Detecting Coseismic Landslides in GEE Using Machine Learning Algorithms on Combined Optical and Radar Imagery

• Published in: Remote sensing (Basel, Switzerland) Switzerland), 2024-05, Vol.16 (10), p.1722
• Main Authors: Peters, Stefan, Liu, Jixue, Keppel, Gunnar, Wendleder, Anna, Xu, Peiliang
• Format: Article
• Language: English
• Subjects: 2018 AD; Accuracy; Algorithms; Artificial satellites in remote sensing; Case studies; classification; Data mining; Dielectric properties; Disaster management; Earthquake damage; Earthquakes; Emergency management; Emergency preparedness; Geospatial data; Google Earth Engine; Haiti; Japan; landslide detection; Landslides; Landslides & mudslides; Learning algorithms; Localization; Machine learning; New Zealand; Papua New Guinea; Radar; Radar imaging; Radar satellites; Remote sensing; Remote sensors; Satellite imagery; satellite remote sensing; Seismic activity; Sensors; Synthetic aperture radar; Topography; Transfer learning; Vegetation; Volcanic activity; Volcanic eruptions; Volcanism
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs16101722

Landslides, resulting from disturbances in slope equilibrium, pose a significant threat to landscapes, infrastructure, and human life. Triggered by factors such as intense precipitation, seismic activities, or volcanic eruptions, these events can cause extensive damage and endanger nearby communities. A comprehensive understanding of landslide characteristics, including spatio-temporal patterns, dimensions, and morphology, is vital for effective landslide disaster management. Existing remote sensing approaches mostly use either optical or synthetic aperture radar sensors. Integrating information from both these types of sensors promises greater accuracy for identifying and locating landslides. This study proposes a novel approach, the ML-LaDeCORsat (Machine Learning-based coseismic Landslide Detection using Combined Optical and Radar Satellite Imagery), that integrates freely available Sentinel-1, Palsar-2, and Sentinel-2 imagery data in Google Earth Engine (GEE). The approach also integrates relevant spectral indices and suitable bands used in a machine learning-based classification of coseismic landslides. The approach includes a robust and reproducible training and validation strategy and allows one to choose between five classifiers (CART, Random Forest, GTB, SVM, and Naive Bayes). Using landslides from four different earthquake case studies, we demonstrate the superiority of our approach over existing solutions in coseismic landslide identification and localization, providing a GTB-based detection accuracy of 87–92%. ML-LaDeCORsat can be adapted to other landslide events (GEE script is provided). Transfer learning experiments proved that our model can be applied to other coseismic landslide events without the need for additional training data. Our novel approach therefore facilitates quick and reliable identification of coseismic landslides, highlighting its potential to contribute towards more effective disaster management.