BAHAREH KARIMIDERMANI

Ms. BAHAREH KARIMIDERMANI


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2025 in Environments
Verified
Journal Article
Open access
PDF file
BKBAHAREH KARIMIDERMANI
BAHAREH KARIMIDERMANI
Christopher T. GreenChristopher T. Green
Christopher T. Green
GTGeoffrey Tick
Geoffrey Tick
HGHossein Gholizadeh
Hossein Gholizadeh
Wei WeiWei Wei
Wei Wei
YZYong Zhang
Yong Zhang
Rising nitrate contamination in water systems poses significant risks to public health and ecosystem stability, necessitating advanced modeling to understand nitrate dynamics more accurately. This study applies the long short-term memory (LSTM) modeling to investigate the hydrologic and environmental factors influencing nitrate concentration dynamics in rivers and aquifers across the state of Alabama in the southeast of the United States. By integrating dynamic data such as streamflow and groundwater levels with static catchment attributes, the machine learning model identifies primary drivers of nitrate fluctuations, offering detailed insights into the complex interactions affecting multi-year nitrate concentrations in natural aquatic systems. In addition, a novel LSTM-based approach utilizes synthetic surface water nitrate data to predict groundwater nitrate levels, helping to address monitoring gaps in aquifers connected to these rivers. This method reveals potential correlations between surface water and groundwater nitrate dynamics, which is particularly meaningful given the lack of water quality observations in many aquifers. Field applications further show that, while the LSTM model effectively captures seasonal trends, limitations in representing extreme nitrate events suggest areas for further refinement. These findings contribute to data-driven water quality management, enhancing understanding of nitrate behavior in interconnected water systems.

23 July 2026 in Water
Verified
Journal Article
Open access
PDF file
BKBAHAREH KARIMIDERMANI
BAHAREH KARIMIDERMANI
YZYong Zhang
Yong Zhang
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.