Related Links
Spatial modeling of landslides in Khorasan Razavi Province using machine learning methods | ||
| مهندسی و مدیریت آبخیز | ||
| Article 4, Volume 16, Issue 3, September 2024, Pages 378-393 PDF (4.42 M) | ||
| Document Type: Research Paper | ||
| DOI: 10.22092/ijwmse.2024.360481.1997 | ||
| Authors | ||
| Malihe Mohamadnia* 1; Abolghasem Amirahmadi2; Liela Goli Mokhtari3 | ||
| 1PhD in Geomorphology, Department of Geography, Faculty of Geography and Environmental Sciences, Hakim Sabzevari University, Sabzevar, Iran | ||
| 2Professor, Department of Geography, Faculty of Geography and Environmental Sciences, Hakim Sabzevari University, Sabzevar, Iran | ||
| 3Assistant Professor, Department of Geography, Faculty of Geography and Environmental Sciences, Hakim Sabzevari University, Sabzevar, Iran | ||
| Abstract | ||
| Introduction Humanity is facing many environmental challenges. Natural disasters are among these problems, causing the death and injury of hundreds of thousands of people and rendering millions homeless worldwide every year. Geomorphological hazards, particularly mass movements and landslides, are considered some of the most potentially harmful phenomena. Mass movement refers to the outward or downward movement of domain-forming materials under the influence of gravity. These movements are primarily triggered by gravity, natural factors such as heavy rainfall, earthquakes, and soil saturation with water, as well as human activities like deforestation and improper engineering operations. According to the 2012 World Natural Hazards Report, landslides were ranked among the seven most dangerous natural disasters globally. The occurrence of natural hazards, including landslides, exerts considerable pressure on the economic development of countries, especially in developing regions, with financial damages hindering economic growth and prosperity. Iran, with its mountainous terrain, high tectonic and seismic activity, and diverse geological and climatic conditions, has created natural conditions conducive to a wide range of landslides. Materials and Methods The aim of this study is to spatially model landslide susceptibility using machine learning techniques, including random forest, support vector machine, and enhanced regression tree, in Razavi Khorasan province. Initially, the distribution map of landslides in the region was prepared through field visits and data from the national landslides database. In the next step, 70% of the identified landslides were used for model development, while 30% were reserved for model evaluation. The information layers for altitude, slope, slope direction, distance from waterway, waterway density, distance from roads, distance from faults, land use, vegetation index, surface curvature, profile curvature, precipitation, and selected lithological units were prepared and mapped using ArcGIS. Results and Discussion Prioritization of the factors affecting landslide occurrence using the random forest model showed that precipitation and altitude had the greatest impact on landslides in the study area. Additionally, the evaluation of the machine learning models using the relative operating characteristic (ROC) curve indicated that the landslide potential map generated by the random forest method had the highest accuracy (0.97). Based on this map, more than 25% of the area was classified into high and very high-risk zones. Conclusion This map can assist environmental planners in construction projects and help prevent land-use changes and construction in high-risk areas. Additionally, public awareness campaigns can reduce harmful human activities in these zones. While controlling landslides may not always be feasible or is often very expensive, proper management can help mitigate or reduce risks. By identifying the key factors in mass movement occurrences and zoning the areas accordingly, it is hoped that this research will contribute to the development of effective risk management plans and reduce the damage caused by landslides. | ||
| Keywords | ||
| Geographic information system; Mass movements; Random forest model; Risk; Susceptibility map | ||
| References | ||
|
Alipour, H., Malekian, A., 2014. Landslide risk zoning in Jahan Esfrain Watershed, North Khorasan. Geograph. Develop. Quart. 39, 165-180 (in Persian). Afifi, M.A., 2021. Spatial analysis of landslide risk with emphasis on geomorphological factors using random forest model, case study: Larestan city in Fars Province. Quart. J. Nat. Geograph. 14, 39-53 (in Persian). Brardinoni, F., Slaymaker, O., Hassan, M.A., 2003. Landslide inventory in a rugged forested watershed: a comparison between air-photo and field survey data. Geomorphol. 54, 179-196. Breiman, L., 2001. Random forests. Machine Learning 45, 5-32. Ebrahimkhani, S., Afzali, M., Shokohi, A., 2018. Forecasting and investigating factors of road accidents using data mining algorithms. Zanjan Police Sci. Quart. 1, 111-127 (in Persian). Ebrahimi, M., Habibullahian, M., Amir Ahmadi, A., Zanganeh Asadi, M.A., Nejad-Solimani, A., 2014. Investigating the effect of road construction on the occurrence of surface landslides using the slope stability model. Case study: Kalat Watershed. J. Geograph. Survey Space. 15, 143-156 (in Persian). Elith, J., 2006. Novel methods improve prediction of species’ distributions from occurrence data. Ecograph. Emendo, J., Gonzales, A., Teran, J., Cendrero, A., Fabbri, A., Chung, A., 2003. Validation of landslide susceptibility maps, examples and applications from a case study in northern Spain. Nat. Hazard 14, 437-449. Erner, A., Sebnem, H., Duzgun, A., 2012. Improvement of statistical landslide susceptibility mapping by using spatial and global regression methods in the case of more and Romsdal (Norway). Landslides 7, 55-68. Farshad, M., Sadeh, J., 2013. Locating short circuit fault in high voltage direct current transmission lines using neural network, generalized regression and random forest algorithm. Intelligent Syst. Electri. Engineer. 4,1-14 (in Persian). Fell, R., Corominas, J., Bonnard, Ch., Cascini, L., Leroi, E., Savage, Z.S., 2008. Guidelines for lanslide susceptibility, hazard and risk zoning for land use planning. Engineer. Geol. 102, 85-98. Fatemi Aqda, M., Ghoumian, J., Eshqli Farahani, A., 2012, Evaluation of the efficiency of statistical methods in determining the landslide risk potential. Earth Sci. Quart. 7, 1-17. Goli Mokhtari, L., Naimi Tabar, M., 2022. Spatial modeling and prediction of landslide risk using advanced data mining algorithms, case study: Kalat City. Quantit. Geomorphol. Res. 40, 116-137 (in Persian). Guzzetti, F., 2000. Landslide fatalities and the evaluation of landslide risk in Italy. Engineer. Geol. 58, 89-107. Hong, H., Naghibi, S.A., Pourghasemi, H.R., Pradhan, B., 2016. GIS-based landslide spatial modeling in Ganzhou City, China. Arab. J. Geosci. 9, 112. Karam, A., Bahramabadi, A., Pakenjad, F., 2020. Instability zoning of slopes with respect to landslide movements using random forest algorithm, case study: Tangrah basin of Golestan Province. J. Quantit. Geomorphol. Res. 36, 59-74 (in Persian). Kint, V., 2012. Forest structure and soil fertility determine internal stem morphology of Pedunculate oak: A modelling approach using boosted regression trees. Eur. J. For. Res. 131, 609-622 . Kumar Dahal, R., 2008. Predictive modeling of rainfall-induced landslide in the lesser Himalaya of Nepal based on weights of evidence. Geomorphol. 102, 496-510. Komac, M., 2006. A landslide susceptibility model using the analytical hierarchy process method and multivariate statistics in perialpine Slovenia. Geomorphol. 74, 17-28. Karimi, H., Naderi, F.A., Morshidi, A., Nik Sarasht, M., 2013. Landslide risk zoning in the Cherdavel watershed of Ilam using geographic information system. Appl. Geol. Quart. 4, 319-332. Kornejad, A., Ong, M., Pourqasmi, H.R., Behermand, A., Motamedi, M., 2019. Landslide susceptibility prediction using mahalanobis distance and machine learning, case study: Oghan Watershed, Golestan Province. Earth Sci. Res. 42, 1-18 (in Persian). Madadi, A., Ghafari Gilande, A., Pirouzi, A., 2014. Evaluation and zoning of landslide risk using Vicor model, case study: Aq Lakhan Chai Watershed. Quantita. Geomorphol. Res. 4, 124- 141 (in Persian). Mahmoudi, F.A., 2007. Dynamic Geomorphology, second edition. Payam Noor Publishing House, 283 pages (in Persian). Mohammadnia, M., Amir Ahmadi, A., Bahrami, S., 2016. Application of weighted evidence model in landslide susceptibility assessment using geographic information system technology, case study: Abkhaz-Jaghregh Basin. Geographi. Res. Quart. 2, 151-137 (in Persian). Mohammadnia, M., Amirahmadi, A., Bahrami, S., Akbari, A., 2016. Landslide risk zoning in Jagharq and Darroud basins (the new proposed route of Tarqabeh-Darroud). Geograph. Space Quart. 55, 217- 238 (in Persian). Mohammadi, M., Pourqasmi, H.R., 2016. Prioritization of factors affecting the occurrence of landslides and preparation of its sensitivity map using the new random forest algorithm, case study: a part of Golestan Province. Watershed Manage. Res. J. 15, 161-170 (in Persian). Mosavi Baigi, M., Ashraf, B., 2012. The study of synoptic patterns leading to autumn and winter droughts in Razavi Khorasan province. J. Water Soil Conserv. Res. 18, 167-183. Mirsanei, R., Kardan, R.A., 2008. Analytical view on landslide features in the country. Proceedings of The First Conference on Environmental Engineering Geology of Iran, Tarbiat Moalem University, Tehran (in Persian). Niazi, Y.M., Ekhtesasi, A., Talebi, S., Mokhtari, M.H., 2010. Performance evaluation of two multivariate statistical model to predict landslide hazard (case study: Ilam). J. Sci. Watershed Engineer. Iran. 10, 9-20 (in Persian). Naghibi, S.A., Pourghasemi, H.R., Dixon, B., 2016. GIS- based groundwater potential mapping using boosted regression tree, classification and regression tree, and random forest machine learning models in Iran. Environ. Monitor. Assess. 44, 1-27 (in Persian). Tien Bui, D., Tuan, T.A., Klempe, H., Pradhan, B., Revhaug, L., 2016. 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 13, 361-378. Paoletti, V., Tarallo, D., Matano, F., Rapolla, A., 2013. Level-2 susceptibility zoning on seismicinducedlandslides: An application to Sannio and Irpinia areas. SouthernItaly. Physic. Chemist. Earth. 63, 147-159. Nicodemus, K.K., 2011. Letter to the editor: on the stability and ranking of predictors from random forest variable importance measures. Brief. Bioinform. 12, 369-373. Pourghasemi, H.R., Goli Jirandeh, A., Pradhan, B., Xu, C., Gokceoglu, C., 2013 Landslide susceptibility mapping using support vector machine and GIS. J. Earth Syst. Sci.e 122 (2), 349-369 (in Persian). Pourghasemi, H.R., Mohammadi, M., Pradhan, B., 2012. Landslide susceptibility mapping using index of entropy and conditional probability models in GIS: Safarood Basin, Iran, Catena 97, 71-84. Porhashmi, S., Amir Ahmadi, A., Akbari, A., 2014. Modeling and estimating the volume of landslide zones based on area (case study: Baqi Neishabur basin). Geograph. Environ. Plan. Year 2026. 59, 81-98 (in Persian). Rajabi, M., Rezai Moghadam, M.H., Keshavarz, A., 2022. Quantitative analysis of landslide risk and its zoning in Alamut River basin using logistic regression method. Geograph. Space Quart. 77, 1-14 (in Persian). Shekari Badi, A., Motamedi Rad, M., Mohammadnia, M., 2014. Combining ANP model and shannon entropy index in estimating factors affecting the occurrence and zoning of landslide risk, case study: Faroub Roman Neishabur Basin. Region. Geographi. Studies Quarter. Dry 22, 89-103 (in Persian). Saberchanari, K., Salmani, H., Mohammadi, M., 2014. Landslide risk assessment using information value models and LNRF. Ecohydrol. 2(1), 105-116 (in Persian). Vapnik, V.N., 1995. The nature of statistical learning theory. New York: Springer Verlag. Vittorio De Blasio, F., 2011. Introduction to the physics of landslides. Springer. Xu, C., Dai, F., Xu, X., Lee, Y.H., 2012. GIS-basedsupport vector machin modeling of earthquake triggered-landslide susceptibility in the Jianjiang River Watershed China. Geomorphol. 8,146-145. Yesilnacar, E.K., Pourghasemi, H.R., Pourtaghi, Z.S., 2005. The application of computational intelligence to landslide susceptibility mapping in Turkey. Ph.D Thesis, Department of Geomatics the University of Melbourne, 423 pages. Youssef, A.M., 2015. Landslide susceptibility delineation in the Ar-Rayth Area, Jizan, Kingdom of Saudi Arabia, by using analytical hierarchy process, frequency ratio and logistic regression models. Environ. Earth Sci. 8, 39-56. | ||
|
Statistics Article View: 380 PDF Download: 161 |
||
Journal management system. designed by sinaweb