# Using Fuzzy Neural Networks to Model Landslide Susceptibility at the Shihmen Reservoir Catchment in Taiwan

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Study Area

^{2}) is steeply dissected, mountainous terrain that includes numerous alluvial terraces (Figure 1). The overall topography is highest in the south and lowest in the north. Elevation ranges from 3500 m at the southernmost edge to about 150 m at the northern end and channels generally flow northwards. In the upland regions of the catchment, high-gradient streams are common and carry enormous amounts of sediment into the Shihmen Reservoir, causing siltation of the reservoir. The average annual rainfall is about 2400 mm. Affected by the plum rain season and typhoons; the main rainy season is from May to October. There are also thunderstorms brought by south-westerly currents and heavy rainfall induced by tropical depressions.

## 3. Materials and Methods

#### 3.1. Landslide Inventory

#### 3.2. Factor Selection

#### 3.3. Methodology

#### 3.3.1. Fuzzy Neural Network

_{b}is a membership function.

#### 3.3.2. Logistic Regression

#### 3.4. Model Calibration

_{1}represents sandstone and shale units, L

_{2}represents indurated sandstone and shale units, L

_{3}represents argillite units, and L

_{4}represents quartzite and argillite units. A

_{1}is the aspect direction within the range 337.5 to 22.5, A

_{2}is the aspect direction within the range 22.5 to 67.5, A

_{3}is the aspect direction within the range 67.5 to 112.5, A

_{4}is the aspect direction within the range 112.5 to 157.5, A

_{5}is the aspect direction within the range 157.5 to 202.5, A

_{6}is the aspect direction within the range 202.5 to 247.5, A

_{7}is the aspect direction within the range 247.5 to 292.5, and A

_{8}is the aspect direction within the range 292.5 to 337.5. Table 1 shows the names of factors F

_{01}to F

_{10}.

## 4. Results

## 5. Discussion

## 6. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Montgomery, D.R.; Dietrich, W.E. A physical-based model for the topographic control on shallow landsliding. Water Resour. Res.
**1994**, 30, 1153–1171. [Google Scholar] [CrossRef] - Van Westen, C.J.; Terlien, M.T.J. An approach towards deterministic landslide hazard analysis in GIS: A case study from Manizales (Colombia). Earth Surf. Process. Landf.
**1996**, 21, 853–868. [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] - Lee, C.T. GIS Application in Landslide Hazard Analysis. In Proceedings of the Pacific Neighborhood Consortium (PNC) Annual Meeting Program, Taibei, China, 28–30 September 2021. [Google Scholar]
- Lee, C.T. Multi-stage statistical landslide hazard analysis: Earthquake-induced landslides. Landslide Sci. Safer Geoenviron.
**2014**, 3, 205–211. [Google Scholar] - Lee, C.T. Multi-stage statistical landslide hazard analysis: Rain-induced landslides. Landslide Sci. Safer Geoenviron.
**2014**, 3, 291–298. [Google Scholar] - Caniani, D.; Pascale, S.; Sdao, F.; Sole, A. Neural networks and landslide susceptibility: A case study of the urban area of Potenza. Nat. Hazards
**2008**, 45, 55–72. [Google Scholar] [CrossRef] - Lee, C.T.; Huang, C.M. Neuro-fuzzy-based landslide susceptibility analysis–an example from Central Western Taiwan. Geophys. Res. Abstr.
**2007**, 9, 06849. [Google Scholar] - Lee, M.J.; Choi, J.W.; Oh, H.J.; Won, J.S.; Park, I.; Lee, S. Ensemble based landslide susceptibility maps in Jinbu area, Korea. Environ. Earth Sci.
**2012**, 67, 23–37. [Google Scholar] [CrossRef] - Ngo, P.T.T.; Panahi, M.; Khosravi, K.; Ghorbanzadeh, O.; Karimnejad, 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] - 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] - Tian, Y.; Xu, C.; Hong, H.; Zhou, O.; Wang, D. Mapping earthquake-triggered landslide susceptibility by use of artificial neural network (ANN) models: An example of the 2013 Minxian (China) Mw 5.9 event. Geomat. Nat. Hazards Risk
**2019**, 10, 1–25. [Google Scholar] [CrossRef] [Green Version] - 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
**2020**, 12, 1047. [Google Scholar] [CrossRef] - Jones, J.M.; Fielding, A.; Sullivan, M. Analysing extinction risk in parrots using decision trees. Biodivers. Conserv.
**2006**, 15, 1993–2007. [Google Scholar] [CrossRef] - Nefeslioglu, H.A.; Sezer, E.; Gokceoglu, C.; Bozkir, A.S.; Duman, T.Y. Assessment of landslide susceptibility by decision trees in the metropolitan area of Istanbul, Turkey. Math. Probl. Eng.
**2010**, 2010, 901095. [Google Scholar] [CrossRef] [Green Version] - Saito, H.; Nakayama, D.; Matsuyama, H. Comparison of landslide susceptibility based on a decision-tree model and actual landslide occurrence: The Akaishi Mountains, Japan. Geomorphology
**2009**, 109, 108–121. [Google Scholar] [CrossRef] - Yeon, Y.K.; Han, J.G.; Ryu, K.H. Landslide susceptibility mapping in Injae, Korea, using a decision tree. Eng. Geol.
**2010**, 116, 274–283. [Google Scholar] [CrossRef] - Kocaman, S.; Tavus, B.; Nefeslioglu, H.A.; Karakas, G.; Gokceoglu, C. Evaluation of floods and landslides triggered by a meteorological catastrophe (Ordu, Turkey, August 2018) using optical and radar data. Geofluids
**2020**, 2020, 18. [Google Scholar] [CrossRef] - Marjanović, M.; Kovačević, M.; Bajat, B.; Voženílek, V. Landslide susceptibility assessment using SVM machine learning algorithm. Eng. Geol.
**2011**, 123, 225–234. [Google Scholar] [CrossRef] - Xu, C.; Dai, F.; Xu, X.; Lee, Y.H. GIS-based support vector machine modeling of earthquake-triggered landslide susceptibility in the Jianjiang River watershed, China. Geomorphology
**2012**, 145–146, 70–80. [Google Scholar] [CrossRef] - Yilmaz, I. Comparison of landslide susceptibility mapping methodologies for Koyulhisar, Turkey: Conditional probability, logistic regression, artificial neural networks, and support vector machine. Environ. Earth Sci.
**2010**, 61, 821–836. [Google Scholar] [CrossRef] - Akgun, A.; Sezer, E.A.; Nefesliogluc, H.A.; Gokceoglu, C.; Pradhane, B. An easy-to-use MATLAB program (MamLand) for the assessment of landslide susceptibility using a Mamdani fuzzy algorithm. Comput. Geosci.
**2012**, 38, 23–34. [Google Scholar] [CrossRef] - Lee, S.; Choi, J.; Oh, H. Landslide Susceptibility Mapping Using a Neuro-Fuzzy. In Proceedings of the American Geophysical Union Fall Meeting, San Francisco, CA, USA, 14–18 December 2009. [Google Scholar]
- Sezer, E.A.; Nefeslioglu, H.A.; Osnac, T. An expert-based landslide susceptibility mapping (LSM) module developed for Netcad Architect Software. Comput. Geosci.
**2017**, 98, 26–37. [Google Scholar] [CrossRef] - Sezer, E.A.; Pradhan, B.; Gokceoglu, C. Manifestation of an adaptive neuro-fuzzy model on landslide susceptibility mapping: Klang valley, Malaysia. Expert Syst. Appl.
**2011**, 38, 8208–8219. [Google Scholar] [CrossRef] - Vahidnia, M.H.; Alesheikh, A.A.; Alimohammadi, A.; Hosseinali, F. A GIS-based neuro-fuzzy procedure for integrating knowledge and data in landslide susceptibility mapping. Comput. Geosci.
**2010**, 36, 1101–1114. [Google Scholar] [CrossRef] - Wilson, J.P.; Gallant, J.C. Terrain Analysis; John Wiley & Sons, Inc.: Hoboken, NJ, USA, 2000; p. 479. [Google Scholar]
- Juang, C.H.; Jhi, Y.Y.; Lee, D.H. Stability analysis of existing slopes considering uncertainty. Eng. Geol.
**1998**, 49, 111–122. [Google Scholar] [CrossRef] - Chung, C.F.; Fabbri, A.G. Probabilistic prediction models for landslide hazard mapping. Photogramm. Eng. Remote Sens.
**1999**, 65, 1389–1399. [Google Scholar] - 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] - Chung, C.J.; Fabbri, A.G. Predicting landslides for risk analysis-spatial models tested by a cross-validation technique. Geomorphology
**2008**, 94, 438–452. [Google Scholar] [CrossRef]

**Figure 2.**The identifying procedure of triggered landslide: (

**a**) recent landslide; (

**b**) expanded landslide.

**Figure 6.**The example of selected factors. (

**a**) lithology; (

**b**) aspect; (

**c**) slope; (

**d**) slope roughness; (

**e**) tangential curvature; (

**f**) total slope height; (

**g**) relative slope height; (

**h**) TWI; (

**i**) distance to a fault; (

**j**) NDVI of typhoon Aere; (

**k**) maximum rainfall intensity of typhoon Aere; (

**l**) total rainfall of typhoon Aere; (

**m**) NDVI of typhoon Matsa; (

**n**) maximum rainfall intensity of typhoon Matsa; (

**o**) total rainfall of typhoon Matsa.

**Figure 10.**The result of curve fitting: (

**a**) FNN’s probability of failure curve; (

**b**) LR’s probability of failure curve.

**Figure 11.**Landslide probability map. (

**a**) training result of FNN; (

**b**) training result of LR; (

**c**) validation result of FNN; (

**d**) validation result of LR.

Code | Factor Item | Code | Factor Item |
---|---|---|---|

L | lithology | F_{05} | relative slope height |

A | aspect | F_{06} | TWI |

F_{01} | slope | F_{07} | distance to a fault |

F_{02} | slope roughness | F_{08} | NDVI |

F_{03} | tangential curvature | F_{09} | maximum rainfall intensity |

F_{04} | total slope height | F_{10} | total rainfall |

Observed | |||
---|---|---|---|

Landslide | Non-Landslide | ||

Predicted | Landslide | a | b |

Non-Landslide | c | d |

Aere Event (Training) | Matsa Event (Validation) | |||
---|---|---|---|---|

FNN | LR | FNN | LR | |

Landslide Accuracy | 90.1% | 82.1% | 75.6% | 72.7% |

Non-Landslide Accuracy | 80.2% | 78.4% | 71.3% | 74.0% |

Overall Accuracy | 84.7% | 80.8% | 72.9% | 73.6% |

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**

Huang, C.-M.; Lee, C.-T.; Jian, L.-X.; Wei, L.-W.; Chu, W.-C.; Lin, H.-H.
Using Fuzzy Neural Networks to Model Landslide Susceptibility at the Shihmen Reservoir Catchment in Taiwan. *Water* **2022**, *14*, 1196.
https://doi.org/10.3390/w14081196

**AMA Style**

Huang C-M, Lee C-T, Jian L-X, Wei L-W, Chu W-C, Lin H-H.
Using Fuzzy Neural Networks to Model Landslide Susceptibility at the Shihmen Reservoir Catchment in Taiwan. *Water*. 2022; 14(8):1196.
https://doi.org/10.3390/w14081196

**Chicago/Turabian Style**

Huang, Chuen-Ming, Chyi-Tyi Lee, Liu-Xuan Jian, Lun-Wei Wei, Wei-Chia Chu, and Hsi-Hung Lin.
2022. "Using Fuzzy Neural Networks to Model Landslide Susceptibility at the Shihmen Reservoir Catchment in Taiwan" *Water* 14, no. 8: 1196.
https://doi.org/10.3390/w14081196