**3. Methodology**

The main remote sensing techniques over Earth Observation data to extract features and conditioning factors related to landslides are listed in **Table 3**.

**Figure 2** shows the functional representation of the EO data indicating the entire flow processing needed to develop the detection model from multi-dimensional

**Figure 2.**

**Figure 3.**

**127**

*Functional data for model building.*

*Chain of processing to landslide detection model.*

Multidimensional data fusion

*ESA's PolSARpro-v5.0 software. <sup>5</sup>*

*Arc-SDM tool [14].*

*R software [15].*

**Table 3.**

*DEMANAL package of BLUH software [13].*

*Retrieved from https://earthexplorer.google.org.*

*SarProZ software retrieved from www.sarproz.com.*

*Retrieved from https://step.esa.int/main/download/snap-download/.*

*DOI: http://dx.doi.org/10.5772/intechopen.94251*

*Methods and approaches of remote sensing techniques used in this research.*

*1*

*2*

*3*

*4*

*6*

*7*

**Approach Variable or method Software Software type**

*The Potential of Remote Sensing to Assess Conditioning Factors for Landslide Detection…*

Random Forest supervised method QGIS/ArcCatalog/R

software<sup>7</sup>

Open-source and commercial


*The Potential of Remote Sensing to Assess Conditioning Factors for Landslide Detection… DOI: http://dx.doi.org/10.5772/intechopen.94251*


**Table 3.**

geomorphologic and catalogue type. The former contained more precise information in its thematic attributes. The overall distribution of SIMMA landslide inventory was 77.4% of slide type, 16.5% of fall type, and 6.1% of flow and creep type for a total of 230 registered events (**Table 1**). The spatial information contained only

**Table 2** summarise the EO data used in this research. EO data corresponds to DEMs, optical remote sensing and radar remote sensing. DEMs provided from SRTM DEM 30 m resolution and Palsar RTC elevation data at 12.5 m. Radar data had as source the spaceborne-based ESA-Copernicus Sentinel-1 satellites and the aerialbased UAVSAR platform. Optical data was provided by time series analysis of the multi-year Landsat 5, Landsat 7, and Landsat 8 NDVI surface reflectance images.

DEM SRTM/NASA<sup>1</sup> C/X 30 — 225 DEM AP-RTC/JAXA<sup>2</sup> L 12.5 46 70 Dual-pol (VV/VH) Sentinel-1/ESA<sup>3</sup> C 15 24 250 Quad-pol UAVSAR/NASA-JPL<sup>4</sup> L 7 365 days 16 Optical Landsat 8 SR/NASA<sup>5</sup> 30 16 days 185

**(m)**

**Cycle (days)** **Wide swath (km)**

The main remote sensing techniques over Earth Observation data to extract features and conditioning factors related to landslides are listed in **Table 3**.

**Approach Variable or method Software Software type**

Binary model WofE analysis and Logistic regression ArcSDM<sup>6</sup> Open-source

Morphometry Land surface parameters Demanal/SAGA/R/

InSAR measurements (coherence and

displacement)

Multi-InSAR Deformation velocities of persistent scatterers

Aerial-based PolSAR Surface, volume, and double-bounce scattering mechanism

**Figure 2** shows the functional representation of the EO data indicating the entire flow processing needed to develop the detection model from multi-dimensional

ArcSDM<sup>1</sup>

NDVI vegetation indices Google Earth Engine<sup>5</sup> Open-source

SNAP toolbox/ SARProZ<sup>2</sup>

SARProZ<sup>3</sup> Commercial

PolSARpro\_v5.0<sup>4</sup> Open-source

Open-source

Open-source and Commercial

allowed mapping in a shapefile of point type.

**Data Platform or mission Band Resolution**

*Retrieved from http://srtm.csi.cgiar.org/ and https://earthexplorer.usgs.gov.*

*Copernicus Sentinel data 2014. Retrieved from ASF DAAC 29 April 2017, processed by ESA.*

*UAVSARdatacourtesyNASA/JPL-Caltech, retrieved from https://uavsar.jpl.nasa.gov/cgi-bin/data.pl.*

*Retrieved from https://www.asf.alaska.edu/doi/105067/z97hfcnkr6va/.*

*Retrieved from https://search.earthdata.nasa.gov.*

*Earth observation data used in this research.*

**2.3 Earth observation data**

*Slope Engineering*

**3. Methodology**

Spaceborne-based InSAR

Optical remote sensing

**126**

*1*

*2*

*3*

*4*

*5*

**Table 2.**

*Methods and approaches of remote sensing techniques used in this research.*

#### **Figure 2.** *Functional data for model building.*

**Figure 3.** *Chain of processing to landslide detection model.*

data, data training and test of landslides. Also, the scheme shown in the **Figure 3** indicates the fusion of all geospatial information by the Random Forest method.

The CGS-SIMMA landslide inventory was split into training and test subset in a proportion of 70:30 in concordance with the study made by Huang and Zhao [16] in order to determine the accuracy of each remote sensing method applied and the detection model generated in this research.
