Evaluating the Effectiveness of Machine Learning Models in Preparing a Landslide Risk Map in the Bar Neyshabur Watershed

Document Type : Research

Authors

1 Assistant Professor, Soil Conservation and Watershed Management Research Department, Khorasan Razavi Agricultural and Natural Resources Research and Education Center, AREEO, Mashhad, Iran

2 Assistant Professor, Soil Conservation and Watershed Management Research Department, Lorestan Agricultural and Natural Resources Research and Education Center, AREEO, Khorramabad, Iran

10.22092/wmrj.2023.361650.1531

Abstract

Introduction and Goal
Landslide susceptibility zoning using different methods is one of the solutions for landslide management. The aim of the upcoming study is to model the sensitivity of landslide occurrence using three methods of machine learning algorithm, random forest (RF), maximum entropy (ME) and support vector machine (SVM) algorithm. Then, the efficiency of these models is compared in zoning the sensitivity of landslides in the Bar Neyshabur watershed, Razavi Khorasan province.
Materials and Methods
In this research, the landslide distribution map layer of Bar watershed with 73 recorded points was prepared. These points were randomly divided into two groups for model training (70%) and model validation (30%). Also, 16 factors affecting the occurrence of landslides in the studied area were identified according to the review of extensive sources and digital layers were prepared in the geographic information system. Then, the landslide hazard map was prepared based on the three mentioned methods. Next, in order to evaluate the accuracy of modeling and compare the efficiency of the models, the total quality index (Qs) was used.
Results and Discussion
The results showed that the random forest algorithm method (RF) with Qs = 0.018 was chosen as the best model for the basin. Support vector models (SVM) with Qs = 0.014 and maximum entropy (ME) model with Qs = 0.013 are in the next priority, respectively.
Conclusion and Suggestions 
Based on the results of this research, the random forest model provided better results. The comparison of the results obtained from this model with the existing real conditions was done with field visits. In addition, the results of the landslide susceptibility zoning map using the random forest model and the actual conditions in the studied area were very compatible. Finally, it was determined that assuming the concentration of management operations in high-sensitivity classes and choosing the random forest model as the superior model, 75.5% of the region's area has been left out of the management process. Therefore, less time and financial resources are needed to manage this sector.

Keywords

Main Subjects

References

Abedini M, Ghasemyan B, Rezaei Mogaddam M.H. 2017. Landslide susceptibility mapping in Bijar City, Kurdistan Province, Iran: a comparative study by logistic regression and AHP models. Environmental Earth Sciences, 76(8): 1-14.
Afifi M. 2021. Spatial analysis of landslide risk with emphasis on geomorphological factors using stochastic forest model (Case study: Larestan City in Fars Province), Journal of Physical Geography, 14(51): 39-53. (In Persian). 20.1001.1.20085656.1400.14.51.3.0
Azimpour Moghadam V. 2014. Landslide risk zoning using Bayesian and Dempster-Schiffer theory (Case study: A part of Babelrud Watershed). Master's Thesis. Faculty of Agricultural Sciences and Natural Resources. University of Sari. pp. 1-135. (In Persian).
Convertino M, Troccoli A, Catani F. 2013. Detecting fingerprints of landslide drivers: A MaxEnt model. Journal of Geophysical Research: Earth Surface, 118(3): 1367-1386. https://doi.org/10.1002/jgrf.20099
Emadodin S, Taheri V, Mohammad Ghasemi M, Nazari Z. 2021. Landslide susceptibility zonation applying frequency ratio models and statistical index in in Oghan Watershed, Quantitative Geomorphological Researches, 9(4): 75-95. (In Persian). DOI:10.1007/s00254-001-0454-2
Ercanoglu M, Gokceoglu C. 2002. Assessment of landslide susceptibility for a landslide-prone area (north of Yenice, NW Turkey) by fuzzy approach. Environmental Geology, 41(6): 720-730. DOI:10.1007/s00254-001-0454-2
Esfandiary Darabad F, Rahimi M, Navidfar A, Mehrvarz A. 2020. Assessment of landslide sensitivity by neural network method and Vector machine algorithm (Case study: Heyran Road -Ardebil Province), Quantitative Geomorphological Researches, 9(3): 18-33. (In Persian). DOI:10.1016/j.jobe.2019.100853
Gholami M, Ghanavati E, Ahmadabadi A. 2019. Landslide susceptibility mapping of Kan using index of Entropy and LSM, Quantitative Geomorphological Researches, 8(1): 16-33. (In Persian). DOI:10.1016/j.catena.2012.05.005
Hallaji M, Asadi M, Amirahmadi A. 2020. An assessment of the landslide susceptibility prediction models in the Bar Watershed- Neyshabur, Whatershed Management Research, 33(127): 20-30. (In Persian).  10.22092/WMEJ.2019.126950.1241
Harmouzi H, Nefeslioglu, H. A, Rouai M, Sezer E. A, Dekayir A, Gokceoglu C. 2019. Landslide susceptibility mapping of the Mediterranean coastal zone of Morocco between Oued Laou and El Jebha using artificial neural networks (ANN). Arabian Journal of Geosciences, 12(22): 1-18.
Hemasinghe H, Rangali R. S, Deshapriya N. L, Samarakoon L. 2018. Landslide susceptibility mapping using logistic regression model (a case study in Badulla District, Sri Lanka). Procedia Engineering, 212(2): 1046-1053. https://doi.org/10.1016/j.proeng.2018.01.135
Heydari N, Habibnejad M, Kavian A, Pourghasemi H. 2020. Landslide susceptibility modelling using the Random Forest Machine Learning algorithm in the Watershed of Rais-Ali Delvari Reservoir, Whatershed Management Research, 33(126): 2-13. (In Persian). 10.22092/WMEJ.2019.126288.1219
Hijazi A, Ranjbarian Shadbad M. 2013. Identification of effective factors and zoning of landslide risk in the western part of Serand Chai watershed, Quantitative Geomorphology Researches, 313(1): 114-129. (In Persian).
   Hong H, Pradhan B, Xu C, Bui D. 2015. Spatial prediction of landslide hazard at the Yihuang area (China) using two-class kernel logistic regression, alternating decision tree and support vector machines. Catena, 133(2): 266-281. https://doi.org/10.1016/j.catena.2015.05.019Get rights and content
Karimi Sangchini E, Ownegh M, Saddodin A. 2012. Comparing applicability of 4 quantitative and semi-quantitative models in landslide hazard zonation in Chehel-Chay watershed, Golestan province, Water and Soil Conservation, pp. 19-32. (In Persian). 20.1001.1.23222069.1391.19.1.11.2
Kerekes A, Poszet S, Andrea GÁL. 2018. Landslide susceptibility assessment using the maximum entropy model in a sector of the Cluj–Napoca Municipality, Romania. Revista de Geomorfologie, 20(1): 130-146. DOI: https://doi.org/10.21094/rg.2018.039
Kim H.G, Lee D.K, Park C, Kil S., Son Y, and Park, J.H. 2015. Evaluating landslide hazards using RCP 4.5 and 8.5 scenarios. Environmental Earth Sciences, 73(3): 1385-1400.
Koohpayma A. 2016. Susceptibility zoning, landslide risk assessment and management (Case study: Lethyan Watershed). Ph.D. Thesis. Tehran University, Agriculture and Natural Resources Campus, Faculty of Natural Resources. Tehran Iran. pp. 1-189. (In Persian).
Kornejady A, Ownegh M,  Pourghasemi H, Bahremand A, Motamedi M. 2020. Landslide susceptibility prediction using the coupled Mahalanobis distance and machine learning models (Case study: Owghan Watershed, Golestan Province), Journal of Earth Science Researches, 11(42): 1-18. (In Persian).  10.52547/ESRJ.11.2.1
Kornejady A, Pourghasemi H. (2019). Landslide susceptibility assessment using data mining models, A case study: Chehel-Chai Basin, Journal of Watershed Engineering and Management, 11(1): 28-42. (In Persian).  https://doi.org/10.22092/ijwmse.2019.118436
Kornejady A. 2017. Assessing potential, danger, risk and preparation of landslide strategic management plan for Oghan watershed, Golestan province, Iran. Ph.D. Thesis. Gorgan University of Agricultural Sciences and Natural Resources, Faculty of Pasture and Watershed Management. Gorgan, Iran. pp. 1-154. (In Persian).
Kornejady A, Pourghasemi H.R, Afzali, S.F. 2019. Presentation of RFFR new ensemble model for landslide susceptibility assessment in Iran. In Landslides: Theory, Practice and Modelling .pp. 123-143.
Lee S, Hong S.M, Jung, H.S. 2017. A support vector machine for landslide susceptibility mapping in Gangwon Province, Korea. Sustainability, 9(1): 48-55.  https://doi.org/10.3390/su9010048
 Meten M, PrakashBhandary N, Yatabe, R. 2015. Effect of landslide factor combinations on the prediction accuracy of landslide susceptibility maps in the Blue Nile Gorge of Central Ethiopia. Geoenvironmental Disasters, 2(1): 1-17.
     Mohammadnia M, Fallah GH. 2018. Landslides susceptibility mapping using fuzzy logic and AHP, Journal of Applied Researches in Geographical Sciences, 18(48): 115-130. (In Persian). 20.1001.1.22287736.1397.18.48.2.3
Mohammady M, Pourghasemi H. 2017. Prioritization of landslide-conditioning factors and its landslide susceptibility mapping using Random Forest New Algorithm (Case study: A Part of Golestan Province), Journal of Watershed Management Research, 8(15): 161-170. (In Persian). doi:10.29252/jwmr.8.15.161
     Pandey V.K. Pourghasemi, H.R, Sharma, M.C. 2020. Landslide susceptibility mapping using maximum entropy and support vector machine models along the Highway Corridor, Garhwal Himalaya. Geocarto International, 35(2): 168-187. https://doi.org/10.1080/10106049.2018.1510038
     Peng L, Niu R, Huang B, Wu X, Zhao Y, Ye R. 2014. Landslide susceptibility mapping based on rough set theory and support vector machines: A case of the Three Gorges area, China. Geomorphology, 204: 287-301. https://doi.org/10.1016/j.geomorph.2013.08.013
Pham B.T, Pradhan B, Bui, D.T, Prakash I, Dholakia M.B. 2016. A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of Uttarakhand area (India). Environmental Modelling and Software, 84(1): 240-250. DOI:10.1016/j.envsoft.2016.07.005
Pourghasemi H.R, Rahmati O. 2018. Prediction of the landslide susceptibility: Which algorithm, which precision? Catena, 162(3): 177-192. https://doi.org/10.1016/j.catena.2017.11.022
Rabet A, Dastranj A, Asadi S, Asadi Nalivan O. 2020. Determination of groundwater potential using artificial neural network, Random Forest, Support Vector Machine and Linear Regression models (Case study: Lake Urmia Watershed), Iranian Journal of Eco Hydrology, 7(4): 1047-1060. (In Persian).
Rahmati O, Kornejady A, Samadi M, Nobre A.D, and Melesse A.M. 2018. Development of an automated GIS tool for reproducing the HAND terrain model. Environmental Modelling and Software, 102(2): 1-12. :10.1016/j.envsoft.2018.01.004
Rajabzadeh F, ghiasi S, Rahmati O. 2019. The performance of the maximum entropy algorithm and geographic information system in shallow landslide susceptibility assessment, Journal of Water and Soil Resources Conservation, 8(2): 57-74. (In Persian). 10.22069/JWSC.2022.19292.3478
Sevgen E, Kocaman S, Nefeslioglu H.A, Gokceoglu C. 2019. A novel performance assessment approach using photogrammetric techniques for landslide susceptibility mapping with logistic regression, ANN and random forest. Sensors, 19(18): 3940, 1-19. https://doi.org/10.3390/s19183940
Shano L, Raghuvanshi T. K, Meten, M. 2021. Landslide hazard zonation using Logistic Regression Model: The Case of Shafe and Baso Catchments, Gamo Highland, Southern Ethiopia. Geotechnical and Geological Engineering, pp. 1-19.
Shirani K, Naderi Samani R. 2022. Determination of effective factors and assessment of landslide susceptibility using random forest and artificial neural network in Doab Samsami Region, Chaharmahal va Bakhtiari Province, Whatershed Management Research, 35(134): 40-60. (In Persian). 10.22092/WMRJ.2021.354962.1421
Sun D, Xu J, Wen H, Wang D. 2021. Assessment of landslide susceptibility mapping based on Bayesian hyperparameter optimization: A comparison between logistic regression and random forest. Engineering Geology, 281: 59-72. https://doi.org/10.1016/j.enggeo.2020.105972
Talebi T, Goudarzi S, Pourghsemi H. 2018. Investigation of the possibility of landslide hazard mapping using the Random Forest algorithm (Case study: Sardarabad Watershed, Lorestan Province), Journal of Natural Environment Hazards, 7(16): 45-64. (In Persian).
Teimouri M, Asadi Nalivan O. 2020. Susceptibility zoning and prioritization of the factors affecting landslide using MaxEnt, geographic information system and remote sensing models (Case study: Lorestan Province), Hydrogeomorphology, 6(21): 155-179. (In Persian). 20.1001.1.23833254.1398.6.21.8.3
Tyagi A, Tiwari R.K, and James N. 2021. GIS-based landslide hazard zonation and risk studies using MCDM. In Local Site Effects and Ground Failures, Springer, Singapore. pp. 251-266.
Yao J, Qin S, Qiao S, Liu X, Zhang, Chen, J. 2022. Application of a two-step sampling strategy based on deep neural network for landslide susceptibility mapping. Bulletin of Engineering Geology and the Environment, 81(4): 1-20.
Yarahmadi J, Raushit Sh, Sharifikia M, Raushit. 2014. Identification and monitoring of domain instability by differential interferometric method, Case study: Garmi Chai Miane Watershed, Quantitative Geomorphology Researches, 3(4): 59- 44. (In Persian). 20.1001.1.22519424.1394.3.4.4.0
     Zhao L, Wu X, Niu R, Wang Y Zhang K. 2020. Using the rotation and random forest models of ensemble learning to predict landslide susceptibility. Geomatics, Natural Hazards and Risk, 11(1): 1542-1564. https://doi.org/10.1080/19475705.2020.1803421
Zhou X, Wen H, Zhang Y, Xu J, Zhang W. 2021. Landslide susceptibility mapping using hybrid random forest with GeoDetector and RFE for factor optimization. Geoscience Frontiers, 12(5): 1-19. https://doi.org/10.1016/j.gsf.2021.101211

Files

History

  • Receive Date: 01 March 2023
  • Revise Date: 19 June 2023
  • Accept Date: 21 September 2023

Share

How to cite

Statistics