These tabular data sets represent the average daily soil moisture water content (kg/m^2) for four different soil layers processed from North American Land Data Assimilation System (NLDAS-2) data (Xia and others, 2012) for the period of record 1980 through 2020 and compiled for three spatial components: 1) select United States Geological Survey stream gage basins (Staub and Wieczorek, 2023), 2) individual reach flowline catchments of the Upper Colorado (ucol) portion of the Geospatial Fabric for the National Hydrologic Model, version 1.1 (nhgfv11, Bock and others, 2020 ), and 3) the upstream watersheds of each individual nhgfv11 flowline catchments. Flowline reach catchment information characterizes data at the local scale using the python tool set called gdptools (McDonald, 2021). Upstream watershed values for each reach catchment were computed using the published python software package Xstrm (Wieferich and others). The following mean daily soil moisture water content layers were processed: 0-10 centimeters, 10-40 centimeters, and 40-100 centimeters.

These tabular data sets represent daily climate metrics processed from 4 kilometer GridMET data (Abatzoglou, 2013) for the period of record 1980 through 2020 and compiled for three spatial components: select United States Geological Survey stream gage basins (Staub and Wieczorek, 2023), 2) individual reach flowline catchments of the Upper and Lower Colorado (ucol) portions of the Geospatial Fabric for the National Hydrologic Model, version 1.1 (nhgfv11, Bock and others, 2020 ), and 3) the upstream watersheds of each individual nhgfv11 flowline catchments. Flowline reach catchment information characterizes data at the local scale using the python tool set called gdptools (McDonald, 2021). Reach catchments accumulated upstream through the river network characterizes cumulative upstream conditions. Network-accumulated values were computed using the published python software package Xstrm (Wieferich and others). The following daily climate metrics were processed: minimum and maximum temperature (Celsius), precipitation (millimeters), potential evapotranspiration (millimeters), reference evapotranspiration (millimeters), and 5 day standardized precipitation evapotranspiration index (unitless).

These tabular data sets represent daily climate metrics processed from 4 kilometer GridMET data (Abatzoglou, 2013) for the period of record 1980 through 2020 and compiled for three spatial components: select United States Geological Survey stream gage basins (Staub and Wieczorek, 2023), 2) individual reach flowline catchments of the Upper and Lower Colorado (ucol) portions of the Geospatial Fabric for the National Hydrologic Model, version 1.1 (nhgfv11, Bock and others, 2020 ), and 3) the upstream watersheds of each individual nhgfv11 flowline catchments. Flowline reach catchment information characterizes data at the local scale using the python tool set called gdptools (McDonald, 2021). Reach catchments accumulated upstream through the river network characterizes cumulative upstream conditions. Network-accumulated values were computed using the published python software package Xstrm (Wieferich and others). The following daily climate metrics were processed: minimum and maximum temperature (Celsius), precipitation (millimeters), potential evapotranspiration (millimeters), reference evapotranspiration (millimeters), and 5 day standardized precipitation evapotranspiration index (unitless).

These tabular data sets represent daily climate metrics processed from 4 kilometer GridMET data (Abatzoglou, 2013) for the period of record 1980 through 2020 and compiled for three spatial components: select United States Geological Survey stream gage basins (Staub and Wieczorek, 2023), 2) individual reach flowline catchments of the Upper and Lower Colorado (ucol) portions of the Geospatial Fabric for the National Hydrologic Model, version 1.1 (nhgfv11, Bock and others, 2020 ), and 3) the upstream watersheds of each individual nhgfv11 flowline catchments. Flowline reach catchment information characterizes data at the local scale using the python tool set called gdptools (McDonald, 2021). Reach catchments accumulated upstream through the river network characterizes cumulative upstream conditions. Network-accumulated values were computed using the published python software package Xstrm (Wieferich and others). The following daily climate metrics were processed: minimum and maximum temperature (Celsius), precipitation (millimeters), potential evapotranspiration (millimeters), reference evapotranspiration (millimeters), and 5 day standardized precipitation evapotranspiration index (unitless).

These tabular datasets represent retrospective forecasts of average minimum temperature (degrees Celsius), maximum temperature (degrees Celsius), and total precipitation (millimeters) within three-hour forecasting periods derived from the Global Ensemble Forecast System (GEFS) reforecast dataset (Hamill and others, 2013). Data are averaged across 7 day forecast horizons for each day within the period of record spanning 2000 through 2019. The data were compiled for two spatial components: 1) select United States Geological Survey streamgage basins (Staub and others, 2023), 2) individual reach flowline catchments of the Upper Colorado (ucol) portion of the Geospatial Fabric for the National Hydrologic Model, version 1.1 (Bock and others, 2020). Flowline reach catchment information characterizes data at the local scale using the python tool set called gdptools (McDonald, 2021).

These tabular data sets represent daily climate metrics processed from 4 kilometer snow water equivalent (SWE) raster data in millimeters (Broxton and others, 2019) for the period of record 10-01-1981 through 09-30-2020 and compiled for three spatial components: select United States Geological Survey stream gage basins (Staub and Wieczorek, 2023), 2) individual reach flowline catchments of the Upper and Lower Colorado (ucol) portions of the Geospatial Fabric for the National Hydrologic Model, version 1.1 (nhgfv11, Bock and others, 2020 ), and 3) the upstream watersheds of each individual nhgfv11 flowline catchments. Flowline reach catchment information characterizes data at the local scale using the python tool set called gdptools (McDonald, 2021). Reach catchments accumulated upstream through the river network characterizes cumulative upstream conditions. Network-accumulated values were computed using the published python software package Xstrm (Wieferich and others).

These tabular data sets represent daily climate metrics processed from 4 kilometer snow water equivalent (SWE) raster data in millimeters (Broxton and others, 2019) for the period of record 10-01-1981 through 09-30-2020 and compiled for three spatial components: select United States Geological Survey stream gage basins (Staub and Wieczorek, 2023), 2) individual reach flowline catchments of the Upper and Lower Colorado (ucol) portions of the Geospatial Fabric for the National Hydrologic Model, version 1.1 (nhgfv11, Bock and others, 2020 ), and 3) the upstream watersheds of each individual nhgfv11 flowline catchments. Flowline reach catchment information characterizes data at the local scale using the python tool set called gdptools (McDonald, 2021). Reach catchments accumulated upstream through the river network characterizes cumulative upstream conditions. Network-accumulated values were computed using the published python software package Xstrm (Wieferich and others).

These tabular data sets represent monthly meteorological metrics processed from North American Multi-Model Ensemble (NMME) for the hindcast (1982-2011) and forecast (2011-2023) periods of record and compiled for the spatial component of select United States Geological Survey stream gage basins (Staub and others, 2023). Flowline reach catchment information characterizes data at the local scale using the python tool set called gdptools (McDonald, 2021). The following monthly meteorological metrics were processed: reference temperature (degree Celsius), and total precipitation (millimeters) for forecast periods of 15, 45, 75, and 105 days (0.5 to 3.5 months).

This metadata record describes model outputs and supporting model code for the Data-Driven Drought Prediction project of the Water Resources Mission Area Drought Program. The data listed here include outputs of multiple machine learning model types for predicting hydrological drought at select locations within the conterminous United States. The child items referenced below correspond to different models and spatial extents (Colorado River Basin region or conterminous United States). See the list below or metadata files in each sub-folder for more details. 1. Daily streamflow percentile predictions for the Colorado River Basin region — Outputs from long short-term memory (LSTM) deep learning models corresponding to selected stream gage locations.

This metadata record describes model outputs and supporting model code for the Data-Driven Drought Prediction project of the Water Resources Mission Area Drought Program. The data listed here include outputs of multiple machine learning model types for predicting hydrological drought at select locations within the conterminous United States. The child items referenced below correspond to different models and spatial extents (Colorado River Basin region or conterminous United States). See the list below or metadata files in each sub-folder for more details. 1. Daily streamflow percentile predictions for the Colorado River Basin region — Outputs from long short-term memory (LSTM) deep learning models corresponding to selected stream gage locations.