Journal Article

Machine Learning Calibration of Groundwater Table Depth in ELM: Impact on Land Surface Hydrology and Land‐Atmosphere Fluxes

Leung, L. Ruby, Fang, Yilin

2026

Overview

Accurate representation of groundwater table depth (GWTD) is crucial for simulating hydrological cycling in Earth system models (ESM). Nevertheless, there is a notable gap in the literature regarding the validation of GWTD simulations in ESMs and their subsequent impact on downstream hydrological components. This study explores the calibration of parameterization of global GWTD using machine learning within the Energy Exascale Earth System Model (E3SM) Land Model (ELM). Despite achieving significant gains in simulating GWTD through calibration, offline ELM simulations unexpectedly show that these improvements do not translate to substantial enhancements in model performance for other key hydrological variables, including soil moisture (SM), runoff, groundwater contribution to runoff or base flow index (BFI), and evapotranspiration and its partitioning. The performance in SM and runoff was even degraded in some regions, while BFI was mostly overestimated. Although there is significant improvement in GWTD within the critical range of 1–5 m, where groundwater traditionally influences land surface energy fluxes, these improvements occurred mostly in humid areas where the impact of GWTD on surface processes is minimal. Although the impacts of model calibration are generally small in offline ELM simulations, coupled land‐atmosphere simulations exhibit much stronger responses to GWTD calibration, highlighting the role of land‐atmosphere feedbacks in Earth system modeling. These findings underscore the need for integrated calibration strategies that simultaneously optimize multiple hydrological variables. However, if a single‐variable approach is necessary, it is crucial to establish clear priorities for calibration, identifying the most critical variables that have the greatest impact on overall model performance. Plain Language Summary Accurately modeling the groundwater table depths is crucial for understanding how water moves through the environment. However, there's a research gap in evaluating how well the Earth system models perform in water table depths and how they affect other important hydrological variables like SM and runoff. In this study, machine learning was used to improve the modeling of groundwater table depth in an Earth System Model. While the improvements in water table depth were notable, they didn't consistently improve other variables. In some cases, the model's performance even worsened for certain variables. However, the improvements had a much greater impact in the coupled land‐atmosphere simulations. This suggests that feedback between land and atmosphere is important for capturing the full impact of groundwater on the climate system. Overall, the study underscores the need for a more holistic approach that considers multiple hydrological variables, rather than focusing on a single target at a time. Key Points Machine learning techniques can be used to effectively calibrate groundwater table depth (GWTD) in the E3SM Land Model Enhancements in GWTD calibration do not significantly improve surface runoff and energy fluxes in offline simulations The amplified effects of GWTD calibration in coupled versus offline simulations underscore the importance of coupled model calibration

• Publisher: John Wiley & Sons, Inc,American Geophysical Union (AGU)
• Subject: Aquifers / Atmosphere / Base flow / Base runoff / Calibration / Drainage / Earth / Energy Exascale Earth System Model (E3SM) / Evapotranspiration / Flow index / Groundwater / Groundwater runoff / Groundwater table / groundwater table depth / Humid areas / Hydrology / land‐atmosphere interactions / Machine learning / Moisture content / Parameterization / Precipitation / Runoff / Soil moisture / Topography / Water table