IMCLASS – A USER-TAILORED MACHINE LEARNING IMAGE CLASSIFICATION CHAIN FOR CHANGE DETECTION OR LANDCOVER MAPPING

Rainfall-induced landslides cause significant damage and fatality worldwide, but we have few datasets constraining the impact of individual storms. We present and analyze 8 landslide inventories, with >150 to >150 00 landslides, comprehensively representing the landslide population caused by 8 storms from Asia and the Americas. We found that the total storm rainfall is a major control on total landsliding, landslide size, and that storms trigger landslides on less steep slopes than earthquakes.

The paper proposes an approach to prepare a multi-date landslide inventory for the Ubaye valley (French Alps), a complex mountainous area affected by several landslide types with different degrees of activity. The inventory covering the period 1956-2010 have been analysed in order to quantify the uncertainties associated to the mapping, to measure the evolution of morphological indicators and to estimate temporal occurrence. Evolution of landslide activity is compared to other inventory sources.

The objective of this paper is to demonstrate the applicability of ground-penetrating radar (GPR) for monitoring the displacement of permanent slow-moving landslides affected by seasonal kinematic pattern and acceleration events. GPR data are used here to estimate the vertical movement of two rotational slides, since 1982, in combination with other surveying techniques.