Super-Resolution for Groundwater Models Using Multi-Resolution MIKE SHE Grids

Type of project

M.Sc.

Contact

Jesper Mariegaard (jem@dhigroup.com)

Topic

Structured-grid groundwater models like MIKE SHE are often run at high spatial resolution to capture important hydrogeological variations. However, this increases runtime, especially in large or operational setups. This project explores whether techniques inspired by computer vision super-resolution (e.g., CNNs or deep learning upsampling) can be applied to map coarse-resolution groundwater model results to fine-resolution outputs. The student will experiment with deep learning models that learn this mapping on selected MIKE SHE test cases.

Relevance to DHI

Running MIKE SHE at high spatial resolution is often too costly for real-time or large-scale simulations. If we can infer high-resolution groundwater heads or fluxes from coarse models, it may allow for faster operational workflows and improved scalability of groundwater applications.

What is the student's contribution

Train and evaluate a deep learning model for "super-resolution" of groundwater simulation results from MIKE SHE. The expected outcome is a trained model, code, and an evaluation of accuracy and performance on 1–2 test cases.