Detail Abstract

Enhancement of Satellite DEM Accuracy using Machine Learning and Remote Sensing data for Flood Mapping

Abstract

The digital elevation model (DEM) is crucial for various applications, such as land management and flood planning, as it reflects the actual topographic characteristic on the Earth’s surface. However, it is quite a challenge to acquire the high-quality DEM, as it is very time-consuming, costly, and often confidential. This research explores a satellite DEM enhancement scheme using a machine learning (ML) that could improve the German Aerospace’s TanDEM-X (12 m resolution). The ML was first trained in Nice, France, with a high spatial resolution surveyed DEM (1 m) and then applied on a faraway city, Singapore, for validation. In the training, Sentinel-2 and TanDEM-X data of the Nice area were used as the input data, while the ground truth observation data of Nice were used as the target data. The applicability of enhanced DEM was finally conducted at a different site in Singapore. The enhanced DEM shows a significant reduction in the root mean square error of 43.6% in Singapore. This research also demonstrated the application of the trained ML on Ho Chi Minh City, Vietnam, where the ground truth data are not available; for cases such as this, a visual comparison with Google satellite imagery was then utilized. The enhanced DEM with 10 m resolution shows much clearer land shapes (particularly the roads and buildings).