Landslide mapping from multi-sensor data through improved change detection-based Markov random field

Ping Lu,Yuanyuan Qin,Zhongbin Li,Alessandro C Mondini,Nicola Casagli

doi:10.1016/j.rse.2019.111235

Abstract

Accurate landslide inventory mapping is essential for quantitative hazard and risk assessment. Although multi-temporal change detection techniques have contributed greatly to landslide inventory preparation, it is still challenging to generate quality change detection images (CDIs) for accurate landslide mapping. The recently proposed change detection-based Markov random field (CDMRF) provides an effective approach for rapid mapping of landslides with minimum user interventions. However, when CDI is generated by change vector analysis (CVA) alone, the CDMRF method may suffer from noise especially when the pre- and post-event remote sensing images are acquired under different atmospheric, illumination, and phenological conditions. This paper improved such CDMRF approach by integrating normalized difference vegetation index (NDVI), principal component analysis (PCA), and independent component analysis (ICA) generated CDIs with MRF for landslide inventory mapping from multi-sensor data. To justify the effectiveness and applicability, the improved methods were applied to map rainfall-, typhoon-, and earthquake-triggered landslides from the pre- and post-event satellite images acquired by very high resolution QuickBird, high resolution FORMOSAT-2, and moderate resolution Sentinel-2. Moreover, they were tested on pre-event Landsat-8 and post-event Sentinel-2 datasets, indicating that they are operational for landslide inventory mapping from combined multi-temporal and multi-sensor data. The results demonstrate that the improved δNDVI-, PCA-, and ICA-based approaches perform much better than CVA-based CDMRF in terms of completeness, correctness, Kappa coefficient, and F-measures. To the best of our knowledge, it is the first time that NDVI, PCA, and ICA are integrated with MRF for landslide inventory mapping from multi-sensor data. It is anticipated that this research can be a starting point for developing new change detection techniques that can readily generate quality CDI and for applying advanced machine learning algorithms (e.g., deep learning) to automatic detection of natural hazards from multi-sensor time series data.

Highlights

Landslides are one of the major types of natural hazards worldwide (Nadim et al, 2006; Kjekstad and Highland, 2009; Petley, 2012; Guzzetti et al, 2012; Froude and Petley, 2018), resulting in major loss of life and damage to infrastructures
The results demonstrate that the improved δNDVI, principal component analysis (PCA), and independent component analysis (ICA)-based approaches perform much better than change vector analysis (CVA)-based change detection-based Markov random field (CDMRF) in terms of completeness, correctness, Kappa coefficient, and F-measures
To the best of our knowledge, it is the first time that normalized difference vegetation index (NDVI), PCA, and ICA are integrated with MRF for landslide inventory mapping from multi-sensor data

Summary

Introduction

Landslides are one of the major types of natural hazards worldwide (Nadim et al, 2006; Kjekstad and Highland, 2009; Petley, 2012; Guzzetti et al, 2012; Froude and Petley, 2018), resulting in major loss of life and damage to infrastructures. Traditional landslide inventory mapping approaches rely on 3D visual interpretation of aerial photos or satellite images in addition to intensive field surveys (Guzzetti et al, 2000, 2012; Brardinoni et al, 2003; Malamud et al, 2004; Sato et al, 2007; Galli et al, 2008; Saba et al, 2010; Gorum et al, 2011; Ghosh et al, 2012; Xu et al, 2014, 2015; Murillo-García et al, 2015; Duric et al, 2017; Fan et al, 2018) Such approaches are time-consuming and tedious for landslide mapping over large areas. This research gap is being filled by introducing new remote sensing technologies (Metternicht et al, 2005; Guzzetti et al, 2012; Scaioni et al, 2014)

Results

Discussion

Conclusion