About

Laura Condon is a faculty member in the Hydrology & Atmospheric Sciences department at the University of Arizona. Her research focuses on large scale groundwater surface water interactions and water sustainability at regional to continental scales. She is involved in computational and numerical modeling, particularly related to water resources and environmental systems. Her work aims to address water sustainability challenges through advanced modeling techniques and interdisciplinary approaches.

Research topics

• Environmental science
• Geology
• Computer Science
• Ecology
• Geography
• Geotechnical engineering
• Meteorology
• Cartography
• Environmental engineering
• Physics
• Oceanography
• Environmental resource management
• Computational science
• Mechanics
• Parallel computing
• Engineering

Selected publications

• Modular approach to calibration of supra-regional scale integrated surface-groundwater models

  2026-03-14

  articleOpen accessCorresponding

  This study presents a theoretically sound operational framework for calibrating large-scale, high-fidelity integrated surface water-groundwater models to improve their reliability for water resources management. The approach combines ParFlow-CLM simulations of three-dimensional variably saturated flow with local sensitivity analysis and Gaussian Process Regression surrogates to enable efficient multi-stage calibration against water table depth and river discharge observations. The framework is applied to the entire system associated with the Po River District (87,000 km2) in northern Italy, resulting in the first robustly calibrated high-fidelity model at this spatial scale. Calibrated model parameters include hydraulic conductivities of the main subsurface geomaterials and Manning roughness coefficients of major rivers in the area. Our results show that clay hydraulic conductivity is a primary driver for groundwater table dynamics, while channel roughness dominates river discharge. Overall, the proposed strategy provides a robust computational framework for scenario analysis and sustainable water management under climate and anthropogenic pressures.

  PublisherDOI

• A high-resolution water table depth (WTD) map for the contiguous United States

  Open MIND · 2026-02-06

  dataset

  A 1-arcsec (~30 m) resolution water table depth (WTD) map for the contiguous United States using machine learning methods trained on over one million well observations compiled from multiple groundwater databases spanning 1914-2023. A random forest model with 300 decision trees was trained on 80% of these data using input variables including climatology (precipitation, temperature, PME), subsurface properties (hydraulic conductivity, soil texture), and topographic features (elevation, slope, distances to streams), achieving test performance of r = 0.79, RMSE = 14.94 m, and NSE = 0.62. Ma, Y., Condon, L.E., Koch, J. et al. High resolution US water table depth estimates reveal quantity of accessible groundwater. Commun Earth Environ 7, 45 (2026). https://doi.org/10.1038/s43247-025-03094-3 Data also accessible via the HydroData platform https://hydroframe.org/hydrodata

  DOI

• Accurately and Efficiently Predicting High-Resolution Inundation using a Hybrid Machine Learning and Physics-Based Approach

  2026-03-14

  articleOpen accessCorresponding

  Predicting high-resolution inundation at large spatial and temporal scales is important in understanding future water availability and flood risk. Classically, hydrologic models have been used to model inundation, but the computational expense associated with applying hydrologic models at large scales has motivated the use of other methodologies, such as machine learning. We propose a hybrid physics-based and machine learning modeling approach to produce high-resolution inundation maps at a much lower computational cost than high-resolution physics-based modeling while still maintaining high accuracy. This methodology is then tested in a representative watershed in Colorado, USA. The proposed hybrid physics-based and machine learning modeling approach consists of a coarse spatial resolution hydrologic model and a random forest downscaling postprocessing step. First, a 1km resolution integrated surface-subsurface hydrologic model, ParFlow-CLM, is ran for the spatial and temporal domain of interest. Then, the resultant modeled inundation as well as additional climate and geographical parameters are fed into a random forest model which predicts inundation at a higher spatial resolution. We tested this methodology in a 1800km2 watershed in Colorado, USA during the 2019 water year to predict modeled inundation produced by a 100m resolution hydrologic model. In our test case, this hybrid methodology predicted whether each fine resolution cell is inundated at each hourly timestep correctly >97% of the time and maintained high accuracy in unseen timesteps as well as in unseen locations within the same region. We will also discuss next steps to predict real-world inundation by training the random forest model on 30m resolution satellite data. This study shows the potential for this methodology to be applied at the continental scale to predict high-resolution inundation accurately and efficiently.

  PublisherDOI

• High resolution US water table depth estimates reveal quantity of accessible groundwater

  Communications Earth & Environment · 2026-01-14 · 2 citations

  articleOpen access

  Groundwater is the largest accessible freshwater on Earth, yet its quantity and distribution remain unknown. Here, we develop a high-resolution (approximately 30 m) estimate of water table depth over the continental United States using machine learning that includes uncertainty. We estimate that there is 306,500 km³ (uncertainty range: 291,850–316,720 km³) of groundwater over North America. This represents our highest resolution estimate of accessible freshwater to date, supported by robust statistical performance. We calculate total and accessible groundwater storage, and results show that coarse resolution products are systematically biased in their estimates locally, where decisions are made, as well as at large scales. Our approaches are spatially extensive and locally relevant and thereby bridge a gap between remote sensing and point observations. A high-resolution estimate finds about 300,000 cubic kilometers of accessible groundwater across North America, which reduces uncertainty in freshwater distribution and bridges gaps between remote sensing and field data.

  PublisherOA PDFDOI

• A prototype hyper-resolution groundwater digital twin for the contiguous United States: integrating physics-based modeling, machine learning, and observations

  Journal of Hydrology · 2026-02-24

  articleOpen access

  • We develop a physics-guided machine learning model for groundwater modeling. • Our model reliably estimates groundwater dynamics at large scales. • We provide daily 1 arcsec water table depth data for the contiguous United States. • This model is a prototype groundwater digital twin for the United States. To advance large-scale hyper-resolution groundwater modeling, we leverage existing physically-based simulation results and water table depth (WTD) observations to develop a prototype groundwater digital twin for the contiguous United States (CONUS). This framework represents a continuously updatable virtual representation that integrates observations with physics-based predictions to support operational decision making. An adjusted random forest model is trained to downscale 1 km simulation results from the integrated physically-based hydrologic model ParFlow-CLM to 1 arcsec (∼30 m) and bias-correct to observations, producing daily 1 arcsec WTD and associated uncertainties across the CONUS. Trained on water year 2003 (WY2003), the model reliably estimates temporal variations in WTD at most previously unseen grid cells, achieving a median Spearman’s ρ of 0.66. Over half of the grid cells that contain continuous daily records in WY2003 exhibit good performance, with ρ ≥ 0.5. At the subbasin scale, the digital twin captures more detailed groundwater variability than ParFlow-CLM, especially in areas with strong surface–groundwater interactions. During the future time period (WY2024), the model consistently outperforms ParFlow-CLM, increasing the median ρ by 0.13. Enabled by multi-GPU computing, the digital twin generates each daily 1-arcsec resolution WTD map in approximately 35 min of GPU time, providing insights into groundwater systems across multiple scales. The success of the physics-guided machine learning (ML) digital twin highlights the advantage of combining ML and physically-based modeling in groundwater applications. This groundwater digital twin demonstrates a path toward operational capability, enabling near-real-time monitoring, scenario exploration, and decision support at unprecedented spatial resolution.

  PublisherDOI

• A Hybrid Machine Learning and Physics-Based Approach Accurately Models High-Resolution Inundation

  SSRN Electronic Journal · 2026-01-01

  preprintOpen access
  PublisherDOI

• A high-resolution water table depth (WTD) map for the contiguous United States

  Zenodo (CERN European Organization for Nuclear Research) · 2026-02-06

  datasetOpen access

  A 1-arcsec (~30 m) resolution water table depth (WTD) map for the contiguous United States using machine learning methods trained on over one million well observations compiled from multiple groundwater databases spanning 1914-2023. A random forest model with 300 decision trees was trained on 80% of these data using input variables including climatology (precipitation, temperature, PME), subsurface properties (hydraulic conductivity, soil texture), and topographic features (elevation, slope, distances to streams), achieving test performance of r = 0.79, RMSE = 14.94 m, and NSE = 0.62. Ma, Y., Condon, L.E., Koch, J. et al. High resolution US water table depth estimates reveal quantity of accessible groundwater. Commun Earth Environ 7, 45 (2026). https://doi.org/10.1038/s43247-025-03094-3 Data also accessible via the HydroData platform https://hydroframe.org/hydrodata

  PublisherDOI

• Towards Water Resilience: A Multi-Stage Calibration Framework for Large-Scale integrated Surface–Subsurface Hydrological Models

  SSRN Electronic Journal · 2025-01-01

  preprintOpen access
  PublisherDOI

• High resolution US water table depth estimates reveal quantity of accessible groundwater

  Research Square · 2025-05-02

  preprintOpen access
  PublisherOA PDFDOI

• Surrogate modeling for large-scale integrated hydrologic modeling: A case study in deep learning, model inversion, and hybrid methods across the Continental United States

  2025-03-15

  preprintOpen accessSenior authorCorresponding

  Use of complex, high-resolution integrated hydrologic models offer the most comprehensive and detailed representations of groundwater, surface water, and land surface processes, but are challenging to use for forecasting tasks due to high computational costs and parameter uncertainty. On the flipside, machine learning approaches are highly accurate and can be computationally frugal for targeted tasks, but are difficult to audit and must be retrained to adapt to new tasks or domains.In this work we present several case studies of using deep learning surrogate modeling approaches for integrated hydrologic modeling that alleviates many of the weaknesses of taking a purely physically based or purely data driven approach. We first show how deep learning surrogates can readily achieve orders of magnitude speedup over the original physically based models with high degree of accuracy, which allows for on demand forecasting. While this approach is great for generating forecasts from the original model configuration, it is still challenging to adapt to new scenarios such as use in parameter calibration or running long simulations such as climate change scenarios. We close the presentation by discussing recent work to address these challenges using model inversion techniques and by developing hybrid model emulation strategies.

  PublisherDOI

Recent grants

• Collaborative Research: Sustainability in the Food-Energy-Water nexus; integrated hydrologic modeling of tradeoffs between food and hydropower in large scale Chinese and US basins

  NSF · $257k · 2018–2023

• CAREER: The Role of Groundwater Storage in Earth System Dynamics; Research to Improve Understanding of Current Hydrologic Regimes and Future Climate Response

  NSF · $495k · 2020–2025

• Collaborative Research: Framework: Software: NSCI : Computational and data innovation implementing a national community hydrologic modeling framework for scientific discovery

  NSF · $700k · 2018–2024

• NSF Convergence Accelerator - Track D: Hidden Water and Hydrologic Extremes: A Groundwater Data Platform for Machine Learning and Water Management

  NSF · $1.0M · 2020–2022

Frequent coauthors

• R. M. Maxwell

  Princeton University

  135 shared

• Jun Zhang

  Nanyang Technological University

  30 shared

• Hoang Tran

  Pacific Northwest National Laboratory

  28 shared

• Jennie C. Steyaert

  16 shared

• Stefan Kollet

  Forschungszentrum Jülich

  16 shared

• Luis De La Fuente

  University of Arizona

  15 shared

• D. Tijerina

  Princeton University

  13 shared

• Agnès Ducharne

  12 shared

Education

• PhD Hydrolgy

  Colorado School of Mines

  2015

• MS Hydrology

  Colorado School of Mines

  2012

• B.S. Environmental Engineering

  Columbia University

  2008