Print Email Facebook Twitter Improving global digital elevation models using space-borne GEDI and ICESat-2 LiDAR altimetry data Title Improving global digital elevation models using space-borne GEDI and ICESat-2 LiDAR altimetry data Author Narin, O.G. (TU Delft Optical and Laser Remote Sensing; Afyon Kocatepe University) Abdikan, Saygin (Hacettepe University) Gullu, Mevlut (Afyon Kocatepe University) Lindenbergh, R.C. (TU Delft Optical and Laser Remote Sensing) Balik Sanli, Fusun (Yildiz Technical University) Yilmaz, Ibrahim (Afyon Kocatepe University) Date 2024 Abstract 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. Subject GEDIGlobal digital elevation modelsICESat-2machine learning To reference this document use: http://resolver.tudelft.nl/uuid:3b2512f5-feee-49c0-8866-9e9ecae309cf DOI https://doi.org/10.1080/17538947.2024.2316113 ISSN 1753-8947 Source International Journal of Digital Earth: a new journal for a new vision, 17 (1) Part of collection Institutional Repository Document type journal article Rights © 2024 O.G. Narin, Saygin Abdikan, Mevlut Gullu, R.C. Lindenbergh, Fusun Balik Sanli, Ibrahim Yilmaz Files PDF Improving_global_digital_ ... y_data.pdf 5.81 MB Close viewer /islandora/object/uuid:3b2512f5-feee-49c0-8866-9e9ecae309cf/datastream/OBJ/view