کاربرد مدل‌های شبکه عصبی مصنوعی، نسبت فراوانی و تابع شواهد قطعی در تهیه نقشه حساسیت به وقوع سیل در حوزه آبخیز هراز: الگویی برای مطالعات مخاطرات سیلاب شهری

الموضوعات : فصلنامه علمی و پژوهشی پژوهش و برنامه ریزی شهری

هیمن شهابی ¹

1 - گروه ژئومورفولوژی، دانشکده منابع طبیعی، دانشگاه کردستان، سنندج، ایران

تاريخ الإرسال : 24 الأحد , رمضان, 1441 تاريخ التأكيد : 12 الجمعة , ذو القعدة, 1441 تاريخ الإصدار : 13 الجمعة , ذو الحجة, 1442

الکلمات المفتاحية: شبکه عصبی مصنوعی, داده‌کاوی, تابع شواهد قطعی, نسبت فراوانی, مخاطرات سیلاب شهری,

ملخص المقالة :

در این تحقیق برای تهیه نقشه­ حساسیت به وقوع سیل در حوزه آبخیز هراز در استان مازندران از روش­های شبکه عصبی مصنوعی (ANN)، نسبت فراوانی (FR) و تابع شواهد قطعی (EBF) استفاده شده است و برای دستیابی به هدف پژوهش از ده پارامتر­ موثر در وقوع سیلاب از قبیل شیب، انحنای زمین، فاصله از رودخانه، طبقات ارتفاعی، بارش، شاخص توان رودخانه (SPI)، شاخص رطوبت توپوگرافی (TWI)، لیتولوژی، کاربری اراضی و شاخص تفرق پوشش گیاهی (NDVI) استفاده گردید. همچنین، موقعیت جغرافیایی 211 نقطه سیل­گیر در منطقه تهیه شده و نقاط به صورت تصادفی به گروه­هایی متشکل از 151 نقطه (70%) و 60 نقطه (30%) به­ترتیب برای واسنجی و اعتبار­سنجی تقسیم شده­اند. سپس احتمال رخداد سیل برای هر کلاس از هر پارامتر­ محاسبه گردید. وزن­های محاسبه شده برای هر کلاس در سیستم اطلاعات جغرافیایی در لایه­های مربوطه اعمال­گردیده و نقشه­های حساسیت به وقوع سیل منطقه مورد مطالعه به­دست آمد. براساس نقشه پتانسیل سیل­خیزی، منطقه به 5 کلاس با حساسیت خیلی زیاد، زیاد، متوسط، کم و خیلی کم تقسیم گردید. روش­های مذکور توسط روش منحنی مشخصه عملکرد سیستم (AUC) ارزیابی شدند. نتایج حاکی از آن است که طبقات ارتفاعی پایین و نزدیک رودخانه دارای احتمال و حساسیت بالایی نسبت به وقوع سیل می­باشند. همچنین نتایج نشان داد که تکنیک نسبت فراوانی (AUC=0.97)، تابع شواهد قطعی (AUC=0.94) و شبکه عصبی مصنوعی (AUC=0.87) به­ترتیب اولویت، دارای بیشترین دقت در پیش­بینی وقوع سیل بوده­اند. از این­رو مدل­های مذکور به منظور پیش­بینی پتانسیل خطر سیل به­ویژه در نواحی مختلف از جمله فضاهای شهری به دلیل کارایی بالا، می­تواند مفید و قابل اعتماد باشند.

المصادر:

1. 1.      Althuwaynee, O.F., Pradhan, B., and Lee, S. (2012): Application of an evidential belief function model in landslide susceptibility mapping. Comput. Geosci. 44, 120–135.


2. 2.      Althuwaynee, O.F., Pradhan, B., Park, H.J., and Lee, J.H. (2014): A novel ensemble bivariate statistical evidential belief function with knowledge-based analytical hierarchy process    and    multivariate    statistical    logistic    regression    for    landslide susceptibility mapping. Catena 114, 21–36.


3. 3.      Billa L, Shattri M, Mahmud AR, and Ghazali, AH. (2006): Comprehensive planning and the role of SDSS in flood disaster management in Malaysia. Disaster Prev Manage 15:233–240.


4. 4.      Dai, FC/, Lee, CF., Li, J., and Xu, ZW. (2001): Assessment of landslide susceptibility on the natural terrain of Lantau Island, Hong Kong. Environ Geol 40:381–391.


5. 5.      Dixon, B. (2005): Applicability of neuro-fuzzy techniques in predicting ground-water vulnerability:  a GIS-based sensitivity analysis. J Hydrol 309:17–38.


6. 6.      Esfandiary Darabad, F., Rahimi, M., and Pourmortaza, G. (2019): Flood zonation of Agerloo Cay Basin using the L-THIA method and fuzzy logic, quantitative geomorphological researches, 8(2), pp: 155 - 171. (in Persian)


7. 7.      Ferna´ndez, DS., and Lutz, MA. (2010): Urban flood hazard zoning in Tucuma´n Province, Argentina, using GIS and multicriteria decision analysis. Eng Geol 111:90–98.


8. 8.      Islam, M.M., Sado, K., Owe, M., Brubaker, K., Ritchie, J., and Rango, A. (2001): Flood damage and management modelling using satellite remote sensing data with GIS: case study of Bangladesh. IAHS Publication, pp. 455-457.


9. 9.      Jamini, Davood., Amini, Abbas., Ghadermarzi, Hamed and Tavakoli, Jafar  (2017): Measurement of Food Security and Investigation of its Challenges in Rural Areas (Case Study: Badr District from Ravansar County), JOURNAL OF REGIONAL PLANNING, 7 (27): pp: 87-102. (in Persian)


10. 10.  Jung, IW., Chang, H., and Moradkhani, H. (2011): Quantifying uncertainty in urban flooding analysis considering hydro-climatic projection and urban development effects. Hydrol Earth Syst Sci 15(2):617–633.


11. 11.  Khosravi, K., Pham, B.T., Chapi, K., Shirzadi, A., Shahabi, H., Revhaug, I., Prakash, I., and Bui, D.T. (2018): A comparative assessment of decision trees algorithms for flash flood susceptibility modeling at Haraz watershed, northern Iran. Science of the Total Environment, 627, pp.744-755.


12. 12.  Khosravi, K., Pourghasemi, H.R., Chapi, K., and Bahri, M. (2016): Environ Monit Assess, 188: 656. doi:10.1007/s10661-016-5665-9.


13. 13.  Khosroshahi, M. (2016): An overview to identification and prioritization of flood prone areas using SSSE method in sub-watersheds, Iranian Journal of Watershed Management Science and Engineering, 10(33), pp: 59 – 72. (in Persian)


14. 14.  Kia, MB., Pirasteh, S., Pradhan, B., Mahmud, AR., Sulaiman, WNA., and Moradi, A. (2012): An artificial neural network model for flood simulation using GIS: Johor River Basin, Malaysia. Environ Earth Sci 67:251–264.


15. 15.  Kron, W. (2002): Keynote lecture: flood risk = hazard * exposure * vulnerability. In: Proceedings of the flood defence. Science Press, New York.


16. 16.  Lee, M.J., Kang, J.E., and Jeon, S (2012): Application of frequency ratio model and validation for predictive flooded area susceptibility mapping using GIS. In: Geoscience and Remote Sensing Symposium (IGARSS), Munich. 895–898.


17. 17.  Merz, B., Thieken, AH., and Gocht, M. (2007): Flood risk mapping at the local scale: concepts and challenges. In: Flood risk management in Europe. Springer, Amsterdam, pp 231–251.


18. 18.  Miller, JR., Ritter DF., and Kochel RC (1990): Morphometric assessment of lithologic controls on drainage basin evolution in the Crawford Upland, south-central Indiana. Am J Sci 290:569–599.


19. 19.  Moore, ID., Grayson, RB., and Ladson, AR. (1991): Digital terrain modelling: a review of hydrological, geomor- phological, and biological applications. Hydrol Process 5:3–30.


20. 20.  Nampak, H., Pradhan, B. and Manap, M.A. (2014): Application of GIS based data driven evidential belief function model to predict groundwater potential zonation. Journal of Hydrology, 513, pp.283-300.


21. 21.  Nasiri, Z., and Talebi, A. (2020): prioritization of sub-watersheds from flooding viewpoint using the Hec-Hms model in upstream of Shiraz Khoshk River, Iranian Journal of Eco Hydrology, 7(1), pp: 47-57. (in Persian)


22. 22.  Nazaripouya, H. (2019): Evaluation of Factor Analysis Method in Prioritizing Flood in Northern Sub-basins of Alvand Hamedan, Journal of Watershed Management Research, 10(20), pp: 49-61. (in Persian)


23. 23.  Nozari, H., Marofi, S., and Edirsh, M. (2017): Identification and prioritize of potential areas to flood inundation in the Dez basin using WMS, Journal of Range and Watershed Management, 70(3), pp: 805 - 820. (in Persian)


24. 24.  Oh, H.J., and Pradhan, B. (2011): Application of a neuro-fuzzy model to landslide- susceptibility mapping for shallow landslides in a tropical hilly area. Computer and Geoscience, 37, 1264–1276.


25. 25.  Ohlmacher, GC., and Davis, JC. (2003): Using multiple logistic regression and GIS technology to predict landslide hazard in northeast Kansas, USA. Eng Geol 69:331–343.


26. 26.  Porhemmat, J. (2016): A model on investigation on flood hazard over watersheds of Iran, Iranian Journal of Watershed Management Science and Engineering, 10 (34), pp: 1-14. (in Persian)


27. 27.  Pourghasemi, H.R., and Beheshtirad, M. (2014): Assessment of a data-driven evidential belief function model and GIS for groundwater potential mapping in the Koohrang Watershed, Iran. Geocarto International, 30(6): 662-685.


28. 28.  Pourghasemi, H.R., Mohammadi, M., and Pradhan, B. (2012): Landslide susceptibility mapping using index of entropy and conditional probability models at Safarood Basin, Iran. Catena 97, 71–84, <http://dx.doi.org/10.1016/j.catena.2012.05.005>.


29. 29.  Pradhan B, and Lee, S. (2010): Delineation of landslide hazard areas on Penang Island, Malaysia, by using frequency ratio, logistic regression, and artificial neural network models. Environ Earth Sci 60:1037-1054.


30. 30.  Pradhan, B. (2013): A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS. Comput. Geosci. 51, 350–365.


31. 31.  Pradhan, B., Abokharima, M.H., Jebur, M.N., and Tehrany, M.S. (2014): Land subsidence susceptibility mapping at Kinta Valley (Malaysia) using the evidential belief function model in GIS. Natural hazards, 73(2), pp.1019-1042.


32. 32.  Pradhan, B., and Youssef, A.M. (2011): A 100‐year maximum flood susceptibility mapping using integrated hydrological and hydrodynamic models: Kelantan River Corridor, Malaysia. Journal of Flood Risk Management, 4(3), pp.189-202.


33. 33.  Pradhan, B., Hagemann, U., Shafapour Tehrany, M., and Prechtel, N. (2014): An easy to use ArcMap based texture analysis program for extraction of flooded areas from TerraSAR-X satellite image. Comput. Geosci. 63, 34-43.


34. 34.  SCWMRI (Soil Conservation and Watershed Management Research Institute). (2015): Atlas of the country's watersheds, Publishers: Agricultural Research Education and Extension Organization, Tehran. (in Persian)


35. 35.  Shamsoddini, Ali and Nasibi, Sasan (2019): The study of urban furniture layout on the urban area's vitality (case study: the whole area of Shiraz), Journal of Research and Urban Planning, 10 (37), pp: 83-96. (in Persian)


36. 36.  Shamsodini, A., Jamini, D., and Jamshidi, A. (2016): Measurement and Analyses of Social Stability in Rural Area (Case Study: Javanrood Township). Journal of Rural Research. 7(3), 486-503. (in Persian)


37. 37.  Smith, K. (2001): Environmental hazards assessing risk and reducing disaster, 3rd edn. Routledge, fetter lane, London.


38. 38.  Talebi, A., Eslami, Z., and Abbasi, A. (2019): Comparing prioritization from flooding of sub-basins using HEC-HMS model and experimental methods in Eskandari Watershed, Journal of Watershed Engineering and Management, 11(2), pp: 336 - 343. (in Persian)


39. 39.  Tehrany, M.S., Lee, M.J., Pradhan, B., Jebur, M.N., and Lee, S. (2014b): Flood susceptibility mapping using integrated bivariate and multivariate statistical models. Environ. Earth sci. 72(10): 4001-4015.


40. 40.  Tehrany, M.S., Pradhan, B., and Jebur, M.N. (2013): Spatial prediction of flood susceptible areas using rule based decision tree (DT) and a novel ensemble bivariate and multivariate statistical models in GIS. Journal of Hydrology, 504: 69-79.


41. 41.  Tehrany, M.S., Pradhan, B., and Jebur, M.N. (2014a): Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS. J. Hydrol. 512: 332-343.


42. 42.  Tehrany, M.S., Pradhan, B., Mansour, Sh., and Ahmad, N. (2015): Flood susceptibility assessment using GIS-based support vector machine model with different kernel types.125:91-101.


43. 43.  Tunusluoglu, M., Gokceoglu, C., Nefeslioglu, H., and Sonmez, H. (2008): Extraction of potential debris source areas by logistic regression technique:  a case study from Barla, Besparmak and Kapi mountains (NW Taurids, Turkey). Environ Geol 54:9–22.


44. 44.  Youssef, A.M., Pradhan, B., Pourghasemi, H.R., and Abdullahi, S. (2014): Landslide susceptibility assessment at Wadi Jawrah Basin, Jizan region, Saudi Arabia using two bivariate models in GIS. Geosciences Journal, 19(1):113-134.


45. 45.  Zarghami, S., Teymouri, A., Mohammadian, H and Shamaei, A (2016): Measuring and evaluating urban neighborhood’s resilience against earthquake: the case of Zanjan downtown, Journal of Research and Urban Planning, 7(27): pp: 77-92. (in Persian)