# Evaluation of Different Landslide Susceptibility Models for a Local Scale in the Chitral District, Northern Pakistan

^{1}

^{2}

^{3}

^{4}

^{5}

^{6}

^{*}

## Abstract

**:**

## 1. Introduction

^{2}. Moreover, the increasing anthropogenic activities, the changing global climate, and the dynamic tectonic nature of the region have been causing more landslides. All these factors make our selected case study area vulnerable to landslides. Landslide susceptibility assessment and LSM provide crucial information for hazard mitigation in this area. So far, to the best of our knowledge, no study has done landslide inventory documentation and susceptibility mapping altogether in this area. In addition, no comparison studies exist for this study area and some of the datasets used in this study have never been used before in this area. Therefore, it is essential to consider the mapping accuracies of various methods for such a sensitive area and highlight the best-performing model.

## 2. Study Area

## 3. Materials and Methods

#### 3.1. Landslide Inventory

#### 3.1.1. Pre-Processing

#### 3.1.2. Change Detection

_{1}, h

_{2}, …, h

_{n})

^{F}and G = (g

_{1}, g

_{2}, …, g

_{n})

^{F}, corresponding to two different dates (i.e., f

_{1}and f

_{2}, the reflectance values of the pixels in two images, correspondingly, where the number of bands is given by n), then the succeeding equation can be used to determine the magnitude of the change ‖Δ$\mathrm{G}$‖,

_{2}are represented by $\mathrm{G}$, whereas the three PCs of f

_{1}are represented by H. Lastly, the change map created using CVA is represented by ‖Δ$\mathrm{G}$‖. Figure 1a, and b illustrates the pre- and post-landslide imagery. Figure 1c shows the change detection results, while the identified landslide is shown in Figure 1d.

#### 3.1.3. Accuracy Assessment

#### 3.2. The Spatial Database of Conditioning Factors

#### 3.3. Evaluation of Condition Factors

#### Multicollinearity Analysis

_{j}

^{2}signifies the determination coefficient when the jth independent variable x

_{j}is regressed against all other variables in the model. The following equation gives the VIF value:

#### 3.4. Training and Validation Database

#### 3.5. Machine Learning (ML) Techniques

#### 3.5.1. Linear Regression (LR)

_{0}+ b

_{1}X

_{1}+ b

_{2}X

_{2}+ b

_{3}X

_{3}+ … + b

_{m}X

_{m}+ ℇ

#### 3.5.2. Logistic Regression (LGR)

_{0}+ b

_{1}x

_{1}+ b

_{2}x

_{2}+ … + b

_{n}x

_{n}

_{0}, and b

_{1}represents the partial regression coefficients… b

_{n}, x

_{1}… x

_{n}, which are the independent variables.

#### 3.5.3. Support Vector Machine (SVM)

#### 3.6. Multi-Criteria Decision-Making (MCDM) Techniques

#### 3.6.1. Analytical Hierarchy Process (AHP)

#### 3.6.2. The Technique for Order Preference by Similarity to Ideal Solution (TOPSIS)

#### 3.7. Landslide Susceptibility Mapping

## 4. Results

#### 4.1. Change Detection Map

#### 4.2. Correlation Analysis of the Conditioning Factors

#### 4.3. Thematic Maps of Conditioning Factors

#### 4.3.1. Land Use

#### 4.3.2. Slope

#### 4.3.3. Soil

#### 4.3.4. Lithology

#### 4.3.5. The Normalized Difference Wetness Index (NDWI)

#### 4.3.6. Normalized Difference Vegetation Index (NDVI)

#### 4.3.7. Rainfall

#### 4.3.8. Elevation

#### 4.3.9. Fault Density

#### 4.3.10. Road Density

#### 4.3.11. Earthquake Activity

#### 4.3.12. Flow Accumulation

#### 4.3.13. Profile Curvature

#### 4.3.14. Plane Curvature

#### 4.3.15. Curvature

#### 4.3.16. Aspect

#### 4.4. Conditioning Factor Analysis

#### 4.5. Landslide Susceptibility Maps (LSMs)

#### 4.6. Model Validation

## 5. Discussion

^{2}and the proportions of all the zones of the susceptibility classes are given in Table 7. The SVM and AHP models have higher area percentages in a very high susceptibility class than the other models. For SVM it is 7.53% (1091.17 km

^{2}), and for AHP it is 7.31% (1059.29 km

^{2}) of the study region that falls under the very high susceptibility class. Furthermore, AHP and TOPSIS have the most incredible area in the low susceptibility class, representing a 9.80% (1420.12 km

^{2}) and 9.18% (1330.27 km

^{2}) portion of the investigation region, respectively. However, with an area of 45.18% (6547.03 km

^{2}) and 43.37% (6284.75 km

^{2}), the LGR and LR models are the dominant ones in the intermediate susceptibility class. Thus, it can be concluded that each technique reacts differently to the conditioning factors and the research area characteristics.

## 6. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Acknowledgments

## Conflicts of Interest

## Abbreviations

LSMs | Landslide susceptibility maps |

LGR | Logistic regression |

LR | Linear regression |

AHP | Analytical hierarchy process |

AHP | Support vector machines |

AHP | Technique for order of preference by similarity to ideal solution |

ML | Machine learning |

ML | Multi-criteria decision-making |

ML | Change vector analysis |

ML | Normalized difference vegetation index |

NDWI | Normalized difference wetness index |

PMD | Pakistan meteorological department |

STRM | Shuttle Radar Topography Mission |

DEM | Digital elevation model |

GIS | Geographical information systems |

## References

- Chen, W.; Shahabi, H.; Zhang, S.; Khosravi, K.; Shirzadi, A.; Chapi, K.; Pham, B.T.; Zhang, T.; Zhang, L.; Chai, H.; et al. Landslide Susceptibility Modeling Based on GIS and Novel Bagging-Based Kernel Logistic Regression. Appl. Sci.
**2018**, 8, 2540. [Google Scholar] [CrossRef] [Green Version] - Thai, P.B.; Bui, D.T.; Dholakia, M.B.; Prakash, I.; Pham, H.V. A comparative study of least square support vector machines and multiclass alternating decision trees for spatial prediction of rainfall-induced landslides in a tropical cyclones area. Geotech. Geol. Eng.
**2016**, 34, 1807–1824. [Google Scholar] - Feizizadeh, B.; Blaschke, T. An uncertainty and sensitivity analysis approach for GIS-based multicriteria landslide susceptibility mapping. Int. J. Geogr. Inf. Sci.
**2014**, 28, 610–638. [Google Scholar] [CrossRef] [Green Version] - Solmaz, A.; Balafar, M.A.; Feizizadeh, B.; Sangar A., B.; Samadzamini, K. Using hybrid artificial intelligence approach based on a neuro-fuzzy system and evolutionary algorithms for modeling landslide susceptibility in East Azerbaijan Province, Iran. Earth Sci. Inform.
**2021**, 14, 1861–1882. [Google Scholar] - Sajid, A.; Biermanns, P.; Haider, R.; Reicherter, K. Landslide susceptibility mapping by using a geographic information system (GIS) along the China–Pakistan Economic Corridor (Karakoram Highway), Pakistan. Nat. Hazards Earth Syst. Sci.
**2019**, 19, 999–1022. [Google Scholar] - Abolfazl, J.; Panahi, M.; Mafi-Gholami, D.; Rahmati, O.; Shahabi, H.; Shirzadi, A.; Lee, S.; Bui, D.T.; Pradhan, B. Swarm intelligence optimization of the group method of data handling using the cuckoo search and whale optimization algorithms to model and predict landslides. Appl. Soft Comput.
**2022**, 116, 108254. [Google Scholar] - Saeedeh, E.; Amiri, M.; Sãdhasivam, N.; Pourghasemi, H.R. Comparison of new individual and hybrid machine learning algorithms for modeling and mapping fire hazard: A supplementary analysis of fire hazard in different counties of Golestan Province in Iran. Nat. Hazards
**2020**, 104, 305–327. [Google Scholar] - Saeedeh, E. Fire of Iranian forests, consequences, opposition methods and solutions. Hum. Environ.
**2021**, 19, 175–187. [Google Scholar] - Xiaojing, W.; Huang, F.; Fan, X.; Shahabi, H.; Shirzadi, A.; Bian, H.; Ma, X.; Lei, X.; Chen, W. Landslide susceptibility modeling based on remote sensing data and data mining techniques. Environ. Earth Sci.
**2022**, 81, 50. [Google Scholar] - Ngo, P.T.; Panahi, M.; Khosravi, K.; Ghorbanzadeh, O.; Kariminejad, N.; Cerda, A.; Lee, S. Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran. Geosci. Front.
**2021**, 12, 505–519. [Google Scholar] - Conforti, M.; Ietto, F. Modeling shallow landslide susceptibility and assessment of the relative importance of predisposing factors, through a GIS-based statistical analysis. Geosciences
**2021**, 11, 333. [Google Scholar] [CrossRef] - Reichenbach, P.; Rossi, M.; Malamud, B.D.; Mihir, M.; Guzzetti, F. A review of statisticallybased landslide susceptibility models. Earth Sci. Rev.
**2018**, 180, 60–91. [Google Scholar] [CrossRef] - Jacek, M. GIS-based land-use suitability analysis: A critical overview. Prog. Plan.
**2004**, 62, 3–65. [Google Scholar] - Omarzadeh, D.; Pourmoradian, S.; Feizizadeh, B.; Khallaghi, H.; Sharifi, A.; Kamran, K.V. A GIS-Based Multiple Ecotourism Sustainability Assessment of West Azerbaijan Province Iran. J. Environ. Plan. Manag.
**2022**, 65, 490–513. [Google Scholar] [CrossRef] - Ghorbanzadeh, O.; Pourmoradian, S.; Blaschke, T.; Feizizadeh, B. Mapping Potential Nature-Based Tourism Areas by Applying GIS-Decision Making Systems in East Azerbaijan Province. Iran. J. Ecotourism
**2019**, 18, 261–283. [Google Scholar] [CrossRef] - Neaupane, K.M.; Piantanakulchai, M. Analytic network process model for landslide hazard zonation. Eng. Geol.
**2006**, 85, 281–294. [Google Scholar] [CrossRef] - Rao, R.V.; Davim, J.P. A decision-making framework model for material selection using a combined multiple attribute decision-making method. Int. J. Adv. Manuf. Technol.
**2008**, 35, 751–760. [Google Scholar] [CrossRef] - Zare, M.; Pourghasemi, H.R.; Vafakhah, M.; Pradhan, B. Landslide susceptibility mapping at Vaz Watershed (Iran) using an artificial neural network model: A comparison between multilayer perceptron (MLP) and radial basic function (RBF) algorithms. Arab. J. Geosci.
**2013**, 6, 2873–2888. [Google Scholar] [CrossRef] - Zhang, W.; Li, H.; Han, L.; Chen, L.; Wang, L. Slope stability prediction using ensemble learning techniques: A case study in Yunyang County, Chongqing, China. J. Rock Mech. Geotech. Eng.
**2022**, in press. [Google Scholar] [CrossRef] - Zhang, W.; Zhang, R.; Wu, C.; Goh, A.T.; Wang, L. Assessment of basal heave stability for braced excavations in anisotropic clay using extreme gradient boosting and random forest regression. Undergr. Space
**2022**, 7, 233–241. [Google Scholar] [CrossRef] - Zhang, W.; Zhang, R.; Wu, C.; Goh, A.T.; Lacasse, S.; Liu, Z.; Liu, H. State-of-the-art review of soft computing applications in underground excavations. Geosci. Front.
**2020**, 11, 1095–1106. [Google Scholar] [CrossRef] - Chen, W.; Peng, J.; Hong, H.; Shahabi, H.; Pradhan, B.; Liu, J.; Zhu, A.X.; Pei, X.; Duan, Z. Landslide susceptibility modelling using GIS-based machine learning techniques for Chongren County, Jiangxi Province, China. Sci. Total Environ.
**2018**, 626, 1121–1135. [Google Scholar] [CrossRef] [PubMed] - Pourghasemi, H.R.; Gayen, A.; Park, S.; Lee, C.W.; Lee, S. Assessment of landslide-prone areas and their zonation using logistic regression, logitboost, and naïvebayes machine-learning algorithms. Sustainability
**2018**, 10, 3697. [Google Scholar] [CrossRef] [Green Version] - Raja, N.B.; Çiçek, I.; Türkoğlu, N.; Aydin, O.; Kawasaki, A. Landslide susceptibility mapping of the Sera River Basin using logistic regression model. Nat. Hazards
**2017**, 85, 1323–1346. [Google Scholar] [CrossRef] [Green Version] - Othman, A.A.; Gloaguen, R.; Andreani, L.; Rahnama, M. Improving landslide susceptibility mapping using morphometric features in the Mawat area, Kurdistan Region, NE Iraq: Comparison of different statistical models. Geomorphology
**2018**, 319, 147–160. [Google Scholar] [CrossRef] - Chen, T.; Niu, R.; Jia, X. A comparison of information value and logistic regression models in landslide susceptibility mapping by using GIS. Environ. Earth Sci.
**2016**, 75, 867. [Google Scholar] [CrossRef] - Akgün, A.; Türk, N. Mapping erosion susceptibility by a multivariate statistical method: A case study from the Ayvalık region, NW Turkey. Comput. Geosci.
**2011**, 37, 1515–1524. [Google Scholar] [CrossRef] - Guzzetti, F.; Reichenbach, P.; Ardizzone, F.; Cardinali, M.; Galli, M. Estimating the quality of landslide susceptibility models. Geomorphology
**2006**, 81, 166–184. [Google Scholar] [CrossRef] - Rahmati, O.; Pourghasemi, H.R. Identification of critical flood prone areas in data-scarce and ungauged regions: A comparison of three data mining models. Water Resour. Manag.
**2017**, 31, 1473–1487. [Google Scholar] [CrossRef] - Tien Bui, D.; Tuan, T.A.; Klempe, H.; Pradhan, B.; Revhaug, I. Spatial prediction models for shallow landslide hazards: A comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree. Landslides
**2016**, 13, 361–378. [Google Scholar] [CrossRef] - Bai, S.; Lü, G.; Wang, J.; Zhou, P.; Ding, L. GIS-based rare events logistic regression for landslide-susceptibility mapping of Lianyungang, China. Environ. Earth Sci.
**2011**, 62, 139–149. [Google Scholar] [CrossRef] - Domínguez-Cuesta, M.J.; Jiménez-Sánchez, M.; Berrezueta, E. Landslides in the Central Coalfield (Cantabrian Mountains, NW Spain): Geomorphological features, conditioning factors and methodological implications in susceptibility assessment. Geomorphology
**2007**, 89, 358–369. [Google Scholar] [CrossRef] - Pradhan, B.; Youssef, A.; Varathrajoo, R. Approaches for delineating landslide hazard areas using different training sites in an advanced artificial neural network model. Geo-Spat. Inf. Sci.
**2010**, 13, 93–102. [Google Scholar] [CrossRef] [Green Version] - Peng, L.; Niu, R.; Huang, B.; Wu, X.; Zhao, Y.; Ye, R. Landslide susceptibility mapping based on rough set theory and support vector machines: A case of the Three Gorges area, China. Geomorphology
**2014**, 214, 287–301. [Google Scholar] [CrossRef] - Aghdam, I.N.; Varzandeh, M.N.H.; Pradhan, B. Landslide susceptibility mapping using an ensemble statistical index (Wi) and adaptive neuro-fuzzy inference system (ANFIS) model at Alborz Mountains (Iran). Environ. Earth Sci.
**2016**, 75, 553. [Google Scholar] [CrossRef] - Chen, W.; Pourghasemi, H.R.; Kornejady, A.; Zhang, N. Landslide spatial modeling: Introducing new ensembles of ANN, MaxEnt, and SVM machine learning techniques. Geoderma
**2017**, 305, 314–327. [Google Scholar] [CrossRef] - Dehnavi, A.; Aghdam, I.N.; Pradhan, B.; Varzandeh, M.H. A new hybrid model using step-wise weight assessment ratio analysis (SWARA) technique and adaptive neuro-fuzzy inference system (ANFIS) for regional landslide hazard assessment in Iran. Catena
**2015**, 135, 122–148. [Google Scholar] [CrossRef] - Kanungo, D.P.; Arora, M.K.; Sarkar, S.; Gupta, R.P. A comparative study of conventional, ANN black box, fuzzy and combined neural and fuzzy weighting procedures for landslide susceptibility zonation in Darjeeling Himalayas. Eng. Geol.
**2006**, 85, 347–366. [Google Scholar] [CrossRef] - Ghorbanzadeh, O.; Blaschke, T.; Aryal, J.; Gholaminia, K. A new GIS-based technique using an adaptive neuro-fuzzy inference system for land subsidence susceptibility mapping. J. Spat. Sci.
**2020**, 65, 401–418. [Google Scholar] [CrossRef] [Green Version] - Aslam, B.; Zafar, A.; Khalil, U. Correction to: Development of integrated deep learning and machine learning algorithm for the assessment of landslide hazard potential. Soft Comput.
**2021**, 25, 13795. [Google Scholar] [CrossRef] - Khosravi, K.; Panahi, M.; Golkarian, A.; Keesstra, S.D.; Saco, P.M.; Bui, D.T.; Lee, S. Convolutional neural network approach for spatial prediction of flood hazard at national scale of Iran. J. Hydrol.
**2020**, 591, 125552. [Google Scholar] [CrossRef] - Omarzadeh, D.; Karimzadeh, S.; Matsuoka, M.; Feizizadeh, B. Earthquake Aftermath from Very High-Resolution WorldView-2 Image and Semi-Automated Object-Based Image Analysis (Case Study: Kermanshah, Sarpol-e Zahab, Iran). Remote Sens.
**2021**, 13, 4272. [Google Scholar] [CrossRef] - Ghorbanzadeh, O.; Blaschke, T.; Gholamnia, K.; Meena, S.R.; Tiede, D.; Aryal, J. Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection. Remote Sens.
**2019**, 11, 196. [Google Scholar] [CrossRef] [Green Version] - Kolb, H. Abflußverhalten von Flüssen in den Hochgebirgen Nordpakistans. Physisch-geographische Beiträge zu den Hochgebirgsräumen Nordpakistans und der Alpen. Beitr. U. Mat. Z. Reg. Geogr
**1994**, 7, 21–114. [Google Scholar] - Huserodt, K. Change of climate in the Hindu Kush region-facts, trends, and necessary observations of the environment. In Proceedings of the Third International Hindu Kush Cultural Conference; Oxford University Press: Oxford, UK, 2008. [Google Scholar]
- Kamp, U., Jr.; Haserodt, K.; Shroder, J.F., Jr. Quaternary landscape evolution in the eastern Hindu Kush, Pakistan. Geomorphology
**2004**, 57, 1–27. [Google Scholar] [CrossRef] - Roohi, R.; Ashraf, R.; Naz, R.; Hussain, S.A.; Chaudhry, M.H. Inventory of Glaciers and Glacial Lakes Outburst Floods (GLOFs) Affected by Global Warming in the Mountains of Himalayan Region, Indus Basin, Pakistan Himalaya; ICIMOD: Kathmandu, Nepal, 2005. [Google Scholar]
- Asif Khan, M.; Haneef, M.; Khan, A.S.; Tahirkheli, T. Debris-flow hazards on tributary junction fans, Chitral, Hindu Kush Range, northern Pakistan. J. Asian Earth Sci.
**2013**, 62, 720–733. [Google Scholar] [CrossRef] - Hafeez, S.; Waqas, A.; Azam, S.; Khan, S. Evaluation of landslide hazards at Herth, Chitral, Pakistan. Innov. Infrastruct. Solut.
**2019**, 4, 13. [Google Scholar] [CrossRef] - Aslam, B.; Khalil, U.; Saleem, M.; Maqsoom, A.; Khan, E. Effect of multiple climate change scenarios and predicted land-cover on soil erosion: A way forward for the better land management. Environ. Monit. Assess.
**2021**, 193, 754. [Google Scholar] [CrossRef] - Hotelling, H. Analysis of a complex of statistical variables into principal components. J. Educ. Psychol.
**1933**, 24, 417. [Google Scholar] [CrossRef] - Ramos-Bernal, R.N.; Vázquez-Jiménez, R.; Romero-Calcerrada, R.; Arrogante-Funes, P.; Novillo, C.J. Evaluation of unsupervised change detection methods applied to landslide inventory mapping using ASTER imagery. Remote Sens.
**2018**, 10, 1987. [Google Scholar] [CrossRef] [Green Version] - Ferrero, S.; Palacio, M.; Campanella, O.R. Análisis de componentes principales en teledetección. Consideraciones estadísticas para optimizar su interpretación. Rev. Teledetección
**2002**, 17, 43. [Google Scholar] - Lorena, R.B.; Santos, J.D.; Shimabukuro, Y.E.; Brown, I.F.; Kux, H.J. A change vector analysis technique to monitor land use/land cover in sw Brazilian amazon: Acre state. PECORA 15-Integr. Remote Sens. Glob. Reg. Local Scale
**2002**, 8–15. [Google Scholar] - Roemer, H.; Kaiser, G.; Sterr, H.; Ludwig, R. Using remote sensing to assess tsunami-induced impacts on coastal forest ecosystems at the Andaman Sea coast of Thailand. Nat. Hazards Earth Syst. Sci.
**2010**, 10, 729–745. [Google Scholar] [CrossRef] - Lüdeke, M.K.; Ramage, P.H.; Kohlmaier, G. The use of satellite NDVI data for the validation of global vegetation phenology models: Application to the Frankfurt Biosphere Model. Ecol. Model.
**1996**, 91, 255–270. [Google Scholar] [CrossRef] - Malila, W.A. Change vector analysis: An approach for detecting forest changes with Landsat. In LARS Symposia; Purdue University Libraries: West Lafayette, IN, USA, 1980. [Google Scholar]
- Chen, J.; Gong, P.; He, C.; Pu, R.; Shi, P. Land-use/land-cover change detection using improved change-vector analysis. Photogramm. Eng. Remote Sens.
**2003**, 69, 369–379. [Google Scholar] [CrossRef] [Green Version] - Cohen, J. A coefficient of agreement for nominal scales. Educ. Psychol. Meas.
**1960**, 20, 37–46. [Google Scholar] [CrossRef] - Vázquez-Jiménez, R.; Ramos-Bernal, R.N.; Romero-Calcerrada, R.; Arrogante-Funes, P.; Tizapa, S.S.; Novillo, C.J. Thresholding algorithm optimization for change detection to satellite imagery. In Color. Image Process; Travieso-Gonzalez, C., Ed.; InTech: London, UK, 2018; pp. 163–182. [Google Scholar] [CrossRef] [Green Version]
- Nasir, S.M.; Kamran, K.V.; Blaschke, T.; Karimzadeh, S. Change of Land Use/Land Cover in Kurdistan Region of Iraq: A Semi-Automated Object-Based Approach. Remote Sens. Appl. Soc. Environ.
**2022**, 26, 100713. [Google Scholar] [CrossRef] - Yang, Z.; Qiao, J.; Uchimura, T.; Wang, L.; Lei, X.; Huang, D. Unsaturated hydro-mechanical behaviour of rainfall-induced mass remobilization in post-earthquake landslides. Eng. Geol.
**2017**, 222, 102–110. [Google Scholar] [CrossRef] - Tsangaratos, P.; Ilia, I.; Hong, H.; Chen, W.; Xu, C. Applying Information Theory and GIS-based quantitative methods to produce landslide susceptibility maps in Nancheng County, China. Landslides
**2017**, 14, 1091–1111. [Google Scholar] [CrossRef] - Youssef, A.M.; Pourghasemi, H.R.; El-Haddad, B.A.; Dhahry, B.K. Landslide susceptibility maps using different probabilistic and bivariate statistical models and comparison of their performance at Wadi Itwad Basin, Asir Region, Saudi Arabia. Bull. Eng. Geol. Environ.
**2016**, 75, 63–87. [Google Scholar] [CrossRef] - Hong, H.S.A.; Naghibi, H.R.; Pradhan, P.B. GIS-based landslide spatial modeling in Ganzhou City, China. Arab J. Geosci.
**2016**, 9, 112. [Google Scholar] [CrossRef] - Chen, W.; Zhang, S.; Li, R.; Shahabi, H. Performance evaluation of the GIS-based data mining techniques of best-first decision tree, random forest, and naïve Bayes tree for landslide susceptibility modeling. Sci. Total Environ.
**2018**, 644, 1006–1018. [Google Scholar] [CrossRef] [PubMed] - O’brien, R.M. A caution regarding rules of thumb for variance inflation factors. Qual. Quant.
**2007**, 41, 673–690. [Google Scholar] [CrossRef] - Colkesen, I.; Sahin, E.K.; Kavzoglu, T. Susceptibility mapping of shallow landslides using kernel-based Gaussian process, support vector machines and logistic regression. J. Afr. Earth Sci.
**2016**, 118, 53–64. [Google Scholar] [CrossRef] - Wang, L.; Wu, C.; Tang, L.; Zhang, W.; Lacasse, S.; Liu, H.; Gao, L. Efficient reliability analysis of earth dam slope stability using extreme gradient boosting method. Acta Geotech.
**2020**, 15, 3135–3150. [Google Scholar] [CrossRef] - Zhang, W.; Wu, C.; Zhong, H.; Li, Y.; Wang, L. Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization. Geosci. Front.
**2021**, 12, 469–477. [Google Scholar] [CrossRef] - Irigaray, C.; Fernández, T.; El Hamdouni, R.; Chacón, J. Evaluation and validation of landslide-susceptibility maps obtained by a GIS matrix method: Examples from the Betic Cordillera (southern Spain). Nat. Hazards
**2007**, 41, 61–79. [Google Scholar] [CrossRef] - Lee, S.; Sambath, T. Landslide susceptibility mapping in the Damrei Romel area, Cambodia using frequency ratio and logistic regression models. Environ. Geol.
**2006**, 50, 847–855. [Google Scholar] [CrossRef] - Yesilnacar, E.; Topal, T. Landslide susceptibility mapping: A comparison of logistic regression and neural networks methods in a medium scale study, Hendek region (Turkey). Eng. Geol.
**2005**, 79, 251–266. [Google Scholar] [CrossRef] - Vapnik, V. The support vector method of function estimation. In Nonlinear Modeling; Springer: Berlin/Heidelberg, Germany, 1998; pp. 55–85. [Google Scholar]
- Cortes, C.; Vapnik, V. Support-vector networks. Mach. Learn.
**1995**, 20, 273–297. [Google Scholar] [CrossRef] - Brenning, A. Spatial prediction models for landslide hazards: Review, comparison and evaluation. Nat. Hazards Earth Syst. Sci.
**2005**, 5, 853–862. [Google Scholar] [CrossRef] - Kavzoglu, T.; Sahin, E.K.; Colkesen, I. Landslide susceptibility mapping using GIS-based multi-criteria decision analysis, support vector machines, and logistic regression. Landslides
**2014**, 11, 425–439. [Google Scholar] [CrossRef] - Mountrakis, G.; Im, J.; Ogole, C. Support vector machines in remote sensing: A review. ISPRS J. Photogramm. Remote Sens.
**2011**, 66, 247–259. [Google Scholar] [CrossRef] - Saaty, T. The Analytic Hierarchy Process; Mcgraw Hill: New York, NY, USA, 1980; p. 324. [Google Scholar]
- Saaty, T.L.; Vargas, L.G. How to make a decision. In Models, Methods, Concepts & Applications of the Analytic Hierarchy Process; Springer: Berlin/Heidelberg, Germany, 2001; pp. 1–25. [Google Scholar]
- Ching, L.H.; Yoon, P. Multiple Attribute Decision Making. In Lecture Notes in Economics and Mathematical Systems; Springer: Berlin/Heidelberg, Germany, 1981. [Google Scholar]
- Ameri, A.A.; Pourghasemi, H.R.; Cerda, A. Erodibility prioritization of sub-watersheds using morphometric parameters analysis and its mapping: A comparison among TOPSIS, VIKOR, SAW, and CF multi-criteria decision making models. Sci. Total Environ.
**2018**, 613, 1385–1400. [Google Scholar] [CrossRef] [PubMed] - Opricovic, S.; Tzeng, G.-H. Compromise solution by MCDM methods: A comparative analysis of VIKOR and TOPSIS. Eur. J. Oper. Res.
**2004**, 156, 445–455. [Google Scholar] [CrossRef] - Basharat, M.; Shah, H.R.; Hameed, N. Landslide susceptibility mapping using GIS and weighted overlay method: A case study from NW Himalayas, Pakistan. Arab. J. Geosci.
**2016**, 9, 292. [Google Scholar] [CrossRef] - Shit, P.K.; Bhunia, G.S.; Maiti, R. Potential landslide susceptibility mapping using weighted overlay model (WOM). Modeling Earth Syst. Environ.
**2016**, 2, 21. [Google Scholar] [CrossRef] [Green Version] - Bachri, S.; Shresta, R.P. Landslide hazard assessment using analytic hierarchy processing (AHP) and geographic information system in Kaligesing mountain area of Central Java Province Indonesia. Annu. Int. Work. Expo Sumatra Tsunami
**2010**, 9, 108–112. [Google Scholar] - Intarawichian, N.; Dasananda, S. Analytical Hierarchy Process for landslide suscpetibility mapping in lower Mae Chaem watershed, northern Thiland. Suranaree J. Sci. Technol.
**2010**, 17, 277–292. [Google Scholar] - Maqsoom, A.; Aslam, B.; Khalil, U.; Kazmi, Z.A.; Azam, S.; Mehmood, T.; Nawaz, A. Landslide susceptibility mapping along the China Pakistan Economic Corridor (CPEC) route using multi-criteria decision-making method. Modeling Earth Syst. Environ.
**2021**, 7, 1–15. [Google Scholar] [CrossRef] - Rahim, I.; Ali, S.M.; Aslam, M. GIS Based landslide susceptibility mapping with application of analytical hierarchy process in District Ghizer, Gilgit Baltistan Pakistan. J. Geosci. Environ. Prot.
**2018**, 6, 34–49. [Google Scholar] [CrossRef] [Green Version] - Ballabio, C.; Sterlacchini, S. Support vector machines for landslide susceptibility mapping: The Staffora River Basin case study, Italy. Math. Geosci.
**2012**, 44, 47–70. [Google Scholar] [CrossRef] - Chen, W.; Pourghasemi, H.R.; Naghibi, S.A. Prioritization of landslide conditioning factors and its spatial modeling in Shangnan County, China using GIS-based data mining algorithms. Bull. Eng. Geol. Environ.
**2018**, 77, 611–629. [Google Scholar] [CrossRef]

**Figure 1.**Pre-landslide imagery before a historical event, (

**a**); post-landslide imagery, (

**b**); image classification, (

**c**); landslide identification (illustrated with red polygon), (

**d**); the study area for the landslide susceptibility mapping with past landslide locations, (

**e**); Pakistan with the highlighted part representing the KPK district, (

**f**); districts of Pakistan with the highlighted part signifying the Chitral district, (

**g**).

**Figure 3.**Maps of landslide conditioning factors: land use (

**a**), slope (

**b**), soil (

**c**), lithology (

**d**), NDWI (

**e**), NDVI (

**f**), rainfall (

**g**), elevation (

**h**), fault density (

**i**), road density (

**j**), earthquake activity (

**k**), flow accumulation (

**l**), profile curvature (

**m**), plane curvature (

**n**), curvature (

**o**), and aspect (

**p**).

Change Detection Method | Image Input | Threshold Method | Threshold Value | Change Ratio (%) |
---|---|---|---|---|

CVA | PC | Statistic | >59.326 | 1.538 |

CVA | PC | Secant | >29.761 | 8.237 |

Change Detection Method | Image Input | Threshold Method | Change Ratio (%) | Mean Omission Error | Mean Commission Error | Kappa Coefficient of Agreement |
---|---|---|---|---|---|---|

CVA | PC | Statistic | 0.43 | 22.45 | 15.34 | 63.453 |

CVA | PC | Secant | 2.73 | 13.43 | 11.03 | 78.483 |

Factor | TOL | VIF |
---|---|---|

Aspect | 0.174 | 5.74 |

Curvature | 0.611 | 1.64 |

Earthquake activity | 0.567 | 1.76 |

Elevation | 0.460 | 2.17 |

Flow accumulation | 0.511 | 1.96 |

Lithology | 0.463 | 2.16 |

NDVI | 0.380 | 2.63 |

NDWI | 0.480 | 2.09 |

Plane Curvature | 0.134 | 7.44 |

Precipitation | 0.585 | 1.71 |

Profile Curvature | 0.108 | 9.23 |

Slope | 0.216 | 4.64 |

Faults | 0.244 | 4.09 |

Roads | 0.407 | 2.46 |

Soil | 0.273 | 3.66 |

Land use | 0.309 | 3.24 |

Dataset | SVM | LGR | LR | AHP | TOPSIS |
---|---|---|---|---|---|

Aspect | 4 | 3 | 5 | 7 | 3 |

Curvature | 7 | 9 | 8 | 4 | 7 |

Earthquake activity | 3 | 4 | 3 | 5 | 6 |

Elevation | 9 | 8 | 9 | 6 | 8 |

Flow accumulation | 9 | 8 | 10 | 7 | 9 |

Lithology | 7 | 6 | 6 | 8 | 6 |

NDVI | 4 | 7 | 5 | 6 | 8 |

NDWI | 7 | 9 | 10 | 9 | 6 |

Plane Curvature | 3 | 7 | 6 | 5 | 4 |

Precipitation | 11 | 9 | 7 | 10 | 13 |

Profile Curvature | 3 | 2 | 2 | 1 | 2 |

Slope | 10 | 9 | 8 | 11 | 7 |

Faults | 7 | 3 | 4 | 4 | 3 |

Roads | 3 | 3 | 3 | 3 | 3 |

Soil | 6 | 5 | 7 | 6 | 6 |

Land use | 7 | 8 | 7 | 8 | 9 |

Total | 100 | 100 | 100 | 100 | 100 |

Confusion matrix for the LGR model | ||

0 | 1 | |

0 | 431 | 61 |

1 | 75 | 445 |

Confusion matrix for the LR model | ||

0 | 1 | |

0 | 385 | 85 |

1 | 121 | 421 |

Confusion matrix for the SVM model | ||

0 | 1 | |

0 | 395 | 111 |

1 | 66 | 440 |

Model Type | Validation |
---|---|

LGR | 82% |

LR | 76% |

SVM | 85% |

Models | Area | Susceptibility Class | ||||
---|---|---|---|---|---|---|

Very Low | Low | Moderate | High | Very High | ||

LGR | km^{2} | 678.18 | 3406.8 | 6284.75 | 3211.2 | 910.03 |

% | 4.68 | 23.51 | 43.37 | 22.16 | 6.28 | |

LR | km^{2} | 375.32 | 2517.1 | 6547.03 | 4271.9 | 779.62 |

% | 2.59 | 17.37 | 45.18 | 29.48 | 5.38 | |

SVM | km^{2} | 246.35 | 1904.1 | 6136.94 | 5112.4 | 1091.17 |

% | 1.70 | 13.14 | 42.35 | 35.28 | 7.53 | |

AHP | km^{2} | 1420.12 | 3787.9 | 5306.6 | 2917 | 1059.29 |

% | 9.80 | 26.14 | 36.62 | 20.13 | 7.31 | |

TOPSIS | km^{2} | 1330.27 | 4553.1 | 5087.79 | 2772.1 | 747.74 |

% | 9.18 | 31.42 | 35.11 | 19.13 | 5.16 |

Models | Accuracy |
---|---|

LGR | 78% |

LR | 84% |

SVM | 88% |

AHP | 81% |

TOPSIS | 79% |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Aslam, B.; Maqsoom, A.; Khalil, U.; Ghorbanzadeh, O.; Blaschke, T.; Farooq, D.; Tufail, R.F.; Suhail, S.A.; Ghamisi, P.
Evaluation of Different Landslide Susceptibility Models for a Local Scale in the Chitral District, Northern Pakistan. *Sensors* **2022**, *22*, 3107.
https://doi.org/10.3390/s22093107

**AMA Style**

Aslam B, Maqsoom A, Khalil U, Ghorbanzadeh O, Blaschke T, Farooq D, Tufail RF, Suhail SA, Ghamisi P.
Evaluation of Different Landslide Susceptibility Models for a Local Scale in the Chitral District, Northern Pakistan. *Sensors*. 2022; 22(9):3107.
https://doi.org/10.3390/s22093107

**Chicago/Turabian Style**

Aslam, Bilal, Ahsen Maqsoom, Umer Khalil, Omid Ghorbanzadeh, Thomas Blaschke, Danish Farooq, Rana Faisal Tufail, Salman Ali Suhail, and Pedram Ghamisi.
2022. "Evaluation of Different Landslide Susceptibility Models for a Local Scale in the Chitral District, Northern Pakistan" *Sensors* 22, no. 9: 3107.
https://doi.org/10.3390/s22093107