کاربرد DEMATEL-AHP و SVM در شناسایی مناطق مستعد سیلاب (مطالعه موردی: حوزه آبخیز برزک کاشان)

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانش آموخته کارشناسی ارشد علوم و مهندسی آبخیز، گروه مهندسی طبیعت، دانشکده منابع طبیعی و علوم زمین، دانشگاه کاشان، کاشان، ایران

2 دانشیار علوم و مهندسی آبخیزداری؛ نویسنده مسئول، گروه مهندسی طبیعت، دانشکده منابع طبیعی و علوم زمین، دانشگاه کاشان، کاشان، ایران

10.22059/ijswr.2024.377663.669724

چکیده

سیل، از جمله فراوانترین و پرهزینهترین حوادث طبیعی محسوب میشود و خسارات مالی و جانی ناشـی از آن هر سال گستره‌ای از کشورها بهویژه کشور ایران را تحت‌تأثیر قرار می‌دهد. لذا یکی از زمینههای پژوهش برای کنترل خطرات سیل، شناسایی نقاط بحرانی منطقه است. به همین دلیل هدف از  پژوهش حاضر، شناسایی مناطق مستعد سیل در حوزه آبخیز برزک کاشان با استفاده از مدل‌های DEMATEL-AHP و SVM است. برای این منظور طی بازدیدهای صحرایی صورت گرفته، 100 نقطه سیل‌گیر شناسایی و ثبت شدند. در ادامه، 12 عامل مؤثر بر وقوع سیل شامل بارش، زمین‌شناسی، کاربری اراضی، فاصله از آبراهه، شیب، تراکم زهکشی، شاخص موقعیت توپوگرافی، شاخص رطوبت توپوگرافی، شاخص زبری توپوگرافی، شاخص قدرت جریان، شماره منحنی و ضریب رواناب به‌منظور تهیه نقشه مناطق مستعد سیل‌خیزی انتخاب شدند و لایه‌های آن‌ها در محیط نرم‌افزارهای ArcGIS 10.7.1 و SAGA GIS تهیه شدند. نتایج نشان داد که مؤلفه بارش با بیشترین وزن معادل 211/0، مؤثرترین متغیر بر سیل‌خیزی است. همچنین ضریب رواناب، تأثیرپذیرترین عامل است و بیشترین ارتباط را با دیگر عوامل دارد. همچنین با توجه به سطح زیر منحنی ROC (859/0=AUC)، کارایی مدل AHP بسیار خوب ارزیابی شد. میزان دقت پیش‌بینی مدل‌ SVM نیز در مرحله اعتبارسنجی، خوب (751/0) بوده است. نقشه مناطق مستعد سیل نیز نشان داد که مناطق شمال، شمال غرب و غرب حوزه آبخیز برزک دارای بیشترین پتانسیل در وقوع سیل و سیل‌خیزی هستند. درنتیجه، نتایج پژوهش حاضر می‌تواند به‌عنوان نقشه راهی برای مدیران و سیاست‌گذاران به‌منظور مدیریت سیلاب قرار گیرد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Application of DEMATEL-AHP and SVM in identifying flood-prone areas (Case study: Barzak-e-Kashan basin)

نویسندگان [English]

  • Seyyedeh Faezeh Lahoutinasab 1
  • Hoda Ghasemieh 2
1 2- Associate Professor of Watershed Sciences and Engineering & Corresponding Author, Department of Natural Engineering, Faculty of Natural Resources and Earth Sciences, Kashan University of Kashan, Kashan, Iran.
2 2- Associate Professor of Watershed Sciences and Engineering & Corresponding Author, Department of Natural Engineering, Faculty of Natural Resources and Earth Sciences, Kashan University of Kashan, Kashan, Iran.
چکیده [English]

Flood is one of the most frequent and costly natural disasters, and the financial and human losses caused by it every year affect a wide range of countries, especially Iran. Therefore, one of the fields of research to control flood risks is to identify the flooding points of the region. For this reason, the aim of the current research is to identify flood-prone areas in Barzak-e-Kashan basin using DEMATEL-AHP and SVM models. For this purpose, 100 flooding points were identified and recorded during field visits. In the following, 12 factors affecting the occurrence of flood including precipitation, lithology, land use, distance from stream, slope, drainage density, topographic position index, topographic wetness index, topographic roughness index, stream power index, curve number and runoff coefficient were selected for preparing maps of flood-prone areas and their layers were prepared in ArcGIS 10.7.1 and SAGA GIS softwares’ environment. The results showed that the precipitation component with the highest weight equal to 0.211 is the most effective variable on flooding and the runoff coefficient is the most influential factor and has the most relationship with other factors. Also, according to AUC=0.859, the AHP efficiency was evaluated very well and the SVM accuracy was good (AUC= 0.751) in validation phase. The map of flood-prone area also showed that the north, northwest, and west lands of Barzak basin have the highest potential for flooding. The results of the present research can be used as a road map for managers and policy makers to manage flood.

کلیدواژه‌ها [English]

  • Rainfall
  • Barzak
  • Multi-criteria decision making
  • Data mining
  • Flood

EXTENDED ABSTRACT

 

Introduction

Flood is one of the most frequent and costly natural disasters and their frequency has been on the rise in recent years not only in developing countries, but also worldwide. The financial, economic and human losses caused by flood every year affect a wide range of countries, particularly Iran. Therefore, one of the research fields to control and mitigate flood risks is the identification of flood-prone areas in the region.

Research Method

For this reason, the aim of the current research is to identify flood-prone areas in the Barzak-e-Kashan basin using the DEMATEL-AHP and SVM models.

Research Method

For this purpose, 100 flooding points were identified and recorded during field visits. In the following, 12 factors affecting the occurrence of flood including precipitation, lithology, land use, distance from the stream, slope, drainage density, topographic position index (TPI), topographic wetness index (TWI), topographic roughness index (TRI), stream power index (SPI), curve number and runoff coefficient were selected for preparing maps of flood-prone areas and their layers were prepared in ArcGIS 10.7.1 and SAGA GIS software environment.

Results and Discussion

According to the results obtained from the implementation of the AHP model, the factors affecting flooding, are ranked in order from the lowest to the highest weight as follows, the stream power index (0.013), topographic roughness index (0.014), topographic wetness index (0.018), topographic position index (0.019), drainage density (0.056), slope (0.063), distance from the stream (0.083), land use (0.094), runoff coefficient (0.124), curve number (0.147), lithology (0.159) and precipitation (0.211). This indicates that precipitation component with the weight to 0.211 is the most influential variable on flooding. The results of the DEMATEL method also support this, showing that precipitation with the highest weight (0.211) is the most effective and influential parameter among other components. Additionally, the runoff coefficient with the weight equal to 0.124 is the most influential and has the most relationship with other factors. Also, according to the area under the ROC curve (AUC=0.859), the AHP model was evaluated to be very well and efficient in the validation stage. Also, the SVM accuracy was good (AUC= 0.751) in validation phase. The final flood zoning maps of Barzak basin using AHP and SVM models also confirm that the southern, southwestern, and southeastern parts of the basin have low to very low sensitivity to flooding, while the northern, northwest and west parts have moderate to very high sensitivity to flooding.

Conclusion

Flood is one of the most important natural crises. This phenomenon causes soil erosion, and landslide and has destructive effects on the environment for which a solution must be found. To prevent the harmful effects of flood, changes cannot be made in atmospheric factors and elements, and a scientific and principled solution must be found for it in basins. One of the ways to control flood risks is to identify flood critical points and the necessity of land use management, because the lack of sufficient knowledge of flood critical points leads to mismanagement and heavy financial and human losses because of flood. Therefore, it is essential to prepare a zoning map and determine potential flood areas in basins, especially study basin. As a result, the findings of this research can be used as a road map for executive managers and urban policymakers to manage flood.

Author Contributions

Conceptualization, Ghasemieh. H.; methodology, Lahoutinasab, S.F. and Ghasemieh. H.; software, Lahoutinaseb. S.F.; validation, Lahoutinasab, S.F. and Ghasemieh. H.; formal analysis, Lahoutinasab, S.F. and Ghasemieh. H.; investigation, Lahoutinasab, S.F. and Ghasemieh. H.; resources, Lahoutinasab, S.F. and Ghasemieh. H.; data curation, Lahoutinasab, S.F.; writing—original draft preparation, Lahoutinasab, S.F.; writing—review and editing, Ghasemieh. H.; visualization, Ghasemieh. H.; supervision, Ghasemieh. H.; project administration, Ghasemieh. H.; funding acquisition, Ghasemieh. H. All authors have read and agreed to the published version of the manuscript.

Data Availability Statement

Data is available on reasonable request from the authors.

Acknowledgements

The authors would like to thank the reviewers and editor for their critical comments that helped to improve the paper.

Ethical considerations

The authors avoided data fabrication, falsification, plagiarism, and misconduct.

Conflict of interest

 

The author declares no conflict of interest.

مراجع

Alfieri, L., Salamon, P., Bianchi, A., Neal, J., Bates, P., & Feyen, L. (2014). Advances in Pan‐European flood hazard mapping. Hydrological processes, 28(13), 4067-4077.
Amiri, M., Pourghasemi, H., & Arabameri, A. (2018). Prioritization of flood inundation sub-watersheds of Maharlo watershed in Fars province using morphometric parameters and VIKOR decision making model. Iranian journal of Ecohydrology, 5(3), 813-827. (In Persian)
Banihabib, M.E., & Laghabdoost Arani, A. (2014). Flood management options using analytical hierarchy process and Evaluation and Mixed Criteria. Irrigation and Water Engineering, 4(2), 72-82. (In Persian)
Bera, S., Das, A., & Mazumdre, T., (2022). Evaluation of machine learning, information theory and multi-criteria decision analysis methods for flood susceptibility mapping under varying spatial scale of analyses. Society and Environment, 25, 100686.
Bouahim, S., Rhazi, L., Amami, B., Sahib, N., Rhazi, M., Waterkeyn, A., Zouahri, A Mesleard, F., Muller, S.D., & Grillas, P. (2010). Impact of grazing on the species richness of plant communities in Mediterranean temporary pool (western Morocco). Determining appropriate sample size in survey research, Information Comptes Rendus Bioloies, 333, 670-679.
Cheraghi Ghalehsari, A., Habibnejad Roshan, M., & Roshun, S.H. (2020). Flood susceptibility mapping using a Support Vector Machine models (SVM) and Geographic Information System (GIS). Journal of Natural Environmental Hazards, 9(25), 61-80. (In Persian)
Chukwuma, E.C., Okonkwa, C.C., Ojediran, J.O., Anizoba, D.C., Ubah, J.I., & Nwachukwu, C.P. (2021). A GIS based flood vulnerability modelling of Anambra State using an integrated IVFRN-DEMATEL-ANP model. Heliyon, 7(9), 1-13, e08048.
Cimren, E., Catay, E., & Budak, E. (2007) Development of a machine tool selection system using AHP. The International Journal of Advanced Manufacturing Technology, 35(3-4), 363-376. 
Costache, R., Popa, M.C., Bui, D.T., Diaconu, D.C., Ciubotaru, N., Minea, G., &bPham, Q.B. (2020). Spatial predicting of flood potential areas using novel hybridizations of fuzzy decision-making, bivariate statistics, and machine learning. Journal of Hydrology, 585, 124808.
Farhadi, H., Esmaeily, A., & Najafzadeh, M. (2021). Developing a Decision Tree based on data mining method for detecting the influential parameters on the power of flood destruction. Amirkabir Journal of Civil Engineering, 53(5), 1763-1780. (In Persian)
Fathollahzadeh, S., & Mehdizadeh, R. (2013). An overview of multi-criteria decision-making methods. The National Conference on Modern Management Sciences, Hakim Jorjani Institute of Higher Education, Gorgan. (In Persian)
Ghasemi, A., Salajegheh, A., Malekian, A., & Esmaliouri, A. (2014). Investigation of flooding and causative factors in Balegli Chay watershed by GIS, RS, and AHP techniques. Journal of Environmental Studies, 40(2), 389-400. (In Persian)
Ghorbaninejad, S., & Zeinivand, H. (2022). Identification of the most important parameters influencing flood occurrence and flooding priority in Kakareza watershed using Shannon entropy and TOPSIS method. Journal of Arid Regions Geographic Studies, 11(42), 95-109. (In Persian)
Ghosh, S., Saha, S., & Bera, B. (2022). Flood susceptibility zonation using advanced ensemble machine learning models within Himalayan foreland basin. Natural Hazards Research, 2(4), 363-374.
Habibnejad Roshan, M., Shahedi, K., & Roshun, S.H. (2023). Identification and prioritization of flooding areas using GIS-based analytical hierarchy process, Case study: Karun Watershed. Watershed Engineering and Management, 15(3), 367-385. (In Persian)
Han, D., Chan, L., & Zhu, N. (2007). Flood forecasting using support vector machines. Journal of hydroinformatics, 9(4): 267-276.
Hosseinzadeh, M.M., Panahi, R., & Tarband, T. (2020). Flood susceptibility zoning in the Sanghar basin, Kermanshah province. Iranian journal of Ecohydrology, 7(4), 873-889. (In Persian)
Ishizaka, A., & Nemery, P. (2013). A multi-criteria group decision framework for partner grouping when sharing facilities. Group Decision and Negotiation, 22, 773-799.
Karami, M., Abedi Koupai, J., & Gohari, S.A. (2024). Integration of SWAT, SDSM, AHP, and TOPSIS to detect flood-prone areas. Natural Hazards, 120(7), 1-19.
Kumar, V., Sharma, K.V., Caloieero, T., Mehta, D., J., & Singh, K. (2023). Comprehensive overview of flood modeling approaches: A review of recent advances. Hydrology, 10(7), 141, 1-32.
Lahoutinasab, F. (2023). Application of Maximum Entropy, Support Vector Machine and DEMATEL-AHP models in identifying flood-prone areas (Case study: Barzak basin). MSc thesis, Faculty of Natural Resources and Earth Sciences, University of Kashan, 167 pp. (In Persian)
Mohamadi, G., Borna, R., & Asadian, F. (2021). Analysis of flood potential of Ghare-Su basin in Kermanshah province. Journal of Geography and Environmental Hazards, 9(4), 1-23. (In Persian)
Mojaddadi Rizeei, H., Habibnezhad Roshan, M., Shahedi, K., & Pradhan, B. (2020). The efficiency of an ensemble Frequency Ratio-Support Vector Machine model in the detection of flood-prone areas of the Kalat Basin. Iranian journal of Ecohydrology, 7(1), 77-95. (In Persian)
Mojaddadi, H.R., Pradhan B., Nampak H., Ahmad, N., & Ghazali, A.H.B. (2017). Ensemble machine-learning-based geospatial approach for flood risk assessment using multi-sensor remote-sensing data and GIS. Geomatics, Natural Hazards and Risk, 8(2), 1080–1102.
Mosavi, S., Negahban, S., Rakhshaninasab, H., & Hossainzadeh, S. (2016). Assessment and zoning flood risk by using Fuzzy logic TOPSIS in GIS (Case study: Baghmalek urban catchment). Journal of Natural Environmental Hazards, 5(10), 79-98. (In Persian)
Mukhtar, M.A., Shangguan, D., Ding, Y., Anjum, M.N., Banerjee, A., Butt, A.Q., Yadav, N., Li, D., Yang, Q., Khan, A.A., Muhammad, A., & He, B.B. (2024). Integrated flood risk assessment in Hunza-Nagar, Pakistan: unifying big climate data analytics and multi-criteria decision-making with GIS. Frontiers in Environmental Science, 12, 1337081, 1-18.
Nsangou, D., Kpoumié, A., Mfonka, Z., Ngouh, A.N., Fossi, D.H., Jourdan, C., Mouncherou, O.F., Vandervaere, J.P., & Ngoupayou, J.R.N. (2022). Urban flood susceptibility modelling using AHP and GIS approach: Case of the Mfoundi watershed at Yaoundé in the South-Cameroon plateau. Scientific African, 15, e01043, 1-16.
Pourkhabbaz, H.R., Javanmardi, S., Yavari, A. R., & Faraji Sabokbar, H. (2013). Application of multi criteria decision making method and the integrated ANP- DEMATEL model for agricultural land suitability analysis (Case study: Qazvin plain). Journal of Environmental Studies, 39(3), 151-164. (In Persian)
Rastgou, A., Ghanbari, A., & Ansari Lari, A. (2019). Evaluation and potential measurement of flood risk in Jinnah city using support vector machine (SVM) algorithm. Quarterly Journal of Physical Geography, 12(45), 107-125. (In Persian)
Saaty, TL., (1980). The Analytical Hierarchy Process: Planning, Priority Setting, Resource Allocation New York: McGraw Hill, 287 pp.
Sadeghi-Pouya, A., Nouri, J., Mansouri, N., & Kia-Lashaki, A. (2017). An indexing approach to assess flood vulnerability in the western coastal cities of Mazandaran, Iran. Disaster Risk Reduction, 22, 304-316.
Safaripour, M., & Rezapour Andabili, N. (2020). Miyandoab flood risk mapping using dematel and SAW methods and DPSIR model. Advances in Environmental Technology, 6(3), 131-138.
Senan, C.P., Ajin, R.S., Danumah, J.H., Costache, R., Arabameri, A., Rajaneesh, A., Sajinkumar, K.S., & Kuriakose, S.L. (2023). Flood vulnerability of a few areas in the foothills of the Western Ghats: A comparison of AHP and F-AHP models. Stochastic Environmental Research and Risk Assessment, 37(2), 527-556.
Shafiei, M., & Ghanbarzadeh Lak, M. (2018). Prioritizing artificial groundwater nourishing-flood spreading scenarios, Based on Analytical Network Process (ANP) (Case study: Khoy plain aquifer). Iran-Water Resources Research, 14(4), 140-159. (In Persian).
Shahiri Tabarestani, E., & Zokaei, M.S. (2020). Assessment of flood hazard using Analytic Hierarchy Process method (AHP) in Mazandaran province, Iran. Environment and Water Engineering, 6(4), 331-344. (In Persian)
Shaterian, M., Kiani, S., Gholami, Y., & Montaseri, Z. (2017). Prioritize the factors affecting on development of ecotourism villages of Barzok district- Kashan by combining DEMATEL and ANP methods. Applied Researches in Geographical Sciences, 17(44), 131-154. (In Persian)
Shirani, K., & Chavoshi, S. (2019). Prioritization of catchments prone to flooding by morphometric analysis. Journal of Water and Soil Science (JWSS), 22(4), 59-72. (In Persian)
Tahmasebi, M.R., Shabanlou, S., Rajabi, A., & Yosefvand, F. (2021). Flood probability zonation using a comparative study of two well-known random forest and support vector machine models in northern Iran. Water and Irrigation Management, 11(2), 223-235. (In Persian)
Tehrany. M.S., Paardhan, B., Mansor, S., Ahmad, N., (2015). Flood susceptibility assessment using GIS-based support vector machine model with different kernel types. Catena, 125, 91-101.
Tempa, K. (2022). District flood vulnerability assessment using analytic hierarchy process (AHP) with historical flood events in Bhutan. PLoS One, 17(6), e0270467, 1-20.
Wu, X., Shen, X., Li, J., & Xie, X. (2024). Determination and projection of flood risk based on multi-criteria decision analysis (MCDA) combining with CA-Markov model in Zhejiang Province, China. Urban Climate, 53, 101769, 1-15.
Xue, P., Huang, S., Xie, K., Sun, Y., & Fei, L. (2024). Identification of the critical factors in flood vulnerability assessment based on an improved DEMATEL method under uncertain environments. International Journal of Disaster Risk Reduction, 100, 104217.
Youssef, A.M., Pourghasemi, H.R., Mahdi, A.M., & Matar, S.S. (2023). Flood vulnerability mapping and urban sprawl suitability using FR, LR, and SVM models. Environmental Science and Pollution Research, 30(6), 16081-16105.
Zheng, C., Yang, W., Jiang, X., Lian, J., Hu, D., Yan, X., & Yan, L. (2024). A novel integrated Urban flood risk assessment approach coupling GeoDetector-Dematel and clustering method. Journal of Environmental Management, 354(3), 120308.
Zheng, Q. (2023). Method for a new risk assessment of urban inundation: G-DEMATEL–AHP. MethodsX, 10, 101997, 1-5.
Zheng, Q., Shen, S. L., Zhou, A., & Lyu, H. M. (2022). Inundation risk assessment based on G-DEMATEL-AHP and its application to Zhengzhou flooding disaster. Sustainable Cities and Society, 86, 104138.
تحقیقات آب و خاک ایران
دوره 55، شماره 10
دی 1403
صفحه 1939-1960

فایل ها

هم رسانی

ارجاع به این مقاله

آمار