Search

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. [ABSTRACT FROM AUTHOR]

Changes in snowpack associated with climatic warming has drastic impacts on surface energy balance in the cryosphere. Yet, traditional monitoring techniques, such as punctual measurements in the field, do not cover the full snowpack spatial and temporal variability, which hampers efforts to upscale measurements to the global scale. This variability is one of the primary constraints in model development. In terms of spatial resolution, active microwaves (synthetic aperture radar – SAR) can address the issue and outperform methods based on passive microwaves. Thus, high-spatial-resolution monitoring of snow depth (SD) would allow for better parameterization of local processes that drive the spatial variability of snow. The overall objective of this study is to evaluate the potential of the TerraSAR-X (TSX) SAR sensor and the wave co-polar phase difference (CPD) method for characterizing snow cover at high spatial resolution. Consequently, we first (1) investigate SD and depth hoar fraction (DHF) variability between different vegetation classes in the Ice Creek catchment (Qikiqtaruk/Herschel Island, Yukon, Canada) using in situ measurements collected over the course of a field campaign in 2019; (2) evaluate linkages between snow characteristics and CPD distribution over the 2019 dataset; and (3) determine CPD seasonality considering meteorological data over the 2015–2019 period. SD could be extracted using the CPD when certain conditions are met. A high incidence angle (>30∘) with a high topographic wetness index (TWI) (>7.0) showed correlation between SD and CPD (R2 up to 0.72). Further, future work should address a threshold of sensitivity to TWI and incidence angle to map snow depth in such environments and assess the potential of using interpolation tools to fill in gaps in SD information on drier vegetation types. [ABSTRACT FROM AUTHOR]

Arctic tundra landscapes are highly complex and are rapidly changing due to the warming climate. Datasets that document the spatial and temporal variability of the landscape are needed to monitor the rapid changes. Synthetic Aperture Radar (SAR) imagery is specifically suitable for monitoring the Arctic, as SAR, unlike optical remote sensing, can provide time series regardless of weather and illumination conditions. This study examines the potential of seasonal backscatter mechanisms in Arctic tundra environments for improving land cover classification purposes by using a time series of HH/HV TerraSAR-X (TSX) imagery. A Random Forest (RF) classification was applied on multi-temporal Sigma Nought intensity and multi-temporal Kennaugh matrix element data. The backscatter analysis revealed clear differences in the polarimetric response of water, soil, and vegetation, while backscatter signal variations within different vegetation classes were more nuanced. The RF models showed that land cover classes could be distinguished with 92.4% accuracy for the Kennaugh element data, compared to 57.7% accuracy for the Sigma Nought intensity data. Texture predictors, while improving the classification accuracy on the one hand, degraded the spatial resolution of the land cover product. The Kennaugh elements derived from TSX winter acquisitions were most important for the RF model, followed by the Kennaugh elements derived from summer and autumn acquisitions. The results of this study demonstrate that multi-temporal Kennaugh elements derived from dual-polarized X-band imagery are a powerful tool for Arctic tundra land cover mapping. [ABSTRACT FROM AUTHOR]