Using boosted regression tree models to predict salinity in Mississippi embayment aquifers, central United States

Journal of American Water Resources Association
By: , and 

Links

Abstract

High salinity limits groundwater use in parts of the Mississippi embayment. Machine learning was used to create spatially continuous and three‐dimensional predictions of salinity across drinking‐water aquifers in the embayment. Boosted regression tree (BRT) models, a type of machine learning, were used to predict specific conductance (SC) and chloride (Cl), and total dissolved solids (TDS) was calculated from a correlation with SC. Explanatory variables for BRT models included well location and construction, surficial variables (e.g., soils and land use), and variables extracted from a groundwater‐flow model, including simulated groundwater ages. BRT model fits (r2) were 0.74 (SC and Cl) and 0.62 (TDS). BRT models provided spatially continuous salinity predictions across surficial and deeper aquifers where discrete water‐quality samples were missing. Uncertainty was smaller where salinity was lower, and models tended to underpredict in areas of highest salinity. Despite this, BRT models were able to capture areas of documented high salinity that exceed the TDS secondary maximum contaminant level for drinking water of 500 mg/L. Variables that served as surrogates for position along groundwater flowpaths were the most important predictors, indicating that much of the control on dissolved solids is related to rock‐water interaction as residence time increases. BRT models additionally support hypotheses of both surficial and deep sources of salinity.

Study Area

Publication type Article
Publication Subtype Journal Article
Title Using boosted regression tree models to predict salinity in Mississippi embayment aquifers, central United States
Series title Journal of American Water Resources Association
DOI 10.1111/1752-1688.12879
Edition 1010
Volume 56
Issue 6
Year Published 2020
Language English
Publisher Wiley
Contributing office(s) Lower Mississippi-Gulf Water Science Center
Description 20 p.
First page 1029
Country United States
State Alabama, Arkansas, Kentucky, Louisiana, Mississippi, Missouri, Tennessee
Other Geospatial Mississippi Embayment
Google Analytic Metrics Metrics page
Additional publication details