Hybrid Projections of Nitrate Response to Hydroclimatic Variability in Selected U.S. Surface-Water and Groundwater Systems
Year: 2026
Type: article
Abstract: Assessing nitrate sensitivity to hydroclimatic variability is important for evaluating water-quality vulnerability under hydroclimatic variations in coupled surface-water and groundwater systems. This study applies a hybrid, scenario-based projection framework combining a Long Short-Term Memory (LSTM) model and Weighted Regression on Time, Discharge, and Season with Projections (WRTDS-P) to examine nitrate plus nitrite responses under idealized wet and dry conditions across seven U.S. river basins and three associated groundwater wells. LSTM projections evaluate conditional sensitivity to altered precipitation forcing, while WRTDS-P projections assess discharge-conditioned responses based on empirically derived concentration–discharge relationships. Results show strong basin-scale heterogeneity in nitrate sensitivity. Agriculturally dominated Midwestern and central U.S. basins generally exhibit higher nitrate concentrations under the idealized wet scenarios, whereas basins influenced by groundwater buffering, flow regulation, or managed hydrology show weak or slightly negative wet–dry responses. For the three evaluated wells, groundwater projections show site-specific damped or delayed responses relative to nearby surface-water systems, reflecting aquifer storage and legacy nitrogen effects, although the Illinois well shows a larger projected wet–dry amplitude than the associated river. Cross-framework comparison reveals moderate agreement in response direction but notable differences in magnitude, highlighting sensitivity to model structure and forcing assumptions. These findings emphasize the value of hybrid projection frameworks for cross-framework sensitivity analysis and for interpreting nitrate vulnerability under hydroclimatic variation while accounting for uncertainty across surface-water and groundwater systems.
Source: Water
Authors: Bahareh KarimiDermani, Yong Zhang
Institution: University of Alabama
Language: English
Subfield: Environmental Chemistry
Field: Environmental Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,137
Funder: National Science Foundation
OpenAlex ID: W7170180065
