Regional Landslide Identification Based on Susceptibility Analysis and Change Detection

Alu, Si; Zhang, Jiquan; Tong, Siqin; Lai, Quan; Zhang, Jiquan; Li, Na; Bao, Yu

doi:10.3390/ijgi7100394

Cited by 16 publications

(8 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this approach has difficulty in meeting rapid emergency needs. Compared with visual interpretation, semi-automatic extraction technology, especially change detection, can quickly obtain landslide inventories through remote sensing images pre-and post-earthquake [29], [30], [35]. However, due to uncertain factors, such as cloud, fog, and terrain effects, it is difficult to obtain detailed complete landslide inventory.…”

Section: A Acquisition Of An Incomplete Landslide Inventorymentioning

confidence: 99%

Application of an Incomplete Landslide Inventory and One Class Classifier to Earthquake-Induced Landslide Susceptibility Mapping

Chen

Zhang

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Rapid and effective evaluation of landslide susceptibility after earthquakes is critical for various applications, such as emergency rescue, land planning, and disaster prevention. Current research suffers from the lack of a complete landslide inventory and sample selection uncertainty issues. To solve these problems, this study presents a landslide susceptibility mapping model that integrates one-class support vector machine (OCSVM) and an incomplete landslide inventory, which was established with the aid of change detection from bi-temporal Landsat images. Wenchuan County is selected as the study area to test the performance of the proposed method. The proposed method is also compared with standard two-class SVM that selects a sample randomly. Experimental results show that OCSVM can achieve better performance than SVM when only an incomplete landslide inventory is available. The findings of this study can be applied to determine regional landslide susceptibility after earthquakes and provide an essential reference for emergency response.

show abstract

Section: A Acquisition Of An Incomplete Landslide Inventorymentioning

confidence: 99%

Application of an Incomplete Landslide Inventory and One Class Classifier to Earthquake-Induced Landslide Susceptibility Mapping

Chen

Zhang

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In [20], the hybrid approaches introduced further for the landslide detection using two well know techniques such as susceptibility analysis and change detection thresholding. They presented a quantitative analysis of the method and claiming improved accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

Methods of Landslide Detection using GIS and Remote Sensing Images

Varangaonkar¹,

Rode²

2019

IJEAT

View full text Add to dashboard Cite

The most challenging and damaging natural disaster is the landslides around the mountainous terrain especially in the western and northern regions of India. The landslides lead to several damages in terms of socio-economic impacts, thus it gains significant researcher's attention since from the last two decades to study and early prediction of landslides. The automatic and accurate landslide detection and localization become essential to suppress the socio-economic impacts with help using sensing remote images & Geographical Information System (GIS). Nowadays remote sensing images provide useful information combined with the GIS environment related to the spatial factors that are influencing the landslide occurrence. The fundamental prerequisite for the landslide prediction using GIS is landslide inventory. In India, the satellite images collected using remote sensors such as LANDSAT ETM+, ASTER, IRS P6, etc. to form the landslide information over the parameters like aspect, slope, drainage density, relative relief, etc. Thus using the remote sensing images, the monitoring of landslide introduced. The landslide prediction using the remote sensing images however suffered from the various challenges. This paper presents the systematic review of various landslide prediction and localization methods using the remote sensing images and GIS information regardless of the study areas. The comparative analysis and the current research challenges for designing the automated landslide detection framework discussed based on the literature review.

show abstract

“…Landslides change the ground surface of the Earth; thus, the progress of mapping landslides can be considered the land cover change detection (LCCD) problem [10], [11], [12]. Recently, landslides can be captured and depicted in enhanced details with the convenience of VHR remote sensing images (satellite, airborne, and UAV platforms) [13], [14].…”

Section: Introductionmentioning

confidence: 99%

Landslide Inventory Mapping With Bitemporal Aerial Remote Sensing Images Based on the Dual-Path Fully Convolutional Network

Lv¹,

Liu²,

Kong

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

This study presents a novel dual-path full convolutional network (DP-FCN) model for constructing a landslide inventory map (LIM) with bitemporal very high-resolution (VHR) remote sensing images. Unlike traditional methods for drawing LIM, the proposed DP-FCN directly draws LIMs from the bitemporal aerial images with VHR through a trained deep neural network without generating the change magnitude map. Thus, the proposed approach can effectively reduce the effects of pseudo changes caused by phenological differences rather than landslide events. The proposed DP-FCN model contains two modules, namely, deep feature extraction and joint feature learning networks. Deep feature extraction aims to reduce redundancy while extracting the high-level deep features from bitemporal images. Joint feature learning establishes the relationship between the deep features of bitemporal images and the ground reference map. Experiments on the real datasets of the landslide sites in Lantau Island of Hong Kong, China demonstrate the feasibility and superiority of the proposed approach in drawing LIM with VHR remote sensing images. Moreover, compared with the results obtained by the state-of-the-art algorithms, the proposed DP-FCN method achieves the best performance in terms of accuracy for landslide inventory mapping. Index Terms-Natural disaster, landslide inventory map (LIM), change detection (CD), remote sensing images.

show abstract

Regional Landslide Identification Based on Susceptibility Analysis and Change Detection

Cited by 16 publications

References 46 publications

Application of an Incomplete Landslide Inventory and One Class Classifier to Earthquake-Induced Landslide Susceptibility Mapping

Application of an Incomplete Landslide Inventory and One Class Classifier to Earthquake-Induced Landslide Susceptibility Mapping

Methods of Landslide Detection using GIS and Remote Sensing Images

Landslide Inventory Mapping With Bitemporal Aerial Remote Sensing Images Based on the Dual-Path Fully Convolutional Network

Contact Info

Product

Resources

About