INTEGRATION OF GIS AND ADVANCED REMOTE SENSING TECHNIQUES FOR LANDSLIDE HAZARD ASSESSMENT: A CASE STUDY OF NORTHWEST SYRIA

Abstract. Landslide susceptibility and hazard mapping has been developed providing remarkable results through the integration of geographic information system (GIS) and remote sensing. In this regard, some approaches have considered the use of Sentinel-1 data and time-series interferometric synthetic aperture radar (InSAR) techniques, such as differential InSAR (D-InSAR) and persistent scatterers interferometric (PSI), for providing precise information about total amount and velocity of ground-surface deformations and landslides within a specific area during a specific time period which is important for disaster management’s planning process.

In this paper, artificial neural network (ANN) was used as a statistical analysis method for landslide susceptibility mapping in Northwest Syria using multi-layer perceptron (MLP) neural network on a training dataset of one dependent variable (landslide or non-landslide) and nine independent variables (slope, aspect, curvature, land cover, NDVI, lithology, distance from faults, distance from road, distance from stream networks). The resulting map of landslide susceptibility was validated using area under curve (AUC) analysis using a testing dataset which showed 90.28% of AUC value. Then, landslide susceptibility map was reclassified into high-moderate-low classes and integrated with intensity map of mean velocity of ground-surface deformations during the time period form (16 October 2018) until (21 March 2019) by using a landslide hazard matrix in a GIS environment in order to get landslide hazard map of the study area for that time period. The result shows that around 44.4%, 52.9% and 2.5% of total study area was classified as a high, moderate and low hazard zone of landslide, respectively.