**4. Results**

The results of remote sensing techniques implemented in the study area are presented in this section.

### **4.1 Land surface parameters (LSP) related to landslides**

The DEMs Palsar RTC elevation data, SRTM DEM 30 m and 90 resolution, and ASTER-GDEM were evaluated in relation to GPS control points and a reference Topo DEM obtained by interpolation of contours at a scale of 1:25 K. The best in terms of vertical root-mean-square-error (RMSE) was SRTM 30 m resolution, and its accuracy at a 95% confidence level (7.8 m) corresponded to a better scale than 1:25 K. ALOSP RTC elevation data was the second best DEM. For this reason we derived from the latter the land surface parameters (LSP) at 12.5 m resolution using algorithms implemented on SAGA software. **Table 4** shows the results of a vertical accuracy assessment of the global DEMs used in this research.

The land surface parameters: slope, aspect, curvature [17], topographic wetness index (TWI) [18], valley depth (Vdepth) [18], convergence index (CONVI) [19], flow path length (FPL), and insolation [20], were converted into independent components by using Principal Component Analysis (PCA) [21]. These were used as independent variables into a landform detection model and a landslide regression model by WofE methods.

**Table 5** shows the results of WofE analysis to relate morphometric and land use conditioning factors with landslide inventory. Only the variable with its class with the most studentised contrast (bigger than 2) C/s(C) is shown. **Figure 4** shows the unit soils at a scale of 1:100 k, which covers plain, undulated and mountainous terrains.

#### **4.2 InSAR measurements**

InSAR measures are phase, coherence, and displacement and they are obtained by the cross-correlation between two or more SAR images to process the line-ofsight displacements. This research used C-band data provided by Sentinel/1 ESA's Copernicus programme. In this investigation, the effect of a DEM on the InSAR


processing was determined [22], concluding that DEM did not have an effect on InSAR coherence but if the InSAR phase is unwrapped with the DEM variable there are significance differences. The above is due to the inaccuracies of external DEM. Two landslide regression models obtained either with InSAR coherence or InSAR displacement from a DEM variable showed that SRTM DEM 30 m resolution had the highest association with landslides inventory (**Table 6**). These models had

**LSP The range of study area Class C/s(C)** Slope 0<sup>∘</sup> - 79.4<sup>∘</sup> 6.6<sup>∘</sup> to 19.9<sup>∘</sup> 2.1

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

FPL 0–2598 m 0–371 m 2

Landform 12 classes Backslopes 3.6

Soil unit 9 classes Humid hill lands (LQ) and very

*WofE studentised contrast* >1*:*5 *for LSP and land use conditioning factors.*

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

**Table 5.**

**Figure 4.**

**129**

*Soil units of the study area.*

13.2<sup>∘</sup> to 26.5<sup>∘</sup> 2.9

3.5

wet cold mountain (MK)

From the point of view of the InSAR coherence measurement, all DEMs are not statistically significant. However, Topo-map showed a weak relation to landslides.

an accuracy of 62% and 68% respectively.

**Table 4.**

*Vertical accuracy of the global DEMs compared with Topo-map DEM reference.*

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


**Table 5.**

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

The results of remote sensing techniques implemented in the study area are

The DEMs Palsar RTC elevation data, SRTM DEM 30 m and 90 resolution, and ASTER-GDEM were evaluated in relation to GPS control points and a reference Topo DEM obtained by interpolation of contours at a scale of 1:25 K. The best in terms of vertical root-mean-square-error (RMSE) was SRTM 30 m resolution, and its accuracy at a 95% confidence level (7.8 m) corresponded to a better scale than 1:25 K. ALOSP RTC elevation data was the second best DEM. For this reason we derived from the latter the land surface parameters (LSP) at 12.5 m resolution using algorithms implemented on SAGA software. **Table 4** shows the results of a vertical

The land surface parameters: slope, aspect, curvature [17], topographic wetness index (TWI) [18], valley depth (Vdepth) [18], convergence index (CONVI) [19], flow path length (FPL), and insolation [20], were converted into independent components by using Principal Component Analysis (PCA) [21]. These were used as independent variables into a landform detection model and a landslide regression

**Table 5** shows the results of WofE analysis to relate morphometric and land use conditioning factors with landslide inventory. Only the variable with its class with the most studentised contrast (bigger than 2) C/s(C) is shown. **Figure 4** shows the unit soils at a scale of 1:100 k, which covers plain, undulated and mountainous terrains.

InSAR measures are phase, coherence, and displacement and they are obtained by the cross-correlation between two or more SAR images to process the line-ofsight displacements. This research used C-band data provided by Sentinel/1 ESA's Copernicus programme. In this investigation, the effect of a DEM on the InSAR

**Metric ALOSP ASTER SRTM1 (30 m) SRTM3 (90 m)** RMSE (m) 39.68 43.52 19.95 22.77 SZ (without bias) (m) 4.427 5.331 3.937 4.595 NMAD (m) 3.806 4.663 3.093 3.883 LE95 (without bias) (m) 8.853 10.236 7.795 9.144

> 5.60 + 89.8\*tan (slp)

3.54 + 109.9\*tan (slp)

4.689 + 100\*tan (slp)

detection model generated in this research.

**4.1 Land surface parameters (LSP) related to landslides**

accuracy assessment of the global DEMs used in this research.

**4. Results**

*Slope Engineering*

presented in this section.

model by WofE methods.

**4.2 InSAR measurements**

SZ= 4.62 + 80.5\*tan

**Table 4.**

**128**

(slp)

*Vertical accuracy of the global DEMs compared with Topo-map DEM reference.*

*WofE studentised contrast* >1*:*5 *for LSP and land use conditioning factors.*

**Figure 4.** *Soil units of the study area.*

processing was determined [22], concluding that DEM did not have an effect on InSAR coherence but if the InSAR phase is unwrapped with the DEM variable there are significance differences. The above is due to the inaccuracies of external DEM.

Two landslide regression models obtained either with InSAR coherence or InSAR displacement from a DEM variable showed that SRTM DEM 30 m resolution had the highest association with landslides inventory (**Table 6**). These models had an accuracy of 62% and 68% respectively.

From the point of view of the InSAR coherence measurement, all DEMs are not statistically significant. However, Topo-map showed a weak relation to landslides.


#### **Table 6.**

*Results of InSAR regression analysis by LR method.*

Topo-map and SRTM 30 m contributed to a better explanation of the linear regression model. InSAR displacement with a DEM variable indicated that SRTM 30 m had the lowest p-value suggesting a strong association of the elevation with the probability of having a landslide with a positive coefficient. ANOVA verificated that by adding the SRTM 30 m to the regression model significantly reduces the residual deviance.

WofE analysis showed that the maximum studentised contrast for InSAR coherence was in the range of 0.43 to 0.66.

Multi-InSAR processing by PS-InSAR method allowed to estimate the deformation rate in relation to a reference point target which is assumed to be stable. This approach overloads the substantial limitation of InSAR measurements: the spatial and temporal decorrelation and atmospheric distortions due to ionospheric electron density and tropospheric water vapour.

**Figure 5.**

**Figure 6.** *BS-coefficient (σ*<sup>∘</sup>

**131**

*OK prediction of the displacement velocity in mm/year.*

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

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

*) in landslide inventory.*

The C-band sensor on-board the Sentinel-1 satellite served as input data to implement PSInSAR processing to estimate the annual linear velocities and the time series of deformations. **Table 7** indicates the geometrical characteristics of S1\_A of the ESA' Copernicus used for PS-InSAR in the study area. The perpendicular baseline in all cases was lower than 150 m, which is an adequate value for studies of terrain deformation. The results were a deformation map which consisted in a set of selected points (12 pts./km2) with both the information of the estimated LOS velocity (in the range 10 mm/year to 10 mm/year) and the accumulated displacement. Ordinary Kriging (OK) method allowed to predict the LOS velocity on landslide inventory (**Figure 5**). A terrain displacement between 4.5 mm/year and 4.8 mm/year in ascending mode, and between 2.7 mm/year and 7.7 mm/year in descending mode was predicted with the satellite LOS velocity, indicating the movement towards (positive values) and away (negative values) the sensor respect to the master radar scene. The prediction variance found was lower than 1.6 (mm/ year)<sup>2</sup> in ascending orbit, and lower than 5.63 (mm/year)<sup>2</sup> in descending pass.


**Table 7.** *Sentinel-1-IW-SLC dataset.* *The Potential of Remote Sensing to Assess Conditioning Factors for Landslide Detection… DOI: http://dx.doi.org/10.5772/intechopen.94251*

**Figure 5.** *OK prediction of the displacement velocity in mm/year.*

**Figure 6.** *BS-coefficient (σ*<sup>∘</sup> *) in landslide inventory.*

Topo-map and SRTM 30 m contributed to a better explanation of the linear regression model. InSAR displacement with a DEM variable indicated that SRTM 30 m had the lowest p-value suggesting a strong association of the elevation with the probability of having a landslide with a positive coefficient. ANOVA verificated that by adding the SRTM 30 m to the regression model significantly reduces the

**DEM InSAR coherence InSAR displacement**

SRTM DEM 30 m 2.627 0.853 0.0014\*\* 0.870 0.0003\*\*\* 1.56e-9 \*\*\* SRTM DEM 90 m 2.674 0.850 0.816 0.467 0.04\* 0.22 Palsar RTC 0.085 0.522 0.069 0.323 0.084. 0.057. Topo-map 0.474 0.004\*\* 0.0031\*\* 0.017 0.924 0.924

Intercept 9.345 < 2e-16\*\*\* 13.15 <2e-16\*\*\*

AUC 0.62 0.68

*Significance of codes: 0 = \*\*\*, 0.001 = \*\*, 0.01 = \*, 0.05 =., 0.1 = ' '.*

**Coeff. Pr( > z) Pr( > Chi) Coeff Pr( > z) Pr( > Chi)**

WofE analysis showed that the maximum studentised contrast for InSAR coher-

Multi-InSAR processing by PS-InSAR method allowed to estimate the deformation rate in relation to a reference point target which is assumed to be stable. This approach overloads the substantial limitation of InSAR measurements: the spatial and temporal decorrelation and atmospheric distortions due to ionospheric electron

The C-band sensor on-board the Sentinel-1 satellite served as input data to implement PSInSAR processing to estimate the annual linear velocities and the time series of deformations. **Table 7** indicates the geometrical characteristics of S1\_A of the ESA' Copernicus used for PS-InSAR in the study area. The perpendicular baseline in all cases was lower than 150 m, which is an adequate value for studies of terrain deformation. The results were a deformation map which consisted in a set of selected points (12 pts./km2) with both the information of the estimated LOS velocity (in the range 10 mm/year to 10 mm/year) and the accumulated displacement. Ordinary Kriging (OK) method allowed to predict the LOS velocity on landslide inventory (**Figure 5**). A terrain displacement between 4.5 mm/year and 4.8 mm/year in ascending mode, and between 2.7 mm/year and 7.7 mm/year in descending mode was predicted with the satellite LOS velocity, indicating the movement towards (positive values) and away (negative values) the sensor respect to the master radar scene. The prediction variance found was lower than 1.6 (mm/ year)<sup>2</sup> in ascending orbit, and lower than 5.63 (mm/year)<sup>2</sup> in descending pass.

**Zone Dates Stack Pass/Pol Bn(m) Bt(days) IncAnc (<sup>∘</sup>**

SE 10–2014/09–2015 and 01–2016/09–2016 24 Asc/VV 7 to 144 24–384 34.2 NW 10–2014/09–2015 and 01–2016/09–2016 21 Asc/VV 7 to 144 24–384 34.2 NE 10–2014/05–2016 21 Des/VV 2 to 117 24–312 34.1 **)**

residual deviance.

**Table 6.**

*Slope Engineering*

**Table 7.**

**130**

*Sentinel-1-IW-SLC dataset.*

ence was in the range of 0.43 to 0.66.

*Results of InSAR regression analysis by LR method.*

density and tropospheric water vapour.


**Table 8.**

*H-α decomposition of quad-pol data.*

## **4.3 PolSAR unsupervised classification**

Dual Pol-Sentinel-1 analysis allowed to analyse the sigma nought scattering coefficient with VV and VH polarisation. Copolarization backscattering (8.5 dB) was higher than cross-polarisation (14.5 dB) (**Figure 6**).

Quad Pol-UAVSAR decomposition allowed to define the mechanism of scattering on landslides inventory using entropy/alpha within the Cloude Pottier method. The scattering mechanism dominant in the study area were volume scattering (vegetation) and surface scattering (**Table 8**). The results indicate that 50% of the landslide have a scattering mechanism of volume and 25.4% of surface type. The WofE method validated that the H-*α* classification of volume and surface scattering were highly related to landslides.

#### **4.4 NDVI time series analysis**

Time series analysis of the multi-year Landsat NDVI was used as input data for the change detection analysis. In the period 2012 to 2017, the multi-year Landsat NDVI cloud-free yearly composites through Google Earth Engine did not show the statistically significant trends in vegetation. But WofE analysis found that the NDVI range with the highest association to the landslide inventory was between 0.40 and 0.72. **Figure 7** shows that only the years 2012, 2014 and 2016 covers, without clouds, the landslide inventory distribution with median values of NDVI.

#### **4.5 Model to the detection of landslides**

All of the variables generated (25) in this research by remote sensing techniques were overlapped and cut into a common sub-zone and then combined into a multidimensional image. Here are found the classification variables. Then the effect of classification variables (derived from remote sensing techniques) over a target variable (landslide inventory) was measured by the algorithm of supervised pixelbased classification called Random Forest. Test data in a proportion of 30% of the entire data set allowed to obtain an independent validation. **Table 9** show the Random Forest classification with an overall accuracy of 70.8%. The user's accuracy refers to the correct classification of the type of movement in relation to the referenced one, and the producer's accuracy refers to the commission or inclusion error. Due to the high frequency of rotational and translational slide, the method was successful, which did not happen with other less frequent types.

resulting in omissions errors of 20% and 9% for each one. User's accuracy for the same type of landslides was of 67% and 71% indicating commission errors of 33%

**Random Forest classification Topic Sw**

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

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

Training model Rotational slide 66.7%

User's accuracy Rotational slide 66.7%

Producer's accuracy Rotational slide 80%

Overall accuracy 70.8%

Translational slide 96.2%

Translational slide 71.4 \$

Translational slide 90.9%

**Figure 9** shows the Mean Decrease Accuracy implemented in Random Forest. The variables which contributed more to the study were PolSAR, the displacement

and 29%. The overall accuracy was 70.8%.

*7-year LANDSAT NDVI composites (2010 to 2017).*

**Figure 7.**

**Table 9.**

**133**

*Random Forest classification.*

InSAR, the NDVI and the morphometric variable slope.

**Figure 8** shows the results of the Random Forest classification for the landslides types: debris fall, flow, planar translational, rotational and translational. Rotational and translational slides had a producer's accuracy of 80% and 91% respectively

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

#### **Figure 7.**

**4.3 PolSAR unsupervised classification**

*H-α decomposition of quad-pol data.*

**Table 8.**

*Slope Engineering*

**132**

were highly related to landslides.

**4.4 NDVI time series analysis**

**4.5 Model to the detection of landslides**

was higher than cross-polarisation (14.5 dB) (**Figure 6**).

Dual Pol-Sentinel-1 analysis allowed to analyse the sigma nought scattering coefficient with VV and VH polarisation. Copolarization backscattering (8.5 dB)

**H-***α* **category Landslide frequency Relative frequency**

4-Medium entropy and multiple scattering 12 9.5 5-Medium entropy and volume scattering 63 50 6-Medium entropy and surface scattering 32 25.4 7-Low entropy and multiple scattering 15 11.9 8-Low entropy and volume scattering 4 3.2 Total: 126 100

Quad Pol-UAVSAR decomposition allowed to define the mechanism of scattering on landslides inventory using entropy/alpha within the Cloude Pottier method. The scattering mechanism dominant in the study area were volume scattering (vegetation) and surface scattering (**Table 8**). The results indicate that 50% of the landslide have a scattering mechanism of volume and 25.4% of surface type. The WofE method validated that the H-*α* classification of volume and surface scattering

Time series analysis of the multi-year Landsat NDVI was used as input data for the change detection analysis. In the period 2012 to 2017, the multi-year Landsat NDVI cloud-free yearly composites through Google Earth Engine did not show the statistically significant trends in vegetation. But WofE analysis found that the NDVI range with the highest association to the landslide inventory was between 0.40 and 0.72. **Figure 7** shows that only the years 2012, 2014 and 2016 covers, without clouds, the landslide inventory distribution with median values of NDVI.

All of the variables generated (25) in this research by remote sensing techniques

**Figure 8** shows the results of the Random Forest classification for the landslides types: debris fall, flow, planar translational, rotational and translational. Rotational and translational slides had a producer's accuracy of 80% and 91% respectively

were overlapped and cut into a common sub-zone and then combined into a multidimensional image. Here are found the classification variables. Then the effect of classification variables (derived from remote sensing techniques) over a target variable (landslide inventory) was measured by the algorithm of supervised pixelbased classification called Random Forest. Test data in a proportion of 30% of the entire data set allowed to obtain an independent validation. **Table 9** show the Random Forest classification with an overall accuracy of 70.8%. The user's accuracy refers to the correct classification of the type of movement in relation to the referenced one, and the producer's accuracy refers to the commission or inclusion error. Due to the high frequency of rotational and translational slide, the method

was successful, which did not happen with other less frequent types.

*7-year LANDSAT NDVI composites (2010 to 2017).*


#### **Table 9.**

*Random Forest classification.*

resulting in omissions errors of 20% and 9% for each one. User's accuracy for the same type of landslides was of 67% and 71% indicating commission errors of 33% and 29%. The overall accuracy was 70.8%.

**Figure 9** shows the Mean Decrease Accuracy implemented in Random Forest. The variables which contributed more to the study were PolSAR, the displacement InSAR, the NDVI and the morphometric variable slope.

An analysis of the effect of DEM on InSAR processing to estimate terrain deformations showed that DEM only had a significant impact on InSAR displacement but

Dual polarimetric SAR analysis found that VV-polarisation radar backscatter produces stronger scattering than cross-polarisation (VH) on landslide inventory in

C/band Sentinel-1 data allowed to measure very slow ground surface displace-

Time series analysis of Landsat NDVI composites with Google Earth Engine [28], allowed to compare measurements of inter-annual NDVI. However, this research only analysed the period 2012–2016. Thus, the lacking of long-term time series of optical satellites data did not detect trends in vegetation cover changes related to landslides. For this reason, inter-annual NDVI in the period 2012–2016

Random Forest (RF) algorithm was applied to classify landslides. Conditioning factors provided by remote sensing techniques were stored as grid cells at 30 m of spatial resolution. RF model for landslide classification needed data to train the model and validate its results. The total training dataset was split with a proportion

Using the test dataset, we found that the overall classification accuracy of the model was 70.8%. This meant that over 70.8% of the test dataset was correctly identified as either a landslide event or non-landslide event in the same sense as is reported in Taalab et al. [29]. The rank of variables importance, based on the relative contribution to the classification accuracy of the model, in order of importance, were: PolSAR, InSAR displacement, NDVI, backslope landform and InSAR

By using Remote Sensing techniques at the visible and microwave frequencies of EM waves this research did relate EO measurements with ground physical parameters such as scattering mechanisms, topography, land cover type and surface deformation patterns. All of the above in relationship with landslides inventory of the

All of the EO data collected and generated by RS techniques during this research

This research used errors' theory, ANOVA, TUKEY and cross-validation techniques to determine the internal and external precision of the method generated for

This research did implement unsupervised and supervised classification methods. The first to understand the pattern of LSI clustering and the second to classify the LSI with multidimensional variables derived from EO data and RS

not on InSAR coherence, such as also is highlighted in Bayer et al. [25].

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

ments with mm precision by PSInSAR method. However, as is indicated in Colesanti et al. [27], it is necessary to combine data from different sources, i.e.

only was taken as conditioning factor to develop of detection model.

of 70% of samples used to train models and 30% for validation.

the same way as is reported by Ningthoujam et al. [26].

GNSS data, to avoid misinterpretations.

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

coherence.

study area.

techniques.

**135**

landslides detection.

was stored in appropriate containers of data.

**6. Conclusions**

**Figure 8.** *Detection model of landslides by the Random Forest method.*

#### **Figure 9.**

*Importance of the variables in decreasing order.*

## **5. Discussion**

This study confirmed that the slope angle is a key classification factor in landslide detection in a similar way reported by Donnarumffia et al. [23]. So as land use is the most influencing factor to the occurrence of landslides [24].

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

An analysis of the effect of DEM on InSAR processing to estimate terrain deformations showed that DEM only had a significant impact on InSAR displacement but not on InSAR coherence, such as also is highlighted in Bayer et al. [25].

Dual polarimetric SAR analysis found that VV-polarisation radar backscatter produces stronger scattering than cross-polarisation (VH) on landslide inventory in the same way as is reported by Ningthoujam et al. [26].

C/band Sentinel-1 data allowed to measure very slow ground surface displacements with mm precision by PSInSAR method. However, as is indicated in Colesanti et al. [27], it is necessary to combine data from different sources, i.e. GNSS data, to avoid misinterpretations.

Time series analysis of Landsat NDVI composites with Google Earth Engine [28], allowed to compare measurements of inter-annual NDVI. However, this research only analysed the period 2012–2016. Thus, the lacking of long-term time series of optical satellites data did not detect trends in vegetation cover changes related to landslides. For this reason, inter-annual NDVI in the period 2012–2016 only was taken as conditioning factor to develop of detection model.

Random Forest (RF) algorithm was applied to classify landslides. Conditioning factors provided by remote sensing techniques were stored as grid cells at 30 m of spatial resolution. RF model for landslide classification needed data to train the model and validate its results. The total training dataset was split with a proportion of 70% of samples used to train models and 30% for validation.

Using the test dataset, we found that the overall classification accuracy of the model was 70.8%. This meant that over 70.8% of the test dataset was correctly identified as either a landslide event or non-landslide event in the same sense as is reported in Taalab et al. [29]. The rank of variables importance, based on the relative contribution to the classification accuracy of the model, in order of importance, were: PolSAR, InSAR displacement, NDVI, backslope landform and InSAR coherence.
