Skip to content

LIDAR-corrected Digital Terrain Model for Hydrological Applications using Deep Learning

Type of project

M.Sc.

Contact

Puzhao Zhang (puzh@dhigroup.com)

Topic

Digital Elevation Models (DEMs) are critical inputs for hydraulic modeling, particularly in data-scarce regions where ground-based measurements are limited. However, many widely available DEMs, such as those derived from the Copernicus GLO-30 dataset, are Digital Surface Models (DSMs), which include surface features like buildings and vegetation. This discrepancy presents challenges for 2D hydraulic modeling, as accurate flood propagation analysis depends on reliable terrain elevation data that excludes these surface features. 

Spaceborne LiDAR missions like ICESat-2 and GEDI offer valuable complementary data by providing high-precision elevation measurements of ground, canopy, and structures. By leveraging these datasets, there is a promising opportunity to develop methodologies that transform DSMs into Digital Terrain Models (DTMs) for hydrodynamic applications. 

This project aims to improve the accuracy of terrain elevation models for hydraulic modelling by predicting the elevation difference between DSMs and DTMs using spaceborne LiDAR observations, multi-source satellite data, and deep learning techniques. The goal is to provide a scalable and hydrologically sound solution for hydraulic modelers.

Relevance to DHI

Accurate DTMs that do not include the effects of buildings vegetation are crucial for hydraulic modelling, flood modelling and other water related applications. While specific airborne LIDAR missions can be conducted to survey an area of interest, these are often expensive and depend on the project budget. Recent global products have been released for research and educational purposes that improve upon existing DEMs, but DHI would benefit by developing more accurate in-house DTMs for commercial use. Doing so would increase the ability of DHI to model water dynamics in data scare regions using free and open data sources.

What is the student's contribution

*Project Objectives *

  • Prepare a training dataset that includes input features and target DTM
  • Develop an effective deep learning to predict the elevation difference between DTM and DSM

  • Assess the performance of the derived DTM for hydrological applications   *The ideal candidate should possess: *

  • Knowledge in satellite data and elevation model

  • Experience in prepare geospatial dataset
  • Experience in building and training deep learning models for regression tasks

References

Hawker, L., Uhe, P., Paulo, L., Sosa, J., Savage, J., Sampson, C., & Neal, J. (2022). A 30 m global map of elevation with forests and buildings removed. Environmental Research Letters, 17(2), 024016.