Skip to main content
U.S. flag

An official website of the United States government

Machine-learning model predictions and rasters of groundwater salinity in the Mississippi Alluvial Plain

November 17, 2023

Groundwater from the Mississippi River Valley alluvial aquifer (MRVA), coincident with the Mississippi Alluvial Plain (MAP), is a vital resource for agriculture and drinking-water supplies in the central United States. Water availability can be limited in some areas of the aquifer by high concentrations of salinity, measured as specific conductance. Boosted regression trees (BRT), a type of ensemble-tree machine-learning method, were used to predict specific conductance concentration at multiple depths throughout the MRVA and underlying aquifers. Two models were created to test the incorporation of datasets from a regional aerial electromagnetic (AEM) survey and evaluate model performance. Explanatory variables for the BRT models included attributes associated with well location and construction, surficial variables (such as hydrologic position and recharge), and variables from the AEM survey of the aquifer. This data release provides the R scripts to tune and reproduce the BRT models and final prediction rasters.

For a full description of modeling workflow and final model selection see: Killian, C.D. and Knierim, K.J., (2023).

Publication Year 2023
Title Machine-learning model predictions and rasters of groundwater salinity in the Mississippi Alluvial Plain
DOI 10.5066/P9WSE8JS
Authors Courtney D Killian, Katherine J Knierim
Product Type Data Release
Record Source USGS Asset Identifier Service (AIS)
USGS Organization Lower Mississippi-Gulf Water Science Center - Nashville, TN Office
Rights This work is marked with CC0 1.0 Universal
Was this page helpful?