTLYR1 predictions https://doi.org/10.5066/p97v6v5d Digital and/or Hardcopy 20210528 publication date Bussel and Killian William H. Asquith Maxwell A. Lindaman 2025 tabular digital data Asquith, W.H., and Lindaman, M.A., 2025, Research software technical note and source code for creation of statistical models for prediction of typical well depths and related spatial diagnostics for the Chicot aquifer system, southwestern Louisiana: U.S. Geological Survey software release at https://doi.org/10.5066/P1UEMKYK [Software home page located at https://code.usgs.gov/map/gw/levs/altaqfrs/chicot/covCHICOTla/-/tree/main/covar/welldepmod/] in Asquith, W.H., and Killian, C.D., 2025, covCHICOTla—Source code for construction of covariates bound to monthly groundwater levels for statistical modeling of water levels in the Chicot aquifer system, southwestern Louisiana: U.S. Geological Survey software release, software home page located at https://code.usgs.gov/map/gw/levs/altaqfrs/chicot/covCHICOTla. https://doi.org/10.5066/P1UEMKYK Digital and/or Hardcopy 2025 publication date Asquith and Lindaman, 2025 Documentation, methods Two scripts within the well depth module (welldepmod) of the covCHICOTla software (Asquith and Killian, 2025) represent the algorithms in the R language (R Core Team, 2024) used to create statistical models for prediction of typical well depths. The script welldepmod_make.R constitutes the primary user interface for (1) data preprocessing including monthly water level and well metadata dataset for the Chicot aquifer and data object organization, (2) creation of and cubist (CUB) (Kuhn and Johnson, 2016; Kuhn and others, 2025) and generalized additive (GAM) (Wood, 2006, 2025) statistical models, and (3) implementation of those models to generate geospatial projects included in this data release. The script welldepmod_svm_aqfrcd.R provides a classification study of aquifer code. For detailed information regarding data processing see Asquith and Lindaman, 2025 (technical note), and/or covCHICOTla software release. Asquith and Killian, 2025 NWIS Clark and others, 2018 Kuhn and Johnson, 2016 Wood, 2006 Wood, 2025 Kuhn and others, 2025 Asquith and Lindaman, 2025 2025 William H. Asquith U.S. Geological Survey Research Hydrologist mailing and physical

8802 Urbana Avenue

Lubbock TX 79424 United States 806-993-0232 wasquith@usgs.gov Raster Grid Cell 214 231 11 Albers Conical Equal Area 29.5 45.5 -96.0 23.0 0.0 0.0 row and column 1000.0 1000.0 meters WGS_1984 WGS 84 6378137.0 298.257223563 well_depth_ft_CHCTLYR1.tif 11 band raster geospatial data file. Producer Defined WellDepth_ft Final blended gridded predictions of typical well depth for the CHCTLYR1 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined -15.901700 598.932617 Feet GAM_WellDepth_ft Gridded generalized additive model predictions of typical well depth for the CHCTLYR1 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined -40.118698 610.973694 Feet GAMsefit_ft Standard error of fit for the generalized additive model. Producer Defined nan not a number Producer defined 2.298200 19.444700 Feet CUB1_WellDepth_ft Gridded cubist model 1 predictions of typical well depth for the CHCTLYR1 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 24.195200 725.532227 Feet CUB2_WellDepth_ft Gridded cubist model 2 predictions of typical well depth for the CHCTLYR1 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 74.340698 539.750488 Feet CUB3_WellDepth_ft Gridded cubist model 3 predictions of typical well depth for the CHCTLYR1 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 43.676399 665.331970 Feet CUB4_WellDepth_ft Gridded cubist model 4 predictions of typical well depth for the CHCTLYR1 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 49.971802 551.109192 Feet CUB5_WellDepth_ft Gridded cubist model 5 predictions of typical well depth for the CHCTLYR1 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 71.890900 610.188721 Feet CUB6_WellDepth_ft Gridded cubist model 6 predictions of typical well depth for the CHCTLYR1 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 62.454102 540.018005 Feet CUB7_WellDepth_ft Gridded cubist model 7 predictions of typical well depth for the CHCTLYR1 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 26.867800 762.231079 Feet CUB8_WellDepth_ft Gridded cubist model 8 predictions of typical well depth for the CHCTLYR1 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 44.925098 450.284607 Feet well_depth_ft_CHCTLYR2.tif 6 band raster geospatial data file. Producer Defined WellDepth_ft Final blended gridded predictions of typical well depth for the CHCTLYR2 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 400.075897 899.888489 Feet GAM_WellDepth_ft Gridded generalized additive model predictions of typical well depth for the CHCTLYR2 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 395.229309 920.136597 Feet GAMsefit_ft Standard error of fit for the generalized additive model. Producer Defined nan not a number Producer defined 6.996800 33.997601 Feet CUB1_WellDepth_ft Gridded cubist model 1 predictions of typical well depth for the CHCTLYR2 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 348.886108 892.076721 Feet CUB2_WellDepth_ft Gridded cubist model 2 predictions of typical well depth for the CHCTLYR2 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 336.049896 884.847229 Feet CUB3_WellDepth_ft Gridded cubist model 3 predictions of typical well depth for the CHCTLYR2 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 341.850403 890.048218 Feet well_depth_hull_CHCTLYR2.tif Raster geospatial data file. Producer Defined Value Computational hull for the CHCTLYR2 bundled Chicot aquifer system classification. Producer Defined nan not a number Producer defined 1.0 1.0 Feet well_depth_hull_CHCTLYR2.gpkg Multipolygon vector geospatial data file. Producer Defined zz_well_depth_hull_CHCTLYR2 Computational hull for the CHCTLYR2 bundled Chicot aquifer system classification. Producer Defined Geometry 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 for other purposes, nor on all computer systems, nor shall the act of distribution constitute any such warranty. Digital Data https://doi.org/10.5066/P14WFPF5 None 20251222 Taylor Watson (Contractor) U.S. Geological Survey Researcher mailing and physical

700 W. Research Center Blvd.

Fayetteville AR 72701 United States 479-841-7567 twatson@contractor.usgs.gov FGDC Content Standard for Digital Geospatial Metadata FGDC-STD-001-1998