Open source Global Digital Elevation Models (GDEMs) serve as an important base for studies in geosciences. However, these models contain vertical errors due to various reasons. In this study, data from two Satellite LiDAR altimetry systems, GEDI and ICESat-2, were used to improve the vertical accuracy of GDEMs. Three different machine learning methods, namely an Artificial Neural Network (ANN), Extreme Gradient Boosting (XGBoost), and a Convolutional Neural Network (CNN), were employed to improve existing DEM data with satellite LiDAR data. The methodology was tested in five areas with varying characteristics. Ground control data were selected from high accuracy DEMs generated from Airborne LiDAR and GNSS data. The use of ANN method improved the vertical accuracy of SRTM data from 6.45 to 3.72 m in Test area-4. Similarly, the CNN method demonstrated an improvement in the vertical accuracy of bare ground SRTM data increasing from 3.4 to 0.6 m in Test area-4. In Test area-5, the ANN method improved the vertical accuracy of SRTM data with slopes between 30 and 60%, increasing from 3.8 to 0.5 m. Notably, the results underscore the successful improvement of GDEMs across all test areas.@en

Digital elevation models (DEM) are an essential data source in many professional disciplines, with the help of gridded height information and values such as slope and aspect produced from that information. In this study, Ice, Cloud and land Elevation Satellite-2 (ICESat-2) and Global Ecosystem Dynamics Investigation (GEDI) satellite-altimetry data, and SRTM, ASTER-GDEM, and ALOS World3D data were used as Global DEMs (GDEMs) data in three different areas (U.S.A., New Zealand and Puerto Rico). We used kriging methods for interpolation to create the new rasters. Point-based accuracies were compared with the GDEMs from satellite-altimetry systems and raster-based comparisons were made by deriving DEMs with satellite-altimetry data in three different areas. It was seen that the ICESat-2 data in point-based results had similar accuracy with other GDEMs. DEMs produced by using ICESat-2 and GEDI data together gave relatively better results than using alone. In particular, the correlation was found to be highly correlated with 99%.

@en