The performance of landslide susceptibility models critically depends on the quality of digital elevation models

• Published in: Geomatics, natural hazards and risk Vol. 11; no. 1; pp. 1075 - 1092
• Main Authors: Brock, Jonas, Schratz, Patrick, Petschko, Helene, Muenchow, Jannes, Micu, Mihai, Brenning, Alexander
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 01.01.2020; Taylor & Francis Ltd; Taylor & Francis Group
• Subjects: Additives; DEM; Digital Elevation Models; Elevation; Landslide; Landslides; Landslides & mudslides; Learning algorithms; Machine learning; Mathematical models; Median (statistics); Modelling; Performance prediction; Regression analysis; Statistical analysis; Support vector machines; Susceptibility; Terrain
• ISSN: 1947-5705; 1947-5713
• DOI: 10.1080/19475705.2020.1776403

Considering the critical importance of the quality of input data for landslide susceptibility, we investigate the performance improvements that can be achieved by different globally available digital elevation models (DEMs) using different state-of-the-art statistical and machine-learning models. For this purpose we compare the predictive performances achieved using terrain attributes derived from TanDEM-X DEM (12 m resolution and resampled to 30 m), ASTER DEM (30 m), SRTM DEM (30 m), and a DEM (25 m) interpolated from contour lines (1:25.000 map scale), exploiting the capabilities of logistic regression, generalized additive models, random forests and support vector machines. The study was conducted in the Buzău Sector of the Curvature Subcarpathians of Romania, a region highly susceptible to landslides. While the performances varied little among modelling techniques, the use of different DEMs strongly influenced the cross-validation accuracy of landslide susceptibility models. TanDEM-X (12 m) based susceptibility models outperformed models based on the other DEMs (median Area Under the Receiver Operating Characteristics Curve (AUROC) values 0.708-0.730). Models using ASTER-derived terrain attributes showed the poorest predictive capabilities (median AUROC 0.568-0.595). We conclude that the quality of DEMs is of critical importance in landslide susceptibility modelling, and greater efforts should be made to obtain suitable DEM products.