Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

GeoFUSE: A High-Efficiency Surrogate Model for Seawater Intrusion Prediction and Uncertainty Reduction

Su Jiang, Chuyang Liu, Dipankar Dwivedi

Abstract

Seawater intrusion into coastal aquifers poses a significant threat to groundwater resources, especially with rising sea levels due to climate change. Accurate modeling and uncertainty quantification of this process are crucial but are often hindered by the high computational costs of traditional numerical simulations. In this work, we develop GeoFUSE, a novel deep-learning-based surrogate framework that integrates the U-Net Fourier Neural Operator (U-FNO) with Principal Component Analysis (PCA) and Ensemble Smoother with Multiple Data Assimilation (ESMDA). GeoFUSE enables fast and efficient simulation of seawater intrusion while significantly reducing uncertainty in model predictions. We apply GeoFUSE to a 2D cross-section of the Beaver Creek tidal stream-floodplain system in Washington State. Using 1,500 geological realizations, we train the U-FNO surrogate model to approximate salinity distribution and accumulation. The U-FNO model successfully reduces the computational time from hours (using PFLOTRAN simulations) to seconds, achieving a speedup of approximately 360,000 times while maintaining high accuracy. By integrating measurement data from monitoring wells, the framework significantly reduces geological uncertainty and improves the predictive accuracy of the salinity distribution over a 20-year period. Our results demonstrate that GeoFUSE improves computational efficiency and provides a robust tool for real-time uncertainty quantification and decision making in groundwater management. Future work will extend GeoFUSE to 3D models and incorporate additional factors such as sea-level rise and extreme weather events, making it applicable to a broader range of coastal and subsurface flow systems.

GeoFUSE: A High-Efficiency Surrogate Model for Seawater Intrusion Prediction and Uncertainty Reduction

Abstract

Seawater intrusion into coastal aquifers poses a significant threat to groundwater resources, especially with rising sea levels due to climate change. Accurate modeling and uncertainty quantification of this process are crucial but are often hindered by the high computational costs of traditional numerical simulations. In this work, we develop GeoFUSE, a novel deep-learning-based surrogate framework that integrates the U-Net Fourier Neural Operator (U-FNO) with Principal Component Analysis (PCA) and Ensemble Smoother with Multiple Data Assimilation (ESMDA). GeoFUSE enables fast and efficient simulation of seawater intrusion while significantly reducing uncertainty in model predictions. We apply GeoFUSE to a 2D cross-section of the Beaver Creek tidal stream-floodplain system in Washington State. Using 1,500 geological realizations, we train the U-FNO surrogate model to approximate salinity distribution and accumulation. The U-FNO model successfully reduces the computational time from hours (using PFLOTRAN simulations) to seconds, achieving a speedup of approximately 360,000 times while maintaining high accuracy. By integrating measurement data from monitoring wells, the framework significantly reduces geological uncertainty and improves the predictive accuracy of the salinity distribution over a 20-year period. Our results demonstrate that GeoFUSE improves computational efficiency and provides a robust tool for real-time uncertainty quantification and decision making in groundwater management. Future work will extend GeoFUSE to 3D models and incorporate additional factors such as sea-level rise and extreme weather events, making it applicable to a broader range of coastal and subsurface flow systems.

Paper Structure

This paper contains 15 sections, 12 equations, 41 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methodology
  3. Beaver Creek Model and Governing Equations Using PFLOTRAN
  4. Surrogate Model Development using U-FNO
  5. GeoFUSE: Data Assimilation Framework Utilizing ESMDA with Parameterization
  6. Results
  7. Surrogate Model (U-FNO) Training and Computational Efficiency
  8. Comparisons of U-FNO Predictions and PFLOTRAN Simulations
  9. Uncertainty Reduction Through GeoFuse: Data Assimilation and Model Calibration
  10. Discussion
  11. Surrogate Model Accuracy and Limitations
  12. Effectiveness of GeoFUSE
  13. Implications for Seawater Intrusion and Floodplain Management
  14. Future Work, Model Scalability, and Caveats
  15. Concluding Remarks

Figures (41)

  • Figure 1: Simulation setup for the Beaver Creek tidal stream-floodplain system. The model simulates subsurface flow and reactive transport using PFLOTRAN, driven by Dirichlet boundary conditions on the upland and stream, with seepage and no-flow boundary conditions applied to the ground surface and bottom, respectively. The initial simulation spans four years to reach steady-state groundwater conditions, followed by a 20-year seawater intrusion simulation. Three monitoring wells are used for validation throughout the simulation.
  • Figure 2: Prior realization 1
  • Figure 3: Prior realization 2
  • Figure 4: Prior realization 3
  • Figure 6: Schematic of U-FNO, modified based on wen2022u.
  • ...and 36 more figures