# Application of a GIS-Based Slope Unit Method for Landslide Susceptibility Mapping in Helong City: Comparative Assessment of ICM, AHP, and RF Model

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Study Area

^{2}(Figure 1). The maximum elevation of the study area is 1679 m, and the minimum elevation is 250 m. The maximum elevation difference is 1479 m. The terrain decreases in elevation gradually from southwest to northeast. The mountainous area is 4681 km

^{2}, accounting for 92.7% of the total area. The southern part of the study area is the Chinese and Korean quasi-platform. The northern part is the Jihei fold system in the Tianshan-Xingan geosyncline fold area, which is bounded by the deep and large fault of the Gudong River. As can be seen in Figure 1, the modified Mercalli index ranges from VI to VII, but no earthquake-induced landslides were found in the study area. There are three major rivers in the study area: The Tumen River, the Hailan River, and the Gudong River. A field investigation revealed that landslides have been mainly distributed along the rivers, which means that the rivers have a significant impact on landslide susceptibility. According to a geological map at a 1:250,000 scale (Figure 1c), the strata of the study area mainly include the Quaternary strata (Q), Neogene strata (N), Cretaceous strata (K), Jurassic strata (J), and Triassic strata (T). Lithology is primarily gravel soil, basalt, sandstone, andesite, marble, etc., and there are several deep and major faults in the study area.

## 3. Methodology

#### 3.1. The Mapping Unit

^{2}, and the minimum unit area is 0.11 km

^{2}. More than 55% of the total units’ area are between 0.30 and 1.00 km

^{2}. The unit shape is between a triangle and a square. Elongated units are rarely present. The slope angle standard deviation of more than 90% of the total units is less than 9°, and the slope aspect standard deviation of more than 50% of the total slope units is less than 70°.

#### 3.2. Landslide Inventory

- (a)
- Data collection: The existing data are the basis of this landslide investigation. Before remote sensing interpretation and field investigation, a large number of data of the study area, including formation conditions and inducing factors of geological disasters, the current situation and prevention of geological disasters, 1:50,000 topographic maps, 1:10,000 topographic maps, 1:250,000 geological maps, and satellite and aerial remote sensing information, were collected.
- (b)
- Remote sensing interpretation: Before the field investigation, the remote sensing interpretation of landslides was carried out according to the topographic features of the landslide [40].
- (c)
- Field investigation: Through field investigation, landslides interpreted through remote sensing were confirmed, and landslides not detected through remote sensing were added.
- (d)
- Production of the landslide inventory map: Based on GIS (Geographic Information System), the landslide inventory map was produced.

#### 3.3. Influencing Factors

#### 3.4. Multicollinearity Analysis of the Influencing Factors

_{i}is the negative correlation coefficient of the regression analysis of the independent variable X

_{i}on the other independent variables. The VIF value is greater than 1. The closer the VIF value is to 1, the weaker the multicollinearity. In this study, we calculated the VIF value for each influencing factor. If the VIF value is greater than 10, then the influencing factor should be excluded from the landslide susceptibility model.

#### 3.5. Landslide Susceptibility Modeling

#### 3.5.1. Information Content Model (ICM)

_{i}, D) is information content value; A is the total number of the landslides in the study area; A

_{i}is the number of landslides for influencing factor X

_{i}; B is the total number of pixels for the study area; and B

_{i}is the number of pixels for influencing factor X

_{i}. Then, the information content value is used to reclassify the influencing factor maps. Finally, the landslide susceptibility index (LSI) can be calculated as follows:

#### 3.5.2. Analytic Hierarchy Process (AHP)

_{ij}is the result of comparing the importance of factor i and factor j, and has the following properties:

_{max}is the largest eigenvalue of the judgment matrix; n is the order of the judgment matrix; and RI is the random index, which is listed in Table 1 [16].

_{i}is the weight of influencing factor i.

#### 3.5.3. Random Forest (RF) Model

## 4. Results

#### 4.1. Multicollinearity Analysis

#### 4.2. Results of the Information Content Model

#### 4.3. Results of the Analytic Hierarchy Process

#### 4.4. Results of the Random Forest Model

## 5. Validation and Discussion

#### 5.1. Validation

#### 5.2. Comparison of Landslide Susceptibility Maps

^{2}, respectively, for the SU-ICM model. For the SU-AHP model, the area of the four classes are 942.80, 1964.54, 1410.72, and 791.49 km

^{2}, respectively. For the SU-RF model, the area of the four classes are 1907.41, 1571.90, 1100.75, and 528.49 km

^{2}, respectively. For the GU-ICM model, the areas are 756.05, 2188.98, 1275.39, and 889.13 km

^{2}, respectively. For the GU-AHP model are 1274.84, 2044.59, 1109.42, and 680.70 km

^{2}, respectively. For the GU-RF model are 1100.92, 2082.84, 1491.10, and 434.68 km

^{2}, respectively. The landslide counts for the four susceptibility classes of the SU-ICM model are 2, 11, 42, and 103, respectively, accounting for 1.26%, 6.92%, 24.42% and 64.78% of the total landslide count of the study area, respectively. The landslide counts for the SU-AHP model are 8, 28, 45, and 78, respectively, accounting for 5.03%, 17.61%, 28.30%, and 49.06% of the total landslides count, respectively. For the SU-RF model are 0, 6, 35, and 118, respectively, accounting for 0.00%, 3.77%, 22.01%, and 74.41% of the total landslides count, respectively. For the GU-ICM model are 2, 22, 35, and 100, respectively, accounting for 1.26%, 13.84%, 22.01%, and 62.89% of the total landslides count, respectively. For the GU-AHP model are 16, 52, 36, and 56, respectively, accounting for 10.06%, 32.70%, 22.01%, and 35.22% of the total landslides count, respectively. For the GU-RF model are 5, 23, 54, and 77, respectively, accounting for 3.14%, 14.47%, 33.96%, and 48.43% of the total landslides count, respectively.

#### 5.3. Comparison with Other Models

#### 5.4. Landslide Suceptibility Maps Analysis

## 6. Conclusions

^{2}, respectively. The landslide counts for the four susceptibility classes of the SU-RF model are 0, 6, 35, and 118, respectively, accounting for 0.00%, 3.77%, 22.01%, and 74.41% of the total landslide counts, respectively.

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Rotigliano, E.; Conoscenti, C.; Costanzo, D.; Agnesi, V.J.N.H. Slope units-based flow susceptibility model: Using validation tests to select controlling factors. Nat. Harzards
**2012**, 61, 143–153. [Google Scholar] [CrossRef] - Sun, X.; Chen, J.; Han, X.; Bao, Y.; Zhan, J.; Peng, W. Application of a GIS-based slope unit method for landslide susceptibility mapping along the rapidly uplifting section of the upper Jinsha River, South-Western China. Bull. Eng. Geol. Environ.
**2019**. [Google Scholar] [CrossRef] - Yang, X.J.; Chen, L.D. Geoinformation. Using multi-temporal remote sensor imagery to detect earthquake-triggered landslides. Int. J. Appl. Earth Obs. Geoinf.
**2010**, 12, 487–495. [Google Scholar] [CrossRef] - Bao, Y.; Zhai, S.; Chen, J.; Xu, P.; Sun, X.; Zhan, J.; Zhang, W.; Zhou, X. The evolution of the Samaoding paleolandslide river blocking event at the upstream reaches of the Jinsha River, Tibetan Plateau. Geomorphology
**2020**, 351, 106970. [Google Scholar] [CrossRef] - Ohlmacher, G.C.; Davis, J.C. Using multiple logistic regression and GIS technology to predict landslide hazard in northeast Kansas, USA. Eng. Geol.
**2003**, 69, 331–343. [Google Scholar] [CrossRef] - Ren, F.; Wu, X. GIS-Based Landslide Susceptibility Mapping Using Remote Sensing Data and Machine Learning Methods; Springer: Berlin/Heidelberg, Germany, 2014; pp. 319–333. [Google Scholar]
- Dieu Tien, B.; Shahabi, H.; Omidvar, E.; Shirzadi, A.; Geertsema, M.; Clague, J.J.; Khosravi, K.; Pradhan, B.; Binh Thai, P.; Chapi, K.; et al. Shallow landslide prediction using a novel hybrid functional machine learning algorithm. Remote Sens.
**2019**, 11, 931. [Google Scholar] [CrossRef] [Green Version] - Liu, L.; Li, S.; Li, X.; Jiang, Y.; Wei, W.; Wang, Z.; Bai, Y. An integrated approach for landslide susceptibility mapping by considering spatial correlation and fractal distribution of clustered landslide data. Landslides
**2019**, 16, 715–728. [Google Scholar] [CrossRef] - Mondal, S.; Mandal, S. Landslide susceptibility mapping of Darjeeling Himalaya, India using index of entropy (IOE) model. Appl. Geomat.
**2019**, 11, 129–146. [Google Scholar] [CrossRef] - Monsieurs, E.; Dewitte, O.; Demoulin, A. A susceptibility-based rainfall threshold approach for landslide occurrence. Nat. Hazards Earth Syst. Sci.
**2019**, 19, 775–789. [Google Scholar] [CrossRef] [Green Version] - Nahayo, L.; Kalisa, E.; Maniragaba, A.; Nshimiyimana, F.X. Comparison of analytical hierarchy process and certain factor models in landslide susceptibility mapping in Rwanda. Model. Earth Syst. Environ.
**2019**, 5, 885–895. [Google Scholar] [CrossRef] - Bai, S.-B.; Wang, J.; Lue, G.-N.; Zhou, P.-G.; Hou, S.-S.; Xu, S.-N. GIS-based logistic regression for landslide susceptibility mapping of the Zhongxian segment in the Three Gorges area, China. Geomorphology
**2010**, 115, 23–31. [Google Scholar] [CrossRef] - Cao, C.; Wang, Q.; Chen, J.; Ruan, Y.; Zheng, L.; Song, S.; Niu, C. Landslide Susceptibility Mapping in Vertical Distribution Law of Precipitation Area: Case of the Xulong Hydropower Station Reservoir, Southwestern China. Water
**2016**, 8, 270. [Google Scholar] [CrossRef] [Green Version] - Lee, S. Application of logistic regression model and its validation for landslide susceptibility mapping using GIS and remote sensing data journals. Int. J. Remote Sens.
**2005**, 26, 1477–1491. [Google Scholar] [CrossRef] - Yalcin, A.; Reis, S.; Aydinoglu, A.C.; Yomralioglu, T. A GIS-based comparative study of frequency ratio, analytical hierarchy process, bivariate statistics and logistics regression methods for landslide susceptibility mapping in Trabzon, NE Turkey. Catena
**2011**, 85, 274–287. [Google Scholar] [CrossRef] - Wang, F.; Xu, P.; Wang, C.; Wang, N.; Jiang, N. Application of a GIS-Based Slope Unit Method for Landslide Susceptibility Mapping along the Longzi River, Southeastern Tibetan Plateau, China. ISPRS Int. J. Geo-Inf.
**2017**, 6, 172. [Google Scholar] [CrossRef] [Green Version] - Du, G.; Zhang, Y.; Yang, Z.; Guo, C.; Yao, X.; Sun, D. Landslide susceptibility mapping in the region of eastern Himalayan syntaxis, Tibetan Plateau, China: A comparison between analytical hierarchy process information value and logistic regression-information value methods. Bull. Eng. Geol. Environ.
**2019**, 78, 4201–4215. [Google Scholar] [CrossRef] - Chen, W.; Panahi, M.; Tsangaratos, P.; Shahabi, H.; Ilia, I.; Panahi, S.; Li, S.; Jaafari, A.; Bin Ahmad, B. Applying population-based evolutionary algorithms and a neuro-fuzzy system for modeling landslide susceptibility. Catena
**2019**, 172, 212–231. [Google Scholar] [CrossRef] - Khosravi, K.; Panahi, M.; Bui, D.T. Spatial prediction of groundwater spring potential mapping based on an adaptive neuro-fuzzy inference system and metaheuristic optimization. Hydrol. Earth Syst. Sci.
**2018**, 22, 4771–4792. [Google Scholar] [CrossRef] [Green Version] - Lei, T.; Xue, D.; Lv, Z.; Li, S.; Zhang, Y.; Nandi, A.K. Unsupervised Change Detection Using Fast Fuzzy Clustering for Landslide Mapping from Very High-Resolution Images. Remote Sens.
**2018**, 10, 1381. [Google Scholar] [CrossRef] [Green Version] - Mokarram, M.; Zarei, A.R. Landslide Susceptibility Mapping Using Fuzzy-AHP. Geotech. Geol. Eng.
**2018**, 36, 3931–3943. [Google Scholar] [CrossRef] - Kose, D.D.; Turk, T. GIS-based fully automatic landslide susceptibility analysis by weight-of-evidence and frequency ratio methods. Phys. Geogr.
**2019**, 40, 481–501. [Google Scholar] [CrossRef] - Kumar, A.; Sharma, R.K.; Bansal, V.K. GIS-based comparative study of information value and frequency ratio method for landslide hazard zonation in a part of mid-Himalaya in Himachal Pradesh. Innov. Infrastruct. Solut.
**2019**, 4, 18. [Google Scholar] [CrossRef] - Sevgen, E.; Kocaman, S.; Nefeslioglu, H.A.; Gokceoglu, C. A Novel Performance Assessment Approach Using Photogrammetric Techniques for Landslide Susceptibility Mapping with Logistic Regression, ANN and Random Forest. Sensors
**2019**, 19, 3940. [Google Scholar] [CrossRef] [Green Version] - Binh Thai, P.; Dieu Tien, B.; Prakash, I.; Dholakia, M.B. Hybrid integration of Multilayer Perceptron Neural Networks and machine learning ensembles for landslide susceptibility assessment at Himalayan area (India) using GIS. Catena
**2017**, 149, 52–63. [Google Scholar] [CrossRef] - Jiang, P.; Zeng, Z.; Chen, J.; Huang, T. Generalized regression neural networks with K-Fold cross-validation for displacement of landslide forecasting. In Advances in Neural Networks—ISNN 2014; Zeng, Z., Li, Y., King, I., Eds.; Springer International Publishing: Cham, Switzerland, 2014; Volume 8866, pp. 533–541. [Google Scholar]
- 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] - Hong, H.; Liu, J.; Zhu, A.X.; Shahabi, H.; Binh Thai, P.; Chen, W.; Pradhan, B.; Dieu Tien, B. A novel hybrid integration model using support vector machines and random subspace for weather-triggered landslide susceptibility assessment in the Wuning area (China). Environ. Earth Sci.
**2017**, 76, 652. [Google Scholar] [CrossRef] - Liu, Y.H.; Li, D.H.; Chen, W.; Lin, B.S.; Seeboonruang, U.; Tsai, F. Soil Erosion Modeling and Comparison Using Slope Units and Grid Cells in Shihmen Reservoir Watershed in Northern Taiwan. Water
**2018**, 10, 1387. [Google Scholar] [CrossRef] [Green Version] - Tian, Y.; Xiao, C.; Wu, L. Slope unit-based landslide susceptibility zonation. In Proceedings of the 2010 18th International Conference on Geoinformatics, Beijing, China, 18–20 June 2010; pp. 1–5. [Google Scholar]
- Tsai, H.Y.; Tsai, C.C.; Chang, W.C. Slope unit-based approach for assessing regional seismic landslide displacement for deep and shallow failure. Eng. Geol.
**2019**, 248, 124–139. [Google Scholar] [CrossRef] - Su, Q.; Zhang, J.; Zhao, S.; Wang, L.; Liu, J.; Guo, J. Comparative Assessment of Three Nonlinear Approaches for Landslide Susceptibility Mapping in a Coal Mine Area. ISPRS Int. J. Geo-Inf.
**2017**, 6, 228. [Google Scholar] [CrossRef] [Green Version] - Sun, X.; Chen, J.; Bao, Y.; Han, X.; Zhan, J.; Peng, W. Landslide Susceptibility Mapping Using Logistic Regression Analysis along the Jinsha River and Its Tributaries Close to Derong and Deqin County, Southwestern China. ISPRS Int. J. Geo-Inf.
**2018**, 7, 438. [Google Scholar] [CrossRef] [Green Version] - Tanyas, H.; Rossi, M.; Alvioli, M.; van Westen, C.J.; Marchesini, I. A global slope unit-based method for the near real-time prediction of earthquake-induced landslides. Geomorphology
**2019**, 327, 126–146. [Google Scholar] [CrossRef] - Romstad, B.; Etzelmuller, B. Mean-curvature watersheds: A simple method for segmentation of a digital elevation model into terrain units. Geomorphology
**2012**, 139, 293–302. [Google Scholar] [CrossRef] [Green Version] - Sun, X.; Chen, J.; Han, X.; Bao, Y.; Zhou, X.; Peng, W. Landslide susceptibility mapping along the upper Jinsha River, south-western China: A comparison of hydrological and curvature watershed methods for slope unit classification. Bull. Eng. Geol. Environ.
**2020**, 79, 4657–4670. [Google Scholar] [CrossRef] - Binh Thai, P.; Dieu Tien, B.; Pourghasemi, H.R.; Indra, P.; Dholakia, M.B. Landslide susceptibility assesssment in the Uttarakhand area (India) using GIS: A comparison study of prediction capability of naïve bayes, multilayer perceptron neural networks, and functional trees methods. Theor. Appl. Climatol.
**2017**, 128, 255–273. [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] - Dahal, R.K.; Hasegawa, S.; Nonomura, A.; Yamanaka, M.; Masuda, T.; Nishino, K. GIS-based weights-of-evidence modelling of rainfall-induced landslides in small catchments for landslide susceptibility mapping. Environ. Geol.
**2008**, 54, 311–324. [Google Scholar] [CrossRef] - 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] [Green Version] - Aditian, A.; Kubota, T.; Shinohara, Y. Comparison of GIS-based landslide susceptibility models using frequency ratio, logistic regression, and artificial neural network in a tertiary region of Ambon, Indonesia. Geomorphology
**2018**, 318, 101–111. [Google Scholar] [CrossRef] - Ayalew, L.; Yamagishi, H. The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda-Yahiko Mountains, Central Japan. Geomorphology
**2005**, 65, 15–31. [Google Scholar] [CrossRef] - 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] - Hong, H.; Pradhan, B.; Jebur, M.N.; Bui, D.T.; Xu, C.; Akgun, A. Spatial prediction of landslide hazard at the Luxi area (China) using support vector machines. Environ. Earth Sci.
**2016**, 75, 40. [Google Scholar] [CrossRef] - Kumar, D.; Thakur, M.; Dubey, C.S.; Shukla, D.P. Landslide susceptibility mapping & prediction using Support Vector Machine for Mandakini River Basin, Garhwal Himalaya, India. Geomorphology
**2017**, 295, 115–125. [Google Scholar] [CrossRef] - Zhan, J.; Chen, J.; Zhang, W.; Han, X.; Sun, X.; Bao, Y. Mass movements along a rapidly uplifting river valley: An example from the upper Jinsha River, southeast margin of the Tibetan Plateau. Environ. Earth Sci.
**2018**, 77, 634. [Google Scholar] [CrossRef] - Binh Thai, P.; Dieu Tien, B.; Dholakia, M.B.; Prakash, I.; Ha Viet, P.; Mehmood, K.; Hung Quoc, L. A novel ensemble classifier of rotation forest and Naive Bayer for landslide susceptibility assessment at the Luc Yen district, Yen Bai Province (Viet Nam) using GIS. Geomat. Nat. Hazards Risk
**2017**, 8, 649–671. [Google Scholar] [CrossRef] [Green Version] - Zhang, X.; Wu, Y.; Zhai, E.; Ye, P. Coupling analysis of the heat-water dynamics and frozen depth in a seasonally frozen zone. J. Hydrol.
**2020**, 125603. [Google Scholar] [CrossRef] - Feng, H.; Yu, J.; Zheng, J.; Tang, X.; Peng, C.J.E.E.S. Evaluation of different models in rainfall-triggered landslide susceptibility mapping: A case study in Chunan, southeast China. Environ. Earth Sci.
**2016**, 75, 1399. [Google Scholar] [CrossRef] - Yi, Y.; Zhang, Z.; Zhang, W.; Xu, Q.; Deng, C.; Li, Q. GIS-based earthquake-triggered-landslide susceptibility mapping with an integrated weighted index model in Jiuzhaigou region of Sichuan Province, China. Nat. Hazards Earth Syst. Sci.
**2019**, 19, 1973–1988. [Google Scholar] [CrossRef] [Green Version] - Hong, H.Y.; Liu, J.Z.; Zhu, A.X. Modeling landslide susceptibility using LogitBoost alternating decision trees and forest by penalizing attributes with the bagging ensemble. Sci. Total Environ.
**2020**, 718, 137231. [Google Scholar] [CrossRef] - Sachdeva, S.; Kumar, B. Comparison of gradient boosted decision trees and random forest for groundwater potential mapping in Dholpur (Rajasthan), India. Stoch. Environ. Res. Risk Assess.
**2020**, 1–20. [Google Scholar] [CrossRef] - Li, Y.; Zhang, S.; Zhang, X. Classification and fractal characteristics of coal rock fragments under uniaxial cyclic loading conditions. Arab. J. Geosci.
**2018**, 11, 201. [Google Scholar] [CrossRef] - Qin, Z.; Fu, H.; Chen, X. A study on altered granite meso-damage mechanisms due to water invasion-water loss cycles. Environ. Earth Sci.
**2019**, 78, 428. [Google Scholar] [CrossRef] - Wang, J.; Li, S.; Li, L.; Lin, P.; Xu, Z.; Gao, C. Attribute recognition model for risk assessment of water inrush. Bull. Eng. Geol. Environ.
**2019**, 78, 1057–1071. [Google Scholar] [CrossRef] - Zhang, S.; Li, Y.; Shen, B.; Sun, X.; Gao, L. Effective evaluation of pressure relief drilling for reducing rock bursts and its application in underground coal mines. Int. J. Rock Mech. Min. Sci.
**2019**, 114, 7–16. [Google Scholar] [CrossRef] - Zhu, C.; Tao, Z.; Yang, S.; Zhao, S. V shaped gully method for controlling rockfall on high-steep slopes in China. Bull. Eng. Geol. Environ.
**2019**, 78, 2731–2747. [Google Scholar] [CrossRef] - Huang, F.; Yin, K.; Huang, J.; Gui, L.; Wang, P. Landslide susceptibility mapping based on self-organizing-map network and extreme learning machine. Eng. Geol.
**2017**, 223, 11–22. [Google Scholar] [CrossRef] - Pourghasemi, H.R.; Kerle, N. Random forests and evidential belief function-based landslide susceptibility assessment in Western Mazandaran Province, Iran. Environ. Earth Sci.
**2016**, 75, 185. [Google Scholar] [CrossRef] - Pradhan, B.; Lee, S. Landslide susceptibility assessment and factor effect analysis: Backpropagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modelling. Environ. Model. Softw.
**2010**, 25, 747–759. [Google Scholar] [CrossRef] - Yao, X.; Tham, L.G.; Dai, F.C. Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China. Geomorphology
**2008**, 101, 572–582. [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] - Yu, C.; Chen, J. Landslide Susceptibility Mapping Using the Slope Unit for Southeastern Helong City, Jilin Province, China: A Comparison of ANN and SVM. Symmetry-Basel
**2020**, 12, 1047. [Google Scholar] [CrossRef]

**Figure 1.**Sketch of the study area: (

**a**) geographic location; (

**b**) landslide inventory map from the geological hazard survey and regionalization of Helong city, Jilin province (1:100,000); (

**c**) geological map: lithology and fault from 91 weitu software; Seismic intensity from the Seismic Intensity Zoning Map of China.

**Figure 5.**Typical landslides and their impacts within the study area. (

**a**) Zhulin landslide; (

**b**) landslide due to a fissure.

**Figure 6.**Influencing factor maps of the study area: (

**a**) lithology, (

**b**) slope angle, (

**c**) slope aspect, (

**d**) rainfall, (

**e**) land use, (

**f**) seismic intensity, (

**g**) distance to river, and (

**h**) distance to fault.

**Figure 7.**Landslide susceptibility maps; (

**a**) information content method (ICM) method (slope units), (

**b**) analytical hierarchy process (AHP) method (slope units), (

**c**) random forest (RF) method (slope units), (

**d**) ICM method (grid units), (

**e**) AHP method (grid units), and (

**f**) RF method (grid units).

**Figure 8.**Receiver operating characteristic (ROC) curve of the models (SU: slope units, GU: grid units).

n | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 |
---|---|---|---|---|---|---|---|---|---|---|---|

RI | 0 | 0 | 0.58 | 0.90 | 1.12 | 1.24 | 1.32 | 1.41 | 1.45 | 1.49 | 1.51 |

Influencing Factor | VIF |
---|---|

Lithology | 1.440 |

Slope angle | 1.748 |

Slope aspect | 1.004 |

Rainfall | 1.728 |

Land use | 1.363 |

Seismic intensity | 1.391 |

Distance to river | 1.152 |

Distance to fault | 1.094 |

Factor | Class | Landslide Count | Total Count | ICM | Factor | Class | Landslide Count | Total Count | ICM |
---|---|---|---|---|---|---|---|---|---|

Lithology | Q | 21 | 3,918,004 | 0.54 | Distance to river | 0–500 | 88 | 9,094,709 | 1.13 |

N | 2 | 6,403,667 | −2.30 | 500–1000 | 13 | 4,187,032 | 0.00 | ||

K | 6 | 3,300,622 | −0.54 | 1000–1500 | 6 | 3,625,727 | −0.63 | ||

J | 44 | 7,867,350 | 0.59 | 1500–2000 | 5 | 3,148,408 | −0.67 | ||

Pt | 76 | 25,177,330 | −0.03 | 2000–2500 | 7 | 3,205,830 | −0.35 | ||

Ar | 10 | 4,428,508 | −0.32 | >2500 | 40 | 27,833,775 | −0.77 | ||

Slope angle | 0–6 | 5 | 6,000,220 | −1.32 | Land use | Hemerophyte | 25 | 5,066,280 | 0.46 |

6–12 | 38 | 14,446,398 | −0.17 | Bare land | 15 | 2,777,508 | 0.55 | ||

12–18 | 78 | 26,126,800 | −0.04 | Leaf wood | 111 | 2,943,655 | 2.49 | ||

18–24 | 29 | 4,422,539 | 0.75 | Coniferous forest | 6 | 6,305,813 | −1.18 | ||

24–30 | 9 | 99,524 | 3.37 | Mixed forest | 2 | 7,509,325 | −2.46 | ||

Slope aspect | N | 0 | 4458 | 0.00 | Seismic intensity | VI | 155 | 44,424,311 | 0.11 |

NE | 1 | 1,603,815 | −1.61 | VII | 4 | 5,854,173 | −1.52 | ||

E | 27 | 9,892,010 | −0.13 | VIII | 0 | 816,997 | 0.00 | ||

SE | 44 | 11,758,719 | 0.18 | Distance to fault | 0–600 | 30 | 8,493,314 | 0.13 | |

S | 49 | 10,308,180 | 0.42 | 600–1200 | 10 | 3,912,575 | −0.20 | ||

SW | 25 | 9,108,996 | −0.13 | 1200–1800 | 17 | 4,060,718 | 0.30 | ||

W | 12 | 7,405,201 | −0.65 | 1800–2400 | 14 | 4,389,149 | 0.02 | ||

NW | 1 | 1,014,102 | −1.15 | 2400–3000 | 5 | 1,370,885 | 0.16 | ||

Rainfall | 500–520 | 57 | 4,872,206 | 1.32 | >3000 | 83 | 28,868,870 | −0.08 | |

520–540 | 29 | 1,0162,854 | −0.09 | ------ | |||||

540–560 | 27 | 12,711,943 | −0.38 | ||||||

560–580 | 13 | 15,620,685 | −1.32 | ||||||

580–600 | 3 | 7,727,793 | −2.08 |

Factor | Class | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | Weight | CI/CR |
---|---|---|---|---|---|---|---|---|---|---|---|

Lithology | Q | 1 | 8 | 5 | 1 | 3 | 4 | 0.3141 | 0.074/0.060 | ||

N | 1/8 | 1 | 1/3 | 1/9 | 1/5 | 1/4 | 0.0281 | ||||

K | 1/5 | 3 | 1 | 1/7 | 1/3 | 1/2 | 0.0548 | ||||

J | 1 | 9 | 7 | 1 | 3 | 5 | 0.3474 | ||||

Pt | 1/3 | 5 | 3 | 1/3 | 1 | 6 | 0.1810 | ||||

Ar | 1/4 | 4 | 2 | 1/5 | 1/6 | 1 | 0.0745 | ||||

Slope angle | 0–6 | 1 | 1/3 | 1/4 | 1/6 | 1/8 | 0.0381 | 0.051/0.046 | |||

6–12 | 3 | 1 | 1/2 | 1/5 | 1/7 | 0.0708 | |||||

12–18 | 4 | 2 | 1 | 1/3 | 1/5 | 0.1152 | |||||

18–24 | 6 | 5 | 3 | 1 | 1/3 | 0.2616 | |||||

24–30 | 8 | 7 | 5 | 3 | 1 | 0.5142 | |||||

Slope aspect | N | 1 | 1/2 | 1/5 | 1/6 | 1/8 | 1/5 | 1/3 | 1/2 | 0.0271 | 0.023/0.016 |

NE | 2 | 1 | 1/4 | 1/5 | 1/7 | 1/4 | 1/3 | 1/2 | 0.0358 | ||

E | 5 | 4 | 1 | 1/2 | 1/4 | 1 | 2 | 3 | 0.1231 | ||

SE | 6 | 5 | 2 | 1 | 1/3 | 2 | 3 | 4 | 0.1917 | ||

S | 8 | 7 | 4 | 3 | 1 | 4 | 5 | 6 | 0.3754 | ||

SW | 5 | 4 | 1 | 1/2 | 1/4 | 1 | 2 | 3 | 0.1231 | ||

W | 3 | 2 | 1/2 | 1/3 | 1/5 | 1/2 | 1 | 4 | 0.0816 | ||

NW | 2 | 1 | 1/3 | 1/4 | 1/6 | 1/3 | 1/4 | 1 | 0.0423 | ||

Rainfall | 500–520 | 1 | 1/2 | 1/2 | 1/3 | 1/4 | 0.0791 | 0.008/0.007 | |||

520–540 | 2 | 1 | 1 | 1/2 | 1/3 | 0.1367 | |||||

540–560 | 2 | 1 | 1 | 1/2 | 1/3 | 0.1367 | |||||

560–580 | 3 | 2 | 2 | 1 | 1/2 | 0.2444 | |||||

580–600 | 4 | 3 | 3 | 2 | 1 | 0.4030 | |||||

Land use | Hemerophyte | 1 | 1/2 | 1/4 | 3 | 4 | 0.1529 | 0.035/0.031 | |||

Bare land | 2 | 1 | 1/3 | 4 | 5 | 0.2359 | |||||

Leaf wood | 4 | 3 | 1 | 6 | 7 | 0.4963 | |||||

Coniferous forest | 1/3 | 1/4 | 1/6 | 1 | 2 | 0.0688 | |||||

Mixed forest | 1/4 | 1/5 | 1/7 | 1/2 | 1 | 0.0461 | |||||

Seismic intensity | VI | 1 | 1/2 | 1/4 | 0.1365 | 0.009/0.016 | |||||

VII | 2 | 1 | 1/3 | 0.2385 | |||||||

VIII | 4 | 3 | 1 | 0.6250 | |||||||

Distance to river | 0–500 | 1 | 5 | 3 | 3 | 2 | 4 | 0.3720 | 0.06/0.005 | ||

500–1000 | 1/5 | 1 | 1/2 | 1/2 | 1/3 | 1 | 0.0700 | ||||

1000–1500 | 1/3 | 2 | 1 | 1 | 1/2 | 2 | 0.1297 | ||||

1500–2000 | 1/3 | 2 | 1 | 1 | 1/2 | 2 | 0.1297 | ||||

2000–2500 | 1/2 | 3 | 2 | 2 | 1 | 3 | 0.2254 | ||||

>2500 | 1/4 | 1 | 1/2 | 1/2 | 1/3 | 1 | 0.0731 | ||||

Distance to fault | 0–600 | 1 | 4 | 1/2 | 2 | 1 | 3 | 0.1952 | 0.028/0.023 | ||

600–1200 | 1/4 | 1 | 1/6 | 1/3 | 1/5 | 1/2 | 0.0435 | ||||

1200–1800 | 2 | 6 | 1 | 3 | 2 | 4 | 0.3376 | ||||

1800–2400 | 1/2 | 3 | 1/3 | 1 | 1/3 | 2 | 0.1077 | ||||

2400–3000 | 1 | 5 | 1/2 | 3 | 1 | 6 | 0.2514 | ||||

>3000 | 1/3 | 2 | 1/4 | 1/2 | 1/6 | 1 | 0.0646 | ||||

All | Lithology | 1 | 1/2 | 4 | 5 | 6 | 7 | 2 | 3 | 0.2307 | 0.041/0.029 |

Slope angle | 2 | 1 | 5 | 6 | 7 | 8 | 3 | 4 | 0.3313 | ||

Slope aspect | 1/4 | 1/5 | 1 | 2 | 3 | 4 | 1/3 | 1/2 | 0.0709 | ||

Rainfall | 1/5 | 1/6 | 1/2 | 1 | 2 | 3 | 1/4 | 1/3 | 0.0477 | ||

Land use | 1/6 | 1/7 | 1/3 | 1/2 | 1 | 2 | 1/5 | 1/4 | 0.0327 | ||

Seismic intensity | 1/7 | 1/8 | 1/4 | 1/3 | 1/2 | 1 | 1/6 | 1/5 | 0.0236 | ||

Distance to river | 1/2 | 1/3 | 3 | 4 | 5 | 6 | 1 | 2 | 0.1572 | ||

Distance to fault | 1/3 | 1/4 | 2 | 3 | 4 | 5 | 1/2 | 1 | 0.1059 |

Models | Susceptibility | Landslides Count | Landslides Ratio | Class Area (km ^{2}) | Class Ratio |
---|---|---|---|---|---|

SU-ICM | Low | 2 | 1.26% | 897.03 | 17.56% |

Moderate | 11 | 6.92% | 1142.43 | 22.36% | |

High | 42 | 26.42% | 1696.53 | 33.20% | |

Very High | 103 | 64.78% | 1373.56 | 26.88% | |

SU-AHP | Low | 8 | 5.03% | 942.80 | 18.45% |

Moderate | 28 | 17.61% | 1964.54 | 38.45% | |

High | 45 | 28.30% | 1410.72 | 27.61% | |

Very High | 78 | 49.06% | 791.49 | 15.49% | |

SU-RF | Low | 0 | 0.00% | 1907.41 | 37.33% |

Moderate | 6 | 3.77% | 1571.90 | 30.76% | |

High | 35 | 22.01% | 1100.75 | 21.54% | |

Very High | 118 | 74.21% | 529.49 | 10.36% | |

GU-ICM | Low | 2 | 1.26% | 756.05 | 14.80% |

Moderate | 22 | 13.84% | 2188.98 | 42.84% | |

High | 35 | 22.01% | 1275.39 | 24.96% | |

Very High | 100 | 62.89% | 889.13 | 17.40% | |

GU-AHP | Low | 16 | 10.06% | 1274.84 | 24.95% |

Moderate | 52 | 32.70% | 2044.59 | 40.02% | |

High | 35 | 22.01% | 1109.42 | 21.71% | |

Very High | 56 | 35.22% | 680.70 | 13.32% | |

GU-RF | Low | 5 | 3.14% | 1100.92 | 21.55% |

Moderate | 23 | 14.47% | 2082.84 | 40.76% | |

High | 54 | 33.96% | 1491.10 | 29.18% | |

Very High | 77 | 48.43% | 434.68 | 8.51% |

Source | Mapping Units | Method | Prediction Accuracy |
---|---|---|---|

This study | Grid units | ICM AHP | 83.4% |

70.9% | |||

RF | 94.6% | ||

Slope units | ICM AHP | 87.1% | |

80.5% | |||

RF | 91.3 | ||

Yu et al. (2020) [63] | Slope units | ANN | 89.7% |

SVM | 90.7% |

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

© 2020 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**

Yu, C.; Chen, J.
Application of a GIS-Based Slope Unit Method for Landslide Susceptibility Mapping in Helong City: Comparative Assessment of ICM, AHP, and RF Model. *Symmetry* **2020**, *12*, 1848.
https://doi.org/10.3390/sym12111848

**AMA Style**

Yu C, Chen J.
Application of a GIS-Based Slope Unit Method for Landslide Susceptibility Mapping in Helong City: Comparative Assessment of ICM, AHP, and RF Model. *Symmetry*. 2020; 12(11):1848.
https://doi.org/10.3390/sym12111848

**Chicago/Turabian Style**

Yu, Chenglong, and Jianping Chen.
2020. "Application of a GIS-Based Slope Unit Method for Landslide Susceptibility Mapping in Helong City: Comparative Assessment of ICM, AHP, and RF Model" *Symmetry* 12, no. 11: 1848.
https://doi.org/10.3390/sym12111848