Ma et al. 2023 random forest water table depth and uncertainty

Water table depth estimates provided by a random forest model trained on well observations compiled from multiple groundwater databases spanning 1914-2023. This dataset includes long-term mean water table estimates and uncertainty at 1km resolution for the CONUS1 domain.

Dataset Name: ma_2023

Data Source: ma_2023

Data Collection or Processing Notes:

Long-term mean water table depth estimates were obtained using the median of tree outputs from the trained random forest model. The uncertainty was assessed based on the coefficient of variation of the tree outputs from the random forest model, which was calculated as the standard deviation of the tree outputs divided by their mean.

Citations:

Please refer to the following citations for more information on this dataset and cite them if you use the data

Extent and Resolution:

  • Available Date Range: 1914-01-01 to 2023-12-31

  • Grid: conus1

    • Spacial Resolution: 1000 meters

    • XY Grid Spacial Extent: 3342 x 1888

    • LatLon Spacial Exent: -121.47939483437318, 31.651836025255015, -76.09875469594509, 50.49802132270979

    • Origin (meters): -1885055.4995, -604957.0654

    • Projection: +proj=lcc +lat_1=33 +lat_2=45 +lon_0=-96.0 +lat_0=39 +a=6378137.0 +b=6356752.31

Variables

This describes the available variables of the dataset. Use the dataset, variables and temporal_resolution in python access functions as described in the Working with Gridded Data, and Working with Point Observations.

Subsurface Variables

variable

description

temporal_resolution

units

grid

3D

water_table_depth

Water table depth

static

m

conus1

no

wtd_uncertainty

Uncertainty in water table depth estimation from a random forest model

static

unitless

conus1

no