Rule-based semi-automated approach for the detection of landslides induced by 18 September 2011 Sikkim, Himalaya, earthquake using IRS LISS3 satellite images

Abstract

Landslide is considered as one of the most devastating and most costly natural hazards in highlands, which is triggered mainly by rainfalls or earthquakes. In comparison with other methods, landslide mapping and monitoring via remote sensing data products are considered as the least expensive method of data collection. The current research attempts to detect landslides which occurred due to a 6.9 magnitude earthquake in Sikkim Himalaya, India, on 18 September 2011 and also to establish the spatial relationship between landslides and the slope of the terrain. To detect the landslides, decision tree method was applied on two Indian remote sensing satellites linear imaging self-scanning sensor (LISS III) images acquired from 2007 and 2011 which were taken before and after the earthquake. As the study area was relatively huge for identifying the landslides, the region was separated into two parts: "tested study area" and "real study area". The overall accuracy of landslide detection was 76%, and 75% for tested and real study area, respectively. Then, the spatial relationship between the landslides and the slope of the terrain was conducted using the digital elevation model. The results revealed that most of the landslides occurred between the slope of 25 and 45 covering 2.3 km 2 and no landslide recorded in the slope of 65 -90 in the real study area. The results obtained in this study may be useful for decision-making and policy support towards reconstruction effort after the landslide occurrence. In addition, the information can be useful for reducing the risk of potential damages to substructures and properties by developing new and efficient strategies.

A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan)

“…Therefore, landslide inventory maps are usually prepared by extracting the landslide information from RS images, including optical satellite images and synthetic aperture radar (SAR) data, because of the relatively low cost associated with obtaining RS images and their wide coverage area 13 , 14 . There is a range of common landslide inventory mapping approaches using optical satellite images, such as the manual extraction of landslide areas based on an expert’s visual interpretation, rule-based image classification approaches carried out by an experienced analyst 1 , 15 , analyzing of the multi-temporal SAR interferometry techniques 16 , applying optical or LiDAR data from unmanned aerial vehicles 17 , 18 and the semi-automatic/ automatic image classification using Machine Learning (ML) models in both pixel- and object-based working environments 19 , 20 .…”

Landslides investigations from geoinformatics perspective: quality, challenges, and recommendations

“…Researchers implemented the diagnosis of landslides process by means of geographical distribution of landslides, developing algorithms and codes (Pirasteh et al 2015), and generating susceptibility maps, and models. Also, some of the researchers attempted the semi-automated approach (Siyahghalat et al 2016), identifying landslide-contributing factors, accuracy performance, geological and engineering perspective, utilizing remote sensing technologies, and early warning systems (Wu & Sidle 1995;Zhou et al 2003;Watts 2004;Jebur et al 2014;Lee et al 2014;Su et al 2015). Nevertheless, very few researchers have discussed on challenges and qualities of the output with a reliable recommendation as well as developing an algorithm for landslides detection from the LiDAR point clouds data.…”

Time-series metrics applied to land use and land cover mapping with focus on landslide detection

“…SVM and ML have been used to identify landslides in São Paulo state coast (SP, Brazil), in which the SVM presented better performance than ML, especially when associated with the NDVI. 36 Moreover, studies show that decision tree algorithms have been used in landslide detection 37 and LULC mapping, 38 and presented suitable results. The RF algorithm can be used both for classification and regression modeling.…”