# Landslide Susceptibility Assessment at Mila Basin (Algeria): A Comparative Assessment of Prediction Capability of Advanced Machine Learning Methods

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Study Area and Data

#### 2.1. Description of the Study Area

^{2}distributed mostly over the central parts of the Mila and Constantine provinces. Geographically, the study area is fully surrounded by mountainous ranges that belong to different paleogeographic domains and make up the basin substratum, such as M’Cid Aicha and Sidi Driss from the North; Djebel Ossmane and Grouz by the South; Djebel Akhal, Chettaba and Kheneg from the East; and Djebel Boucherf and Oukissene by the West (Figure 1). The elevation of the basin varies from 60 m to 1550 m.

#### 2.2. Data Used

#### 2.2.1. Landslide Inventory Map

^{®}software. 47 landslide polygons were detected and mapped (from 2000 to 2017). On the other hand, the non-landslide samples were extracted by random sampling a unique 578 sample site (equal to the total number of landslide samples) from public stability maps available at DUC (Direction d’Urbanisme et Construction) using PAW (Plan d’Amenagement de Wilya) and PDAU (Plan Directeur d’Amenagement et d’Urbanisme). Extensive field inspections and Google Earth Pro software were performed to verify the landslide and non-landslide samples (Figure 3).

^{3}to 620,000 m

^{3}. According to the survey campaigns achieved by local authorities (2003–2017), the slopes in the study area fail under the conjunction of both predisposition factors (i.e., geology, lithology geomorphology, and faults) and triggering factors (i.e., intense and persistent meteorological events, human activities, and so forth), resulting in landslides of different sizes and types. Reports suggest that the long and persistent periods of intense to moderate rainfall are the main culprit in triggering and/or reactivating existent deep-seated landslides due to the high amount of water infiltrating underground. On the contrary, short and intense to moderate rainstorms/precipitations indirectly affect slope stability by intensive erosive processes [19,22].

#### 2.2.2. Landslide Conditioning Factors

^{2}/m) and $\beta $ is the local slope in degree.

## 3. Methods

#### 3.1. Random Forest

#### 3.2. Gradient Boosting Machine

#### 3.3. Logistic Regression

#### 3.4. Artificial Neural Network

#### 3.5. Support Vector Machine

## 4. Used Methodology

#### 4.1. Construction of the Geospatial Database, the Training Dataset, and the Validation Dataset

#### 4.2. Analyzing and Optimizing Landslide Conditioning Factor

#### 4.3. Model Configuration and Implementation

#### 4.4. Model Training, Validation, and Comparison

#### 4.5. Landslide Susceptibility Map Generation and Assessment

## 5. Results

#### 5.1. Analyzing and Optimizing Landslide Conditioning Factor

#### 5.2. Model Training

- Set a single objective function for each learner using “smoof” [54] with AUC to maximize it as a single performance criterion.
- During every single iteration, a new point is being proposed through LCB infill optimization of the estimated standard error. This error is usually obtained by a surrogate model that is either kriging-based for a purely numeric space or random forest for a mixed search space.
- Select and return the optimum values of the desired hyperparameters based on the highest AUC (Table 7).

#### 5.3. Model Evaluation and Comparison

#### 5.4. Generating Landslide Susceptibility Map

## 6. Discussions

## 7. Conclusions

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Pham, B.T.; Pradhan, B.; Tien Bui, D.; Prakash, I.; Dholakia, M.B. A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of uttarakhand area (India). Environ. Model. Softw.
**2016**, 84, 240–250. [Google Scholar] [CrossRef] - Tien Bui, D.; Pradhan, B.; Lofman, O.; Revhaug, I.; Dick, O.B. Landslide susceptibility assessment in the hoa binh province of vietnam: A comparison of the levenberg–marquardt and bayesian regularized neural networks. Geomorphology
**2012**, 171–172, 12–29. [Google Scholar] [CrossRef] - Chen, W.; Xie, X.; Wang, J.; Pradhan, B.; Hong, H.; Bui, D.T.; Duan, Z.; Ma, J. A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility. Catena
**2017**, 151, 147–160. [Google Scholar] [CrossRef] - Guzzetti, F.; Carrara, A.; Cardinali, M.; Reichenbach, P. Landslide hazard evaluation: A review of current techniques and their application in a multi-scale study, Central Italy. Geomorphology
**1999**, 31, 181–216. [Google Scholar] [CrossRef] - Lary, D.J.; Alavi, A.H.; Gandomi, A.H.; Walker, A.L. Machine learning in geosciences and remote sensing. Geosci. Front.
**2016**, 7, 3–10. [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] - Dou, J.; Yamagishi, H.; Pourghasemi, H.R.; Yunus, A.P.; Song, X.; Xu, Y.; Zhu, Z. An integrated artificial neural network model for the landslide susceptibility assessment of osado island, Japan. Nat. Hazards
**2015**, 78, 1749–1776. [Google Scholar] [CrossRef] - Goetz, J.N.; Brenning, A.; Petschko, H.; Leopold, P. Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling. Comput. Geosci.
**2015**, 81, 1–11. [Google Scholar] [CrossRef] - Tien Bui, D.; Tuan, T.A.; Hoang, N.-D.; Thanh, N.Q.; Nguyen, D.B.; Van Liem, N.; Pradhan, B. Spatial prediction of rainfall-induced landslides for the lao cai area (Vietnam) using a hybrid intelligent approach of least squares support vector machines inference model and artificial bee colony optimization. Landslides
**2017**, 14, 447–458. [Google Scholar] [CrossRef] - Dou, J.; Paudel, U.; Oguchi, T.; Uchiyama, S.; Hayakawa, Y. Shallow and deep-seated landslide differentiation using support vector machines: A case study of the chuetsu area, Japan. Terr. Atmos. Ocean. Sci.
**2015**, 26, 13. [Google Scholar] [CrossRef] - Youssef, A.M.; Pourghasemi, H.R.; Pourtaghi, Z.S.; Al-Katheeri, M.M. Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at wadi tayyah basin, asir region, Saudi Arabia. Landslides
**2015**, 13, 839–856. [Google Scholar] [CrossRef] - Lombardo, L.; Cama, M.; Conoscenti, C.; Märker, M.; Rotigliano, E. Binary logistic regression versus stochastic gradient boosted decision trees in assessing landslide susceptibility for multiple-occurring landslide events: Application to the 2009 storm event in messina (Sicily, Southern Italy). Nat. Hazards
**2015**, 79, 1621–1648. [Google Scholar] [CrossRef] - Carrara, A.; Pike, R.J. Gis technology and models for assessing landslide hazard and risk. Geomorphology
**2008**, 94, 257–260. [Google Scholar] [CrossRef] - Wolpert, D.H. The lack of a priori distinctions between learning algorithms. Neural Comput.
**1996**, 8, 1341–1390. [Google Scholar] [CrossRef] - Elith, J.; Leathwick, J.R. Species distribution models: Ecological explanation and prediction across space and time. Ann. Rev. Ecol. Evol. Syst.
**2009**, 40, 677–697. [Google Scholar] [CrossRef] - Tsangaratos, P.; Ilia, I. Comparison of a logistic regression and naïve bayes classifier in landslide susceptibility assessments: The influence of models complexity and training dataset size. Catena
**2016**, 145, 164–179. [Google Scholar] [CrossRef] - Mebarki, A. Le Bassin du Kébir-Rhumel: Hydrologie de Surface et Aménagement des Ressources en eau: Travaux du Laboratoire de Géographie Physique; Éditeur Inconnu: Nancy, France, 1982; p. 304. [Google Scholar]
- Rullan-Perchirin, F. Recherches sur L’érosion dans Quelques Bassins du Constantinois (Algérie). Ph.D. Thesis, Université Panthéon-Sorbonne, Paris, France, 1985. [Google Scholar]
- Chettah, W. Investigation des Propriétés Minéralogiques et Géomécaniques des Terrains en Mouvement Dans la Ville de Mila «Nord-Est d’Algérie». Ph.D. Thesis, Université Hadj Lakhdar, Batna, Algeria, 2009. [Google Scholar]
- Guzzetti, F.; Mondini, A.C.; Cardinali, M.; Fiorucci, F.; Santangelo, M.; Chang, K.-T. Landslide inventory maps: New tools for an old problem. Earth Sci. Rev.
**2012**, 112, 42–66. [Google Scholar] [CrossRef] - Yalcin, A. Gis-based landslide susceptibility mapping using analytical hierarchy process and bivariate statistics in ardesen (Turkey): Comparisons of results and confirmations. Catena
**2008**, 72, 1–12. [Google Scholar] [CrossRef] - Zouaoui, S. Etude Géologique et Géotechnique des Glissements de Terrains Dans le Bassin Néogéne de Mila: Glissement de Sibari. Ph.D. Thesis, Université Hadj Lakhdar, Batna, Algeria, 2008. [Google Scholar]
- Ayalew, L.; Yamagishi, H.; Marui, H.; Kanno, T. Landslides in sado island of Japan: Part II. Gis-based susceptibility mapping with comparisons of results from two methods and verifications. Eng. Geol.
**2005**, 81, 432–445. [Google Scholar] [CrossRef] - Van Westen, C.J.; Castellanos, E.; Kuriakose, S.L. Spatial data for landslide susceptibility, hazard, and vulnerability assessment: An overview. Eng. Geol.
**2008**, 102, 112–131. [Google Scholar] [CrossRef] - Conforti, M.; Pascale, S.; Robustelli, G.; Sdao, F. Evaluation of prediction capability of the artificial neural networks for mapping landslide susceptibility in the turbolo river catchment (Northern Calabria, Italy). CATENA
**2014**, 113, 236–250. [Google Scholar] [CrossRef] - Iwahashi, J.; Pike, R.J. Automated classifications of topography from dems by an unsupervised nested-means algorithm and a three-part geometric signature. Geomorphology
**2007**, 86, 409–440. [Google Scholar] [CrossRef] - Beven, K.J.; Kirkby, M.J. A physically based, variable contributing area model of basin hydrology/un modèle à base physique de zone d’appel variable de l’hydrologie du bassin versant. Hydrol. Scie. Bull.
**1979**, 24, 43–69. [Google Scholar] [CrossRef] - Breiman, L. Random forests. Mach. Learn.
**2001**, 45, 5–32. [Google Scholar] [CrossRef] - Natekin, A.; Knoll, A. Gradient boosting machines, a tutorial. Front. Neurorobot.
**2013**, 7. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Mason, L.; Baxter, J.; Bartlett, P.; Frean, M. Boosting Algorithms as Gradient Descent in Function Space; Australian National University: Canberra, Australia, 1999. [Google Scholar]
- Nelder, J.A.; Baker, R.J. Generalized Linear Models; John Wiley & Sons, Inc.: Hoboken, NJ, USA, 2004. [Google Scholar]
- Paola, J.D.; Schowengerdt, R.A. A review and analysis of backpropagation neural networks for classification of remotely-sensed multi-spectral imagery. Int. J. Remote Sens.
**1995**, 16, 3033–3058. [Google Scholar] [CrossRef] - Ripley, B.D. Pattern Recognition and Neural Networks; Cambridge University Press: Cambridge, UK, 2007; p. 403. [Google Scholar]
- Cristianini, N.; Schölkopf, B. Support Vector Machines and kerNel Methods: The New Generation of Learning Machines. Artif. Intell. Mag.
**2002**, 23, 3. [Google Scholar] [CrossRef] - Yao, X.; Dai, F.C. Support Vector Machine Modeling of Landslide Susceptibility Using a Gis: A Case Study; The Geological Society: London, UK, 2006. [Google Scholar]
- Guo, Q.; Kelly, M.; Graham, C.H. Support vector machines for predicting distribution of sudden oak death in california. Ecol. Model.
**2005**, 182, 75–90. [Google Scholar] [CrossRef] - Molinaro, A.M.; Simon, R.; Pfeiffer, R.M. Prediction error estimation: A comparison of resampling methods. Bioinformatics
**2005**, 21, 3301–3307. [Google Scholar] [CrossRef] [PubMed] - Dormann, C.F.; Elith, J.; Bacher, S.; Buchmann, C.; Carl, G.; Carré, G.; Marquéz, J.R.G.; Gruber, B.; Lafourcade, B.; Leitão, P.J.; et al. Collinearity: A review of methods to deal with it and a simulation study evaluating their performance. Ecography
**2012**, 36, 27–46. [Google Scholar] [CrossRef] - Booth, G.D.; Niccolucci, M.J.; Schuster, E.G. Identifying Proxy Sets in Multiple Linear Regression: An Aid to Better Coefficient Interpretation; Research paper INT (USA); U.S. Department of Agriculture, Forest Service, Rocky Mountain Research Station: Ogden, UT, USA, 1994.
- Bergstra, J.; Yamins, D.; Cox, D.D. Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. In JMLR Workshop and Conference Proceedings, Proceedings of the 30th International Conference on Machine Learning, Atlanta, GA, USA, 16–21 June 2013; Sanjoy, D., David, M., Eds.; PMLR: Atlanta, GA, USA, 2013; Volume 28, pp. 115–123. [Google Scholar]
- Thornton, C.; Hutter, F.; Hoos, H.H.; Leyton-Brown, K. Auto-Weka: Combined Selection and Hyperparameter Optimization of Classification Algorithms; ACM Press: New York, NY, USA, 2013. [Google Scholar]
- López-Ibáñez, M.; Dubois-Lacoste, J.; Pérez Cáceres, L.; Birattari, M.; Stützle, T. The irace package: Iterated racing for automatic algorithm configuration. Oper. Res. Perspect.
**2016**, 3, 43–58. [Google Scholar] [CrossRef] - Bischl, B.; Richter, J.; Bossek, J.; Horn, D.; Thomas, J.; Lang, M. Mlrmbo: A modular framework for model-based optimization of expensive black-box functions. arXiv, 2017; arXiv:1703.03373. [Google Scholar]
- Bischl, B.; Lang, M.; Kotthoff, L.; Schiffner, J.; Richter, J.; Studerus, E.; Casalicchio, G.; Jones, Z.M. Mlr: Machine learning in R. J. Mach. Learn. Res.
**2016**, 17, 1–5. [Google Scholar] - Kertész, C. Rigidity-based surface recognition for a domestic legged robot. IEEE Robot. Autom. Lett.
**2016**, 1, 309–315. [Google Scholar] [CrossRef] - Kavzoĝlu, T. An Investigation of the Design and Use of Feed-Forward Artificial Neural Networks in the Classification of Remotely Sensed Images. Ph.D. Thesis, University of Nottingham, Nottingham, UK, 2001. [Google Scholar]
- Hecht, N. IEEE First Annual International Conference on Neural Networks San Diego, California June 21–24, 1987. IEEE Expert
**1987**, 2, 14. [Google Scholar] - Ripley, B.D. Statistical Aspects of Neural Networks; Springer: Boston, MA, USA, 1993; pp. 40–123. [Google Scholar]
- Wang, C. A Theory of Generalization in Learning Machines with Neural Network Applications; University of Pennsylvania: Philadelphia, PA, USA, 1994. [Google Scholar]
- Aldrich, C.; Van Deventer, J.S.J.; Reuter, M.A. The application of neural nets in the metallurgical industry. Miner. Eng.
**1994**, 7, 793–809. [Google Scholar] [CrossRef] - Kaastra, I.; Boyd, M. Designing a neural network for forecasting financial and economic time series. Neurocomputing
**1996**, 10, 215–236. [Google Scholar] [CrossRef] [Green Version] - Landis, J.R.; Koch, G.G. The measurement of observer agreement for categorical data. Biometrics
**1977**, 33, 159–174. [Google Scholar] [CrossRef] [PubMed] - Kennedy, P. A Guide to Econometrics, 5th ed.; The MIT Press: Cambridge, MA, USA, 2003; p. 500. [Google Scholar]
- Bossek, J. Smoof: Single- and multi-objective optimization test functions. R J.
**2017**, 9. [Google Scholar] - Carnell, R. Lhs: Latin Hypercube Samples; R Package Version 0.14 ed.; R Project: Vienna, Austria, 2016. [Google Scholar]
- Stocki, R. A method to improve design reliability using optimal latin hypercube sampling. Comput. Assist. Mech. Eng. Sci.
**2005**, 12, 393. [Google Scholar] - Klimeš, J.; Stemberk, J.; Blahut, J.; Krejčí, V.; Krejčí, O.; Hartvich, F.; Kycl, P. Challenges for landslide hazard and risk management in ‘low-risk’regions, Czech Republic—Landslide occurrences and related costs (ipl project No. 197). Landslides
**2017**, 14, 771–780. [Google Scholar] [CrossRef] - Pham, B.T.; Tien Bui, D.; Prakash, I. Bagging based support vector machines for spatial prediction of landslides. Environ. Earth Sci.
**2018**, 77, 146. [Google Scholar] [CrossRef] - Dang, V.-H.; Dieu, T.B.; Tran, X.-L.; Hoang, N.-D. Enhancing the accuracy of rainfall-induced landslide prediction along mountain roads with a GIS-based random forest classifier. Bull. Eng. Geol. Environ.
**2018**, 76, 1–15. [Google Scholar] [CrossRef] - Chen, W.; Xie, X.; Peng, J.; Shahabi, H.; Hong, H.; Bui, D.T.; Duan, Z.; Li, S.; Zhu, A.X. Gis-based landslide susceptibility evaluation using a novel hybrid integration approach of bivariate statistical based random forest method. CATENA
**2018**, 164, 135–149. [Google Scholar] [CrossRef] - Hong, H.; Liu, J.; Bui, D.T.; Pradhan, B.; Acharya, T.D.; Pham, B.T.; Zhu, A.X.; Chen, W.; Ahmad, B.B. Landslide susceptibility mapping using j48 decision tree with adaboost, bagging and rotation forest ensembles in the guangchang area (China). CATENA
**2018**, 163, 399–413. [Google Scholar] [CrossRef] - Conoscenti, C.; Ciaccio, M.; Caraballo-Arias, N.A.; Gómez-Gutiérrez, Á.; Rotigliano, E.; Agnesi, V. Assessment of susceptibility to earth-flow landslide using logistic regression and multivariate adaptive regression splines: A case of the belice river basin (Western Sicily, Italy). Geomorphology
**2015**, 242, 49–64. [Google Scholar] [CrossRef] - Dai, Q.; Ye, R.; Liu, Z. Considering diversity and accuracy simultaneously for ensemble pruning. Appl. Soft Comput.
**2017**, 58, 75–91. [Google Scholar] [CrossRef] - Brillante, L.; Gaiotti, F.; Lovat, L.; Vincenzi, S.; Giacosa, S.; Torchio, F.; Segade, S.R.; Rolle, L.; Tomasi, D. Investigating the use of gradient boosting machine, random forest and their ensemble to predict skin flavonoid content from berry physical-mechanical characteristics in wine grapes. Comput. Electron. Agric.
**2015**, 117, 186–193. [Google Scholar] [CrossRef] - Caruana, R.; Karampatziakis, N.; Yessenalina, A. An empirical evaluation of supervised learning in high dimensions. In Proceedings of the 25th International Conference on Machine Learning, Helsinki, Finland, 5–9 July 2008; pp. 96–103. [Google Scholar]
- Vorpahl, P.; Elsenbeer, H.; Märker, M.; Schröder, B. How can statistical models help to determine driving factors of landslides? Ecol. Model.
**2012**, 239, 27–39. [Google Scholar] [CrossRef]

**Figure 3.**Landslide examples (Source: Mila and Constantine municipalities, Location: see Figure 1): (

**a**) RN 79a, (Type: Deep-Rotational landslide; Date: October 2011); (

**b**) Sibari (Type: Shallow-Planar landslide; Date: February 2008); (

**c**) Mila (Type: Deep-Rotational landslide; Date: September 2013); (

**d**) Grarem (Type: Planar landslide; Date: June 2015); (

**e,f**) Mila (Type: Deep-Rotational landslide; Date: October 2017); (

**g**,

**h**) Didouche Mourad (Type: Deep-Rotational landslide; Date Left: August 2003, Date Right: September 2005).

**Figure 4.**The landslide conditioning factors maps: (

**A**) altitude, (

**B**) slope, (

**C**) aspect, (

**D**) Topographic Wetness Index (TWI), (

**E**) landforms, (

**F**) rainfall, (

**G**) lithology, (

**H**) stratigraphy, (

**I**) soil type, (

**J**) soil texture, (

**K**) land use, (

**L**) depth to bedrock, (

**M**) bulk density, (

**N**) distance to faults, (

**O**) distance to hydrographic network, and (

**P**) distance to road networks.

**Figure 5.**The overall concept of the used methodology for this research: (

**A**) construct a spatial database that will serve as an input dataset for the study from the landslide inventory map and the landslide conditioning factors; (

**B**) Analyzing and optimizing the landslide conditioning factor based on the Pearson correlation and Variance Inflation Factors analysis (VIF) results; (

**C**) Model configuration and implementation using the desired hyperparameters optimization strategy; (

**D**) Model training, validation, and comparison using 5-times-repeated 10 k-folds cross-validations (CV) and the selected performance indicator metrics; (

**E**) susceptibility maps generation and evaluation based on the appropriate assessment strategy.

**Figure 10.**The generated landslide susceptibility maps using: (

**A**) GBM, (

**B**) RF, (

**C**) NNET (

**D**) SVM; and (

**E**) LR.

**Figure 11.**The sufficiency analysis of the susceptibility maps: (

**A**) Landslide density distribution by susceptibility zones; (

**B**) the total area extent covered by susceptibility zones.

Unit | Period | Epoch | Description |
---|---|---|---|

Post-nappes | Quaternary | Alluvium, colluvium, scree, detritus deposits and slopes formations like terraces | |

Neogene | Predominantly detritus composed of clay, marl, limestone, conglomerates, sandstone, sand, lacustral limestone and evaporitic formations | ||

Substratum | Paleogene | Eocene | Limestone, cherty limestone, and platted marls |

Paleocene | Opaque to somber marls | ||

Cretaceous | Upper and Mid-Upper Cretaceous | Marl dominance (variation are ranging from different horizons of gray marly limestone, alternating marl, and limestone, blueish marl, massive bars of limestone, to alternating marl, cherty limestone, and thin micritic limestone all surmounted by grey marls with conglomerate interbeds) | |

Lower Cretaceous | Mainly marly limestone and neritic limestone | ||

Jurassic | Mostly thick carbonate formations (dolostone, limestone, and cherty limestone) | ||

Triassic | Evaporitic and clayey deposits |

**Table 2.**The spatial relationship between the landslide conditioning factors and landslides by frequency ratio.

Conditioning Factors | Class | Class Percentage (%) | Landslide Percentage (%) |
---|---|---|---|

Altitude (m) | 60–326.047 | 8.786 | 19.550 |

326.047–597.105 | 36.055 | 48.789 | |

597.105–813.952 | 28.967 | 18.512 | |

813.952–1003.694 | 18.637 | 7.785 | |

1003.694–1722 | 7.555 | 5.363 | |

Slopes (°) | 0–5.543 | 26.667 | 21.107 |

5.543–11.394 | 39.877 | 37.889 | |

11.394–18.16987664 | 23.325 | 28.374 | |

18.169–27.101 | 8.299 | 10.900 | |

27.101–78.530 | 1.831 | 1.730 | |

Aspects | Flat | 0.757 | 1.038 |

1st Quadrant (0° to 90°) | 23.709 | 26.298 | |

2nd Quadrant (90° to 180°) | 28.195 | 25.260 | |

3rd Quadrant (180° to 270°) | 22.593 | 21.453 | |

4th Quadrant (270° to 360°) | 24.746 | 25.952 | |

Topographic Wetness Index (TWI) | 0.034–3.550 | 8.521 | 3.979 |

3.550–5.481 | 50.807 | 21.280 | |

5.481–8.997 | 31.076 | 67.647 | |

8.997–15.402 | 9.597 | 7.093 | |

Landforms | Steep slope, fine texture, high convexity | 6.920 | 2.422 |

Steep slope, coarse texture, high convexity | 25.290 | 32.007 | |

Steep slope, fine texture, low convexity | 41.067 | 40.830 | |

Steep slope, coarse texture, low convexity | 26.723 | 24.740 | |

Gentle slope, fine texture, high convexity | 22.043 | 19.031 | |

Gentle slope, coarse texture, high convexity | 33.809 | 34.429 | |

Gentle slope, fine texture, low convexity | 39.618 | 42.907 | |

Gentle slope, coarse texture, low convexity | 4.460 | 3.633 | |

Rainfall (mm/Year) | 403–593.263 | 0.070 | 0.000 |

593.263–711.030 | 3.353 | 5.190 | |

711.030–901.294 | 50.109 | 48.097 | |

901.294–1208.684 | 44.909 | 45.156 | |

Lithology | Alluvium | 1.629 | 1.557 |

Claystone | 13.055 | 16.090 | |

Colluvium-Detritus Deposits-Scree | 16.184 | 16.263 | |

Limestone | 5.846 | 6.920 | |

Marl | 10.668 | 13.668 | |

Neogene Complex | 3.173 | 4.152 | |

Sandstone | 24.293 | 11.592 | |

Stratigraphy | Quaternary | 2.225 | 1.730 |

Neogene | 24.557 | 29.585 | |

Paleogene | 30.166 | 22.318 | |

Upper Cretaceous | 61.891 | 61.246 | |

Upper-Mid Cretaceous | 7.943 | 16.436 | |

Lower Cretaceous | 10.793 | 18.858 | |

Triassic-Jurassic | 34.420 | 21.626 | |

Soil type | Calcisols | 25.679 | 27.163 |

Cambisols | 17.017 | 26.125 | |

Luvisols | 12.090 | 6.228 | |

Leptosols | 25.701 | 40.311 | |

Podzols | 30.189 | 28.893 | |

Regosols | 32.091 | 24.740 | |

Vertisols | 12.019 | 6.055 | |

Soil Texture (Texture) | Clay | 5.331 | 7.439 |

Sandy Clay | 4.057 | 2.941 | |

Clay Loam | 9.438 | 7.612 | |

Silty Clay Loam | 8.220 | 7.612 | |

Sandy Clay Loam | 9.545 | 7.785 | |

Landuse | Water Bodies | 56.050 | 59.862 |

Artificial Surfaces | 7.359 | 6.747 | |

Forests | 19.011 | 25.433 | |

Grasslands | 1.692 | 1.384 | |

CropLand | 59.084 | 60.035 | |

Bareland | 0.796 | 1.730 | |

Depth to Bedrock (cm) (DepthBR) | 49–574.750 | 19.417 | 11.419 |

574.7502397–761.629 | 9.797 | 1.211 | |

761.6293378–1287.379 | 15.499 | 19.723 | |

1287.379578–2766.481 | 50.172 | 58.651 | |

2766.481936–7479 | 13.075 | 8.997 | |

Bulk Density (Kg/m^{3}) (Bdensity) | 1209–1394.941 | 5.218 | 5.882 |

1394.941–1463.333 | 3.775 | 2.249 | |

1463.333–1521.039 | 2.464 | 3.287 | |

1521.039–1754 | 1.472 | 3.979 | |

Distance to Faults (m) (FDist) | 0–581 | 13.958 | 17.993 |

581–4784.550 | 7.565 | 6.920 | |

4784.550–8192 | 4.753 | 6.228 | |

Distance to Hydrographic Network (m) (WDist) | 0–300 | 26.129 | 23.702 |

300–750 | 46.124 | 41.176 | |

750–1500 | 10.521 | 14.014 | |

1500–3000 | 56.840 | 61.419 | |

3000–5856 | 12.376 | 6.401 | |

Distance to Roads networks (m) (RDist) | 0–908.103 | 7.572 | 4.498 |

908.103–2612.509 | 8.614 | 9.862 | |

2612.509–5811.481 | 2.624 | 2.768 | |

5811.481–11957 | 1.453 | 1.038 |

Model | Package | Parameter | Definition | Value |
---|---|---|---|---|

GBM | “Generalized Boosted Regression Models” Formerly: “gbm” package, | distribution | The loss function | Bernoulli |

Shrinkage | Learning rate | From 0 to 1 | ||

bag.fraction | The fraction of the training set observations randomly selected to propose the next tree | 0.5 (default) | ||

train.fraction | Observations fraction that is used to fit the GBM | 1 (default) | ||

n.trees | Total number of trees | From 2^{5} to 2^{10} | ||

interaction.depth | Maximum depth of variable interactions | From 1 to 8 | ||

n.minobsinnode | Minimum number of observations in the trees terminal nodes | 20 (default) | ||

LR | “stats” package, | link | Model link function | logit |

NNET | “Feed-Forward Neural Networks and Multinomial Log-Linear” Formerly: “nnet” package, | Maxit | Maximum number of iterations | 150 (default) |

MaxNWts | The maximum allowable number of weights | 10,000 (default) | ||

Rang | Initial random weights on [-rang, rang] | 0.5 (default) | ||

Hess | Find the Hessian of the measure of fit at the best set of weights | TRUE (default) | ||

Size | Number of units in the hidden layer | From 4 to 33 | ||

Decay | Penalty term or weight decay | From 0 to 1 | ||

RF | “A Fast Implementation of Random Forests ranger” Formerly: “ranger” package, | Replace | Sample with replacement | FALSE or TRUE |

respect.unordered.factors | Handling of unordered factor covariates | TRUE (default) | ||

sample.fraction | The fraction of observations to sample | From 0.632 to 1 | ||

num.trees | Number of trees | From 2^{5} to 2^{10} | ||

mtry | Number of variables | From 2 to 8 | ||

SVM | “Misc Functions of the Department of Statistics, Probability Theory Group, TU Wien” Formerly: “E1071” package, | kernel | kernel function | radial or polynomial |

Cost | regularization cost | From 2^{−15} to 2^{15} (default) | ||

gamma (if kernel =: “radial”) | kernel width | From 2^{−15} to 2^{15} (default) | ||

degree (if kernel =: “polynomial”) | Polynomial degree | From 1 to 16 (default) |

**Table 4.**The heuristics proposed by the package instructions to set the optimum number of variables for GBM and RF. (${N}_{i}$: the total number of variables (i.e., 16 in this research)).

Package | Suggested Value | |
---|---|---|

mtry | interaction.depth | |

gbm | N.A | $\sqrt{{N}_{i}}$, but often the search space is set between 1 and $\sqrt{{N}_{i}}$ |

ranger | $\sqrt{{N}_{i}}$ = 4 | N.A |

xgboost | 6 | 6 |

H_{2}O | 2 to 8 | 2 to 8 |

randomForest | $\sqrt{{N}_{i}}$ = 4 | N.A |

**Table 5.**The heuristics proposed to compute the optimum number of hidden layer nodes for NNET (modified from and Kavzoĝlu [46]; ${N}_{i}$: number of input nodes (i.e., the total number of variables of 16 in this study); ${N}_{o}$: number of output nodes ;${N}_{p}$: Number of training samples; $k$: the noise factor (varies between 4 and 10) is an index number representing the percentage of false measurements in the data or degree of error).

Proposed by | Heuristic | Hidden Nodes |
---|---|---|

Hecht [47] | $2{N}_{i}+1$ | 33 |

Ripley [48] | $({N}_{i}+{N}_{o})/2$ | 8 or 9 |

Paola and Schowengerdt [32] | $\frac{2+({N}_{i}\ast {N}_{o})+\frac{1}{2}{N}_{o}\left({N}_{i}{}^{2}+{N}_{i}\right)-3}{{N}_{i}+{N}_{o}}$ | 9 |

Wang [49] | $2\ast {N}_{i}/3$ | 11 |

Aldrich, et al. [50] | $\frac{{N}_{p}}{k({N}_{i}+{N}_{o})}\left(k=10\right)$ | 7 |

Aldrich, Van Deventer and Reuter [50] | $\frac{{N}_{p}}{k({N}_{i}+{N}_{o})}\left(k=7\right)$ | 10 |

Kaastra and Boyd [51] | $\sqrt{{N}_{i}\ast {N}_{o}}$ | 4 |

$2{N}_{i}$ | 32 |

Susceptibility Class | Very Low | Low | Moderate | High | Very High |
---|---|---|---|---|---|

Probability Range | From 0 to 0.05 | From 0.05 to 0.30 | From 0.30 to 0.60 | From 0.60 to 0.75 | From 0.75 to 1 |

Model | Hyperparameter | Optimal Value |
---|---|---|

GBM | Shrinkage | 0.020 |

n.trees | 570 | |

interaction.depth | 8 | |

NNET | Size | 29 |

Decay | 0.809 | |

RF | Replace | FALSE |

sample.fraction | 0.953 | |

num.trees | 1012 | |

mtry | 5 | |

SVM | kernel | radial |

cost | 2^{8.382} | |

gamma | 2^{−8.398} | |

degree | N/A |

Metrics | Model | ||||
---|---|---|---|---|---|

GBM | LR | NNET | RF | SVM | |

Acc | 0.820 | 0.780 | 0.809 | 0.817 | 0.802 |

Kappa Index | 0.640 | 0.560 | 0.619 | 0.635 | 0.605 |

**Table 9.**The pairwise comparison of the five landslide susceptibility models using the Wilcoxon signed-rank test.

No. | Pairwise Comparison | z Value | p Value | Significance |
---|---|---|---|---|

1 | GBM vs. RF | −0.579 | 0.562 | No |

2 | GBM vs. LR | 6.111 | 0.000 | Yes |

3 | GBM vs. NNET | 3.606 | 0.001 | Yes |

4 | GBM vs. SVM | 5.266 | 0.000 | Yes |

5 | RF vs. LR | 6.149 | 0.000 | Yes |

6 | RF vs. NNET | 2.905 | 0.004 | Yes |

7 | RF vs. SVM | 4.025 | 0.000 | Yes |

8 | SVM vs.LR | 5.589 | 0.000 | Yes |

9 | SVM vs. NNET | −3.223 | 0.001 | Yes |

10 | NNET vs. LR | 5.995 | 0.000 | Yes |

© 2018 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 (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Merghadi, A.; Abderrahmane, B.; Tien Bui, D.
Landslide Susceptibility Assessment at Mila Basin (Algeria): A Comparative Assessment of Prediction Capability of Advanced Machine Learning Methods. *ISPRS Int. J. Geo-Inf.* **2018**, *7*, 268.
https://doi.org/10.3390/ijgi7070268

**AMA Style**

Merghadi A, Abderrahmane B, Tien Bui D.
Landslide Susceptibility Assessment at Mila Basin (Algeria): A Comparative Assessment of Prediction Capability of Advanced Machine Learning Methods. *ISPRS International Journal of Geo-Information*. 2018; 7(7):268.
https://doi.org/10.3390/ijgi7070268

**Chicago/Turabian Style**

Merghadi, Abdelaziz, Boumezbeur Abderrahmane, and Dieu Tien Bui.
2018. "Landslide Susceptibility Assessment at Mila Basin (Algeria): A Comparative Assessment of Prediction Capability of Advanced Machine Learning Methods" *ISPRS International Journal of Geo-Information* 7, no. 7: 268.
https://doi.org/10.3390/ijgi7070268