This data release replicates the methods detailed in the 2017 publication titled "Improving predictions of hydrological low-flow indices in ungaged basins using machine learning" for a different data set. The original data set and the associated readme file for the model archive can be viewed here: https://doi.org/10.5066/F7CR5S4T. The original data set contained streamflow data for sites located in South Carolina, Georgia, and Alabama. The data set used in this data release is for 6 states in the Southern Midwest U.S.A. The datafile contains the annual minimum seven-day mean streamflow with an annual exceedance probability of 90% (7Q10) for 173 basins in Arkansas (AR), Iowa (IA), Kansas (KS), Missouri (MO), Nebraska (NE), and Oklahoma (OK). The datafile also contains 231 basin characteristics from the Gages II dataset (https://water.usgs.gov/lookup/getspatial?gagesII_Sept2011).

This data release provides the data and R scripts used for the 2018 publication titled "Improving predictions of hydrological low-flow indices in ungaged basins using machine learning", Environmental Modeling and Software, https://doi.org/10.1016/j.envsoft.2017.12.021. There are two .csv files and 14 R-scripts included below. The lowflow_sc_ga_al_gagesII_2015.csv datafile contains the annual minimum seven-day mean streamflow with an annual exceedance probability of 90% (7Q10) for 224 basins in South Carolina, Georgia, and Alabama. The datafile also contains 231 basin characteristics from the Gages II dataset (https://water.usgs.gov/lookup/getspatial?gagesII_Sept2011). The "all_preds.csv" file contains the leave-one-out cross validated predictions for all the models. The paper associated with the data release compares the ability of eight machine-learning models (elastic net, gradient boosting, kernel-k-nearest neighbors, two variants of support vector machines, M5-cubist, random forest, and a meta-learning ensemble M5-cubist model) and four baseline models (ordinary kriging, a unit-area discharge model, and two variants of censored regression) to generate estimates of the 7Q10 at 224 unregulated sites in South Carolina, Georgia, and Alabama.

This dataset provides numerical and categorical descriptions of 48 basin characteristics for 956 basins with observed streamflow information at U.S. Geological Survey (USGS) streamflow-gaging stations. Characteristics are indexed by National Hydrography Dataset (NHD) version 2 COMID (integer that uniquely identifies each feature in the NHD) and USGS station number for streamflow-gaging station. The variables represent mutable and immutable basin characteristics and are organized by characteristic type: physical (5), hydrologic (6), categorical (12), climate (6), landscape alteration (7), and land cover (12). Mutable characteristics such as climate, land cover, and landscape alteration variables are reported in decadal increments (for example, average percent forest for the decade 1950-1959, 1960-1969, etc). The majority of basin characteristics in this dataset were calculated using divergence-routing methods and are often referred to as “network-accumulated”. This method uses a modified routing database to navigate the NHDPlus reach network to aggregate (accumulate) the values derived from the reach catchment scale (Schwarz, G.E., and Wieczorek, M.E., 2018, Database of modified routing for NHDPlus version 2.1 flowlines: ENHDPlusV2_us: U.S. Geological Survey data release, https://doi.org/10.5066/P9PA63SM ). In four instances, values are also provided for the entire catchment above a site and area designated using the “CAT_” prefix.

This dataset provides numerical and categorical descriptions of 48 basin characteristics for 956 basins with observed streamflow information at U.S. Geological Survey (USGS) streamflow-gaging stations. Characteristics are indexed by National Hydrography Dataset (NHD) version 2 COMID (integer that uniquely identifies each feature in the NHD) and USGS station number for streamflow-gaging station. The variables represent mutable and immutable basin characteristics and are organized by characteristic type: physical (5), hydrologic (6), categorical (12), climate (6), landscape alteration (7), and land cover (12). Mutable characteristics such as climate, land cover, and landscape alteration variables are reported in decadal increments (for example, average percent forest for the decade 1950-1959, 1960-1969, etc). The majority of basin characteristics in this dataset were calculated using divergence-routing methods and are often referred to as “network-accumulated”. This method uses a modified routing database to navigate the NHDPlus reach network to aggregate (accumulate) the values derived from the reach catchment scale (Schwarz, G.E., and Wieczorek, M.E., 2018, Database of modified routing for NHDPlus version 2.1 flowlines: ENHDPlusV2_us: U.S. Geological Survey data release, https://doi.org/10.5066/P9PA63SM ). In four instances, values are also provided for the entire catchment above a site and area designated using the “CAT_” prefix.

This dataset was compiled to summarize discharge measurements from several published groundwater and surface-water studies in the Ozarks of southern Missouri and northern Arkansas. The discharge measurements were part of numerous USGS studies to assess interaction between streams and groundwater aquifers. A gaining stream is described as a surface-water stream that gains water from the groundwater aquifer and a losing stream is described as a surface-water stream that loses water to the groundwater aquifer. This product is intended to be used in surface-water and groundwater investigations assessing water quantity, quality, and availability. The product includes flow-line data digitized along National Hydrography Dataset (NHD) flow lines and between adjacent discharge measurements (that is, seepage flow-line reaches). The seepage flow-line reaches include a calculation to determine if discharge between the upstream and downstream measurement points is increasing (termed "Gain"), decreasing (termed "Lose"), or remaining neutral if the net change in discharge is not greater than the error (termed "Neutral"). Original seepage-run studies included estimates of discharge measurement error and some studies estimated error along the seepage flow-line reach; however, because of the variety of ways that error was calculated in the original studies and to create a consistent error estimation for the entire spatial dataset, error was assumed to be 10% of the largest discharge measurement along the seepage flow-line reach. Contribution of discharge from tributaries and springs that emerge before flowing into the stream was taken into account, such that the net change in discharge between the upstream and downstream measurement points was calculated as the downstream discharge minus the total discharge from the upstream measurement point and from tributaries/springs. This calculation quantifies the amount of groundwater flow entering the stream as diffuse or point discharge, presumably into the stream bed. The net change in discharge was additionally calculated as the downstream discharge minus the total discharge from both the upstream measurement point and from surface-water tributaries only. This calculation quantifies the amount of groundwater entering the stream as discrete springs adjacent to the stream and diffuse or point groundwater flow directly to the stream bed. A positive net change in discharge results in the seepage flow-line reach gaining discharge (that is, "Gain") and a negative net change in discharge results in the seepage flow-line reach losing discharge (that is, "Lose"). Designations of gaining, losing, or neutral streams may vary between this dataset and the original studies because of differences in how error was calculated and other interpretations made in the seepage-run studies. Users are encouraged to refer to the source reports for further details about data collection methods, results, and interpretations of stream-aquifer dynamics. This spatial dataset is meant to provide a digital compilation of seepage studies in the Ozarks and to create a consistent dataset across studies completed over 24 years.

This dataset was compiled to summarize discharge measurements from several published groundwater and surface-water studies in the Ozarks of southern Missouri and northern Arkansas. The discharge measurements were part of numerous USGS studies to assess interaction between streams and groundwater aquifers. A gaining stream is described as a surface-water stream that gains water from the groundwater aquifer and a losing stream is described as a surface-water stream that loses water to the groundwater aquifer. This product is intended to be used in surface-water and groundwater investigations assessing water quantity, quality, and availability. The product includes flow-line data digitized along National Hydrography Dataset (NHD) flow lines and between adjacent discharge measurements (that is, seepage flow-line reaches). The seepage flow-line reaches include a calculation to determine if discharge between the upstream and downstream measurement points is increasing (termed "Gain"), decreasing (termed "Lose"), or remaining neutral if the net change in discharge is not greater than the error (termed "Neutral"). Original seepage-run studies included estimates of discharge measurement error and some studies estimated error along the seepage flow-line reach; however, because of the variety of ways that error was calculated in the original studies and to create a consistent error estimation for the entire spatial dataset, error was assumed to be 10% of the largest discharge measurement along the seepage flow-line reach. Contribution of discharge from tributaries and springs that emerge before flowing into the stream was taken into account, such that the net change in discharge between the upstream and downstream measurement points was calculated as the downstream discharge minus the total discharge from the upstream measurement point and from tributaries/springs. This calculation quantifies the amount of groundwater flow entering the stream as diffuse or point discharge, presumably into the stream bed. The net change in discharge was additionally calculated as the downstream discharge minus the total discharge from both the upstream measurement point and from surface-water tributaries only. This calculation quantifies the amount of groundwater entering the stream as discrete springs adjacent to the stream and diffuse or point groundwater flow directly to the stream bed. A positive net change in discharge results in the seepage flow-line reach gaining discharge (that is, "Gain") and a negative net change in discharge results in the seepage flow-line reach losing discharge (that is, "Lose"). Designations of gaining, losing, or neutral streams may vary between this dataset and the original studies because of differences in how error was calculated and other interpretations made in the seepage-run studies. Users are encouraged to refer to the source reports for further details about data collection methods, results, and interpretations of stream-aquifer dynamics. This spatial dataset is meant to provide a digital compilation of seepage studies in the Ozarks and to create a consistent dataset across studies completed over 24 years.

The U.S. Geological Survey Central Midwest Water Science Center completed a report (Over and others, 2023) documenting methods, results, and applications of an updated flood-frequency study for the State of Illinois. The study developed regional regression equations that relate the peak-flow quantiles and the basin characteristics of selected streamgages in Illinois, Indiana, and Wisconsin, based on data through water year 2017 (a water year is the period from October 1 to September 30 and is designated by the year in which it ends; for example, water year 2017 was from October 1, 2016, to September 30, 2017). The data provided through this data release are those digital datasets of basin characteristics that have been collected, tested, and ultimately selected for use in regional regression equations. These datasets consist of raster grid files for slope (slope100.zip), calculated from a published digital elevation model (DEM) (Schafer and Sharpe, 2023), soil slope (stats_slope100.zip) subsetted and resampled from Wolock (1997), a soil texture permeability index (texp_indx_rnd.zip) computed using data from Wolock (1997), land cover (nlcd16_22_23_24.zip) adapted from Yang and others (2018), a basin soil wetness measure (drclass1a.zip) computed from U.S. Department of Agriculture (USDA) (2013), and an urbanization fraction (urbthe2010.zip) computed from Theobald 2010 data (Theobald, 2005). Some basin characteristics are not included in this data release as they are easily derived from StreamStats basin delineations themselves, such as basin drainage area. The U.S. Geological Survey (USGS), in cooperation with the Illinois Center for Transportation (ICT) and the Illinois Department of Transportation (IDOT), prepared these digital datasets of basin characteristics for use in the Illinois StreamStats application (https://streamstats.usgs.gov/ss/). Two additional shapefiles are provided: a shapefile of the streamgages (IL_StreamStats_Gages.zip) and a shapefile of the associated delineated streamgage drainage basins (IL_StreamStats_DrainageBasins.zip) used in analysis (Over and others, 2023).

The U.S. Geological Survey Central Midwest Water Science Center completed a report (Over and others, 2023) documenting methods, results, and applications of an updated flood-frequency study for the State of Illinois. The study developed regional regression equations that relate the peak-flow quantiles and the basin characteristics of selected streamgages in Illinois, Indiana, and Wisconsin, based on data through water year 2017 (a water year is the period from October 1 to September 30 and is designated by the year in which it ends; for example, water year 2017 was from October 1, 2016, to September 30, 2017). The data provided through this data release are those digital datasets of basin characteristics that have been collected, tested, and ultimately selected for use in regional regression equations. These datasets consist of raster grid files for slope (slope100.zip), calculated from a published digital elevation model (DEM) (Schafer and Sharpe, 2023), soil slope (stats_slope100.zip) subsetted and resampled from Wolock (1997), a soil texture permeability index (texp_indx_rnd.zip) computed using data from Wolock (1997), land cover (nlcd16_22_23_24.zip) adapted from Yang and others (2018), a basin soil wetness measure (drclass1a.zip) computed from U.S. Department of Agriculture (USDA) (2013), and an urbanization fraction (urbthe2010.zip) computed from Theobald 2010 data (Theobald, 2005). Some basin characteristics are not included in this data release as they are easily derived from StreamStats basin delineations themselves, such as basin drainage area. The U.S. Geological Survey (USGS), in cooperation with the Illinois Center for Transportation (ICT) and the Illinois Department of Transportation (IDOT), prepared these digital datasets of basin characteristics for use in the Illinois StreamStats application (https://streamstats.usgs.gov/ss/). Two additional shapefiles are provided: a shapefile of the streamgages (IL_StreamStats_Gages.zip) and a shapefile of the associated delineated streamgage drainage basins (IL_StreamStats_DrainageBasins.zip) used in analysis (Over and others, 2023).

This data set is one of many developed in support of The High Plains Groundwater Availability Project and the USGS Data Series Report: Geodatabase Compilation of Hydrogeologic, Remote Sensing, and Water-Budget-Component data for the High Plains aquifer, 2011 (DS 777). This dataset contains point vector data from the National Hydrography Dataset Plus (NHD+) 1:100,000 stream polyline data converted into points and attributed with elevation values in feet above sea level. Streams were initially included if they had a mean estimated base flow of more than 10 cubic feet per second (based on streamflow data from long-term streamflow-gaging stations operated by the USGS or the Nebraska Department of Natural Resources). The stream network then was expanded to include selected streams that were deemed hydrogeologically important but had a mean estimated base flow of less than 10 cubic feet per second.

This dataset provides numerical and categorical descriptions of 48 basin characteristics for 9,314 ungaged basins coinciding with 12-digit hydrologic unit code (HUC12) pour points that drain to the Gulf of Mexico. Characteristics are indexed by National Hydrography Dataset (NHD) version 2 COMID (integer that uniquely identifies each feature in the NHD) and HUC12 identifying number. The variables represent mutable and immutable basin characteristics and are organized by characteristic type: physical (5), hydrologic (6), categorical (12), climate (6), landscape alteration (7), and land cover (12). Mutable characteristics such as climate, land cover, and landscape alteration variables are reported in decadal increments (for example, average percent forest for the decade 1950-1959, 1960-1969, etc). The majority of basin characteristics in this dataset were calculated using divergence-routing methods and are often referred to as “network-accumulated”. This method uses a modified routing database to navigate the NHDPlus reach network to aggregate (accumulate) the values derived from the reach catchment scale (Schwarz, G.E., and Wieczorek, M.E., 2018, Database of modified routing for NHDPlus version 2.1 flowlines: ENHDPlusV2_us: U.S. Geological Survey data release, https://doi.org/10.5066/P9PA63SM ). In four instances, values are also provided for the entire catchment above a site and area designated using the “CAT_” prefix.