Machine Learning Techniques for Landslide Susceptibility Mapping in Choman District, Iraq

Authors

DOI:

https://doi.org/10.23918/eajse.v10i3p1

Keywords:

Landslide, Geographic Information System, Machine Learning, Choman District

Abstract

The geographic information system (GIS) and remote sensing techniques used in this study with an integration of different machine learning techniques such as support vector machine (SVM), Random Forest and Decision Trees (RT), and K-Nearest Neighbor (KNN)  to generate accurate and reliable map of areas susceptible to landslides for Choman District in Kurdistan region of Iraq. Residents and infrastructures can be damaged dramatically by landslides, emphasizing the critical need for accurate susceptibility map of landslides for effective disaster management and risk mitigation procedures.  High resolution imagery from Google Earth Pro and field trips were used to collect historical landslide data to assess and validate the generated results. 14 different geological and environmental factors were considered as the primary contribution factors for landslides that used as to establish an effective susceptibility model. The research categorized Choman District into four vulnerability zones: very low, low, medium, and high susceptibility. The results highlighted that steep slope regions with proximity to geological faults and main roads are most vulnerable regions to landslides in Choman district. The results of landslide susceptibility mapping for SVM, RT, and KNN algorithms showed that 165.8 km2 (19.3%), 278.2 km2 (32.3%), 306.5 km2 (35.6%) of Choman District is highly susceptible to landslides, however, only 96.1 km2 (11.2%), 111.5 km2 (12.9%), and 182.8 km2 (21.2%) of Choman District were located in very low landslide susceptible areas. The area under the curve (AUC) were used to assess the accuracy of each machine learning techniques. AUC values for SVM, RT, and KNN techniques were 91.9%, 96.4% and 75%, respectively. The assessment indicated that SVM and RT showed better performance than KNN to generate the landslide susceptible areas. The results of this study provide valuable insights for urban planners and policy makers to perform sustainable planning and robust mitigation strategies.

References

[1] Al-Dhahi AD, Hussain AI, Al-Shwaily AK. Assessment of Landslide Susceptibility Using the AHP and GIS Techniques for the Zurbatiya Region, East of Iraq. The Iraqi Geological Journal. 2023:201-13. https://doi.org/10.46717/igj.56.2D.16ms-2023-10-22.

[2] Othman AA, Gloaguen R, Andreani L, Rahnama M. Landslide susceptibility mapping in Mawat area, Kurdistan Region, NE Iraq: a comparison of different statistical models. Nat Hazards Earth Syst Sci Discuss. 2015;2015:1789-833. https://doi.org/10.5194/nhessd-3-1789-2015.

[3] Othman AA, Gloaguen R. Automatic extraction and size distribution of landslides in Kurdistan region, NE Iraq. Remote Sensing. 2013;5(5):2389-410. https://doi.org/10.3390/rs5052389.

[4] Rudaw. Erbil2024 [Available from: https://www.rudaw.net/sorani/kurdistan/1601201618.

[5] Qallam. 2024 [Available from: https://qallam.net/posts/14187.

[6] Kurdiu. Erbil2023 [Available from: https://www.kurdiu.org/ku/b/527004.

[7] Rudaw. 2023 [Available from: https://www.rudaw.net/english/kurdistan/200520231.

[8] Fatah KK, Mustafa YT, Hassan IO. Geoinformatics-based frequency ratio, analytic hierarchy process and hybrid models for landslide susceptibility zonation in Kurdistan Region, Northern Iraq. Environment, Development and Sustainability. 2024;26(3):6977-7014. https://doi.org/10.1007/s10668-023-02995-7.

[9] Othman AA, Al-Jaff AU, Al-Manmi DA, Al-Maamar AF. Landslide susceptibility mapping using remote sensing and GIS application: A case study in Qala Diza and surrounding area, Kurdistan region, NE Iraq. Iraqi Bulletin of Geology and Mining. 2018;14(1):65-90.

[10] Abedini M, Ghasemyan B, Rezaei Mogaddam M. Landslide susceptibility mapping in Bijar city, Kurdistan Province, Iran: a comparative study by logistic regression and AHP models. Environmental earth sciences. 2017;76:1-14. https://doi.org/10.1007/s12665-017-6502-3.

[11] Gov.org. Hawler gov; 2024 [Available from: https://www.hawlergov.org/app/en/node/387.

[12] Pro GE. 2024 [Available from: https://www.google.com/earth/about/versions/.

[13] Buringh P, cartographer Exploratory soil map of Iraq. Bagdad: Ministry of Agriculture, Directorate General of Agricultural Research and Projects, Division of Soils and Agricultural Chemistry.; 1957. https://esdac.jrc.ec.europa.eu/content/exploratory-soil-map-iraq-map-1.

[14] Stevanovic ZM, M. Hydrogeology of Northern Iraq, Climate, Hydrology, Geomorphology & Geology. FAO. 2003;1:1–122

[15] Shano L, Raghuvanshi TK, Meten M. Landslide susceptibility evaluation and hazard zonation techniques – a review. Geoenvironmental Disasters. 2020;7(1):18 https://doi.org/10.1186/s40677-020-00152-0.

[16] Barman J, Soren DDL, Biswas B. Landslide Susceptibility Evaluation and Analysis: A Review on Articles Published During 2000 to 2020. In: Das J, Bhattacharya SK, editors. Monitoring and Managing Multi-hazards: A Multidisciplinary Approach. Cham: Springer International Publishing; 2023. p. 211-20. https://doi.org/10.1007/978-3-031-15377-8_14.

[17] Sujatha ER, Sudharsan JS. Landslide Susceptibility Mapping Methods—A Review. In: Panda GK, Shaw R, Pal SC, Chatterjee U, Saha A, editors. Landslide: Susceptibility, Risk Assessment and Sustainability: Application of Geostatistical and Geospatial Modeling. Cham: Springer Nature Switzerland; 2024. p. 87-102. https://doi.org/10.1007/978-3-031-56591-5_4.

[18] Adnan MSG, Rahman MS, Ahmed N, Ahmed B, Rabbi MF, Rahman RM. Improving spatial agreement in machine learning-based landslide susceptibility mapping. Remote Sensing. 2020;12(20):3347. https://doi.org/10.3390/rs12203347.

[19] Ganesh B, Vincent S, Pathan S, Benitez SRG. Integration of GIS and machine learning techniques for mapping the landslide-prone areas in the state of Goa, India. Journal of the Indian Society of Remote Sensing. 2023;51(7):1479-91. https://doi.org/10.1007/s12524-023-01707-y.

[20] Wang Z, Liu Q, Liu Y. Mapping landslide susceptibility using machine learning algorithms and GIS: A case study in Shexian County, Anhui Province, China. Symmetry. 2020;12(12):1954. https://doi.org/10.3390/sym12121954.

[21] Benmakhlouf M, El Kharim Y, Galindo Zaldívar J, Sahrane R. Landslide susceptibility assessment in western external rif chain using machine learning methods. 2023. https://doi.org/10.28991/CEJ-2023-09-12-018.

[22] Rabby YW, Hossain MB, Abedin J. Landslide susceptibility mapping in three Upazilas of Rangamati hill district Bangladesh: application and comparison of GIS-based machine learning methods. Geocarto International. 2022;37(12):3371-96. https://doi.org/10.1080/10106049.2020.1864026.

[23] Huang W, Ding M, Li Z, Zhuang J, Yang J, Li X, et al. An efficient user-friendly integration tool for landslide susceptibility mapping based on support vector machines: SVM-LSM toolbox. Remote Sensing. 2022;14(14):3408. https://doi.org/10.3390/rs14143408.

[24] Edrich A-K, Yildiz A, Roscher R, Bast A, Graf F, Kowalski J. A modular framework for FAIR shallow landslide susceptibility mapping based on machine learning. Natural Hazards. 2024:1-30. https://doi.org/10.1007/s11069-024-06563-8.

[25] Xing Y, Chen Y, Wang P, Huang S, Xiang Y. Research on landslide master control factor identification and susceptibility prediction modelling. EGUsphere. 2024;2024:1-24. https://doi.org/10.5194/egusphere-2023-3134, 2024.

[26] Liu H, Ding Q, Yang X, Liu Q, Deng M, Gui R. A Knowledge-Guided Approach for Landslide Susceptibility Mapping Using Convolutional Neural Network and Graph Contrastive Learning. Sustainability. 2024;16(11):4547. https://doi.org/10.3390/su16114547.

[27] Huang Y, Zhao L. Review on landslide susceptibility mapping using support vector machines. Catena. 2018;165:520-9. https://doi.org/10.1016/j.catena.2018.03.003.

[28] MOHAPATRA R. Landslide susceptibility modelling in a part of Himachal Pradesh, India: An integrated method based on machine learning and geospatial techniques. Nova Geodesia. 2023;3(1):63-. https://doi.org/10.55779/ng3163.

[29] Shahabi H, Ahmadi R, Alizadeh M, Hashim M, Al-Ansari N, Shirzadi A, et al. Landslide susceptibility mapping in a mountainous area using machine learning algorithms. Remote Sensing. 2023;15(12):3112. https://doi.org/10.3390/rs15123112.

[30] Tien Bui D, Shirzadi A, Shahabi H, Geertsema M, Omidvar E, Clague JJ, et al. New ensemble models for shallow landslide susceptibility modeling in a semi-arid watershed. Forests. 2019;10(9):743. https://doi.org/10.3390/f10090743.

[31] Cristina Dias H, Henrique Sandre L, Satizábal Alarcón DA, Henrique Grohmann C, Alberto Quintanilha J. Landslide recognition using SVM, Random Forest, and Maximum Likelihood classifiers on high-resolution satellite images: A case study of Itaóca, southeastern Brazil. Revista Brasileira de Geociências. 2021;51(4). https://doi.org/10.1590/2317-4889202120200105.

[32] Sharma A, Prakash C, Manivasagam V. Entropy-based hybrid integration of random forest and support vector machine for landslide susceptibility analysis. Geomatics. 2021;1(4):399-416. https://doi.org/10.3390/geomatics1040023.

[33] Nhu V-H, Shirzadi A, Shahabi H, Singh SK, Al-Ansari N, Clague JJ, et al. Shallow landslide susceptibility mapping: A comparison between logistic model tree, logistic regression, naïve bayes tree, artificial neural network, and support vector machine algorithms. International journal of environmental research and public health. 2020;17(8):2749. https://doi.org/10.3390/ijerph17082749.

[34] Pradhan B. A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS. Computers & Geosciences. 2013;51:350-65. https://doi.org/10.1016/j.cageo.2012.08.023.

[35] Jari A, Khaddari A, Hajaj S, Bachaoui EM, Mohammedi S, Jellouli A, et al. Landslide susceptibility mapping using multi-criteria decision-making (MCDM), statistical, and machine learning models in the Aube Department, France. Earth. 2023;4(3):698-713. https://doi.org/10.3390/earth4030037.

Downloads

Published

2024-12-09

Data Availability Statement

Data will be available upon reasonable request.

Issue

Section

Articles

Categories

How to Cite

Chomani, K. (2024). Machine Learning Techniques for Landslide Susceptibility Mapping in Choman District, Iraq. EURASIAN JOURNAL OF SCIENCE AND ENGINEERING, 10(3), 1-13. https://doi.org/10.23918/eajse.v10i3p1

Similar Articles

1-10 of 106

You may also start an advanced similarity search for this article.