ارزیابی و پهنه‌بندی وقوع مخاطرۀ سیلاب در پارک ملی گلستان

نوع مقاله : پژوهشی

نویسندگان

1 دانشجوی دکتری جنگل‌داری دانشگاه تربیت مدرس، دانشکدۀ منابع طبیعی و علوم دریایی نور، مازندران‌

2 استاد گروه جنگل‌داری دانشگاه تربیت مدرس، دانشکدۀ منابع طبیعی و علوم دریایی نور، مازندران

3 دانشیار بخش مهندسی منابع طبیعی و محیط زیست، دانشکدۀ کشاورزی، دانشگاه شیراز، شیراز‌

4 محقق مرکز GIS، گروه جغرافیای فیزیکی و علوم اکوسیستم، دانشگاه لند، سوئد‌

چکیده

شناسایی مناطق حساس به سیل، عنصر حیاتی و مهمی برای کنترل و کاهش تلفات سیل به‏شمار می‏آید. هدف از تحقیق حاضر، شناسایی متغیرهای مهم در ایجاد مناطق سیل‏گیر و ارائۀ پتانسیل مخاطرۀ سیل پارک ملی گلستان با استفاده از تکنیک‏های یادگیری ماشین شامل مدل جنگل تصادفی، درخت رگرسیون تقویت‌شده و آنتروپی بیشینه است. برای رسیدن به اهداف یادشده، ابتدا عوامل تأثیرگذار با توجه به مرور منابع تعیین شده و پایگاه داده‏ها ایجاد شد. در نهایت، با استفاده از تکنیک‏های یادگیری ماشین مدل‏سازی مخاطرۀ سیل صورت گرفت و دقت این مدل‏ها با استفاده از روش منحنی‏ ROC و داده‏های واقعی از رخ‏داد سیل بررسی شد. نتایج مدل‏ها، اهمیت زیاد متغیرهای ارتفاع از سطح دریا، میانگین دمای سالیانه، فاصله از آبراهه‏ها، بارش و فاصله از جادۀ ترانزیتی را در وقوع مخاطرۀ سیل نشان دادند. نتایج به‌دست‌آمده از درخت رگرسیون تقویت‌شده تأثیر متغیر ارتفاع از سطح دریا، میانگین دمای سالیانه، بارندگی و فاصله از آبراهه‏ها را به‌ترتیب، 9/38، 2/19، 6/13 و 13 درصد نشان داد. همچنین، در نتایج حاصل از آنتروپی بیشینۀ متغیرهای ارتفاع از سطح دریا، میانگین دما و جادۀ ترانزیتی به‌ترتیب با مقدار مشارکت 7/35، 4/22 و 5/19 درصد جزء متغیرهای مهم به‌دست آمدند. نتایج به‌دست‌آمده از ارزیابی صحت مدل‏ها با استفاده از 30 درصد از داده‏های وقوع سیل که در مدل‏سازی وارد نشده بود نیز دقت زیاد مدل درخت رگرسیون تقویت‌شده و جنگل تصادفی را با مقدار ROC، 99/0 و دقت مناسب آنتروپی بیشینه را با مقدار ROC، 89/0 نشان داد، به‏طوری ‏که نقشه‏های به‌دست‌آمده از این مدل‏ها به طور مشترک 4500 هکتار از مساحت پارک را دارای احتمال زیاد خطر سیل برآورد کردند.

کلیدواژه‌ها


عنوان مقاله [English]

Assessment and Zoning of Flood Risk in Golestan National Park

نویسندگان [English]

  • Hassan Faramarzi 1
  • Seyed Mohsen Hosseini 2
  • Hamid Reza Pourghasemi 3
  • Mahdi Farneghi 4
1 PhD Student, Department of Natural Resources, Tarbiat Modares University, Noor, Mzandaran
2 Professor, Department of Natural Resources, Tarbiat Modares University, Noor, Mzandaran
3 Associate Professor, Department of Natural Resources and Environment, Faculty of Agriculture, Shiraz University, Shiraz
4 GIS Center, Department of Physical Geography and Ecosystem Science, Lund University, Sweden
چکیده [English]

Identifying the flood susceptible areas is a vital and substantial element of disaster management to control and mitigate injuries of the natural hazards. The purpose of this study was to identify the important variables in creating flood areas and to present the potential hazard of flood in Golestan National Park (GNP) using machine learning techniques including random forest (RF), boosted regression tree (BRT) and maximum entropy (ME) models. In order to achieve these purposes, firstly, factors were determined by reviewing the relevant sources, and the databases were created by sorting out these factors. Finally, Flood risk modeling was done using machine learning techniques and the accuracy assessment were determined using the ROC method and real data recorded in nature. The results of the models showed the importance of elevation, distance from the river and transit road, moisture and maximum temperature variables in the event of flood hazard. So that the results of the BRT showed role elevation variable to be 38.9%, mean temperature 19/2 %, Rainfall 13/6 %  and distance from the rivers 13% and the results of ME showed role elevation, mean temperature and distance of road  variables to be respectively 35.7, 22/4 and 13.8%. The results of the accuracy assessment models using 30% of the data that were not included in the modeling the ROC value showed BRT and RF model with 0.99 values, and the proper accuracy ME was with value of 0.89. The maps obtained from these models estimated 4,500 hectares of park area among the high risk areas.

کلیدواژه‌ها [English]

  • Flood hazards
  • Maximum entropy
  • Random forest
  • Boosted Regression Tree
  • Crisis Management
[1]. Samela, C., Albano, R., Sole, A., & Manfreda, S. A GIS tool for cost-effective delineation of flood-prone areas. Computers, Environment and Urban Systems. 2018; 70: 43–52.
[2].  Garrote, J., Alvarenga, F.M., Díez-Herrero, A. Quantification of flash flood economic risk using ultra-detailed stage–damage functions and 2-D hydraulic models. J. Hydrol. 2017; 541 (Part A, October), 611–625.
 
[3].  Guhathakurta, P.,Sreejith,O.P.,Menon,P.A. Impactofclimatechangeon extreme rainfall event sand flood risk in India.J.EarthSyst.Sci. 2011; 120: 359–373.
[4].  Toda, L. L., Yokingco, J. C. E., Paringit, E. C., & Lasco, R. D. A LiDAR-based flood modelling approach for mapping rice cultivation areas in Apalit, Pampanga. Applied Geography, 2017; 80: 34-47.
[5].  Vasu, N. N., Lee, S. R., Pradhan, A. M. S., Kim, Y. T., Kang, S. H., & Lee, D. H. A new approach to temporal modelling for landslide hazard assessment using an extreme rainfall induced-landslide index. Engineering Geology. 2016; 215: 36-49.
[6].  Alfieri L, Salamon P, Bianchi A, Neal J, Bates P, Feyen L. Advances in pan-European flood hazard mapping. Hydrological processes. 2014; 28(13):4067-77.
[7].  Mosavi A, Ozturk P, Chau KW. Flood prediction using machine learning models: Literature review. Water. 2018;10(11):1536.
[8].  Mosavi, SM., Negahban, S., RakhasniMoghadam, H., Hossinzadeh, SM. Assessment and zoning Flood risk by using Fuzzy logic TOPSIS in GIS (Case study: Baghmalek urban catchment), Environmental Hazards. 2017; 5(10): 79-98. In persian.
[9].  Abedini, M., FathiJokadan, R. Flood Risk Zoning in Karaganrouds Catchment Basin Using ArcGIS, Hydrogeomorphology. 2017; 7: 1-17. In persian.
[10].            Rahmati, O., & Pourghasemi, H. R. Identification of Critical Flood Prone Areas in Data-Scarce and Ungauged Regions: A Comparison of Three Data Mining Models. Water Resources Management. 2017; 31(5): 1473-1487.
[11].            Darabi H, Choubin B, Rahmati O, Haghighi AT, Pradhan B, Kløve B. Urban flood risk mapping using the GARP and QUEST models: A comparative study of machine learning techniques. Journal of hydrology. 2019; 569:142-54.
[12].            Tehrany MS, Jones S, Shabani F. Identifying the essential flood conditioning factors for flood prone area mapping using machine learning techniques. Catena. 2019; 1(175):174-92.
[13].            Khorozyan, I., Soofi, M., Ghoddousi, A., Hamidi, A. K., & Waltert, M. The relationship between climate, diseases of domestic animals and human-carnivore conflicts. Basic and Applied Ecology. 2015; 16(8), 703-713.
[14].            Djamali, M., de Beaulieu, J. L., Campagne, P., Andrieu-Ponel, V., Ponel, P., Leroy, S. A. G., & Akhani, H. Modern pollen rain–vegetation relationships along a forest–steppe transect in the Golestan National Park, NE Iran. Review of Palaeobotany and Palynology. 2009; 153(3): 272-281.
[15].            Khoshzaher, H., VarasteMoradi, H., SalmanMahini, a. The Impact of Snags and Logs on the Bird Community in the Non-breeding Season in Golestan National Park, Environment Since. 2017; 14(2): 69-78. In persian.
[16].            Moradi, H.R., Hosseini, SM. Investigating Effective Environmental Factors on Golestan Flood, Conference on Natural Resources and Sustainable Development in Southern Caspian Sea, Islamic Azad University, Noor. 2007. In persian.
[17].            Davis, J., & Blesius, L.A hybrid physical and maximum-entropy landslide susceptibility model. Entropy. 2015; 17(6), 4271-4292.
[18].            Majnonian, H., Zahzad, B., FarhangDareshuri, B., GashtasbMigui, H. Personal information of Golestan National Park Biosphere Reserve, 2nd ed, Environmental Organization Publications. 2008; 129 p. In persian.
[19].            Chen, L., van Westen, C. J., Hussin, H., Ciurean, R. L., Turkington, T., Chavarro-Rincon, D., & Shrestha, D. P. Integrating expert opinion with modelling for quantitative multi-hazard risk assessment in the Eastern Italian Alps. Geomorphology. 2016; 273: 150-167.
[20].            Khosrvai, Kh., Marufiniya, A., Nohani, A., Chapi, K. Evaluation of Logistic Regression Efficiency in Mapping Flood Susceptibility, Range and Watershed Management. 2017; 69 (4): 863-876. In persion.
[21].            Siahkamari, S., Zeinivand, H. Flood prone areas mapping by using statistical index and weights of evidence models (Case study: Madar Soo watershed, Golestan), RS and GIS for natural resourses, 2017; 7(4): 116-133. In Persian.
[22].            TehranyMS, Pradhan B, Jebur MN. Spatial prediction of flood susceptible areas using rule based decision tree (DT) and a novel ensemble bivariate and multivariate statistical models in GIS. Jornal of Hydrology. 2013, 504:69–79.
[23].            Moore, I.D., and Grayson, R.B. Landson. Digital terrain Modeling: A review of hydrological, Geomorphological and Biological application. Hydrology Process. 1991; 5: 3-30.
[24].            Sullivan-Wiley, K. A., & Gianotti, A. G. S. Risk Perception in a Multi-Hazard Environment. World Development, article in press. 2017; 1-15.
[25].            Dai FC, Lee CF, Li JX, Xu ZW. Assessment of landslide susceptibility on the natural terrain of Lantau Island, Hong Kong. Environmental Geology. 2001; 40(3):381-91.
[26].            Forman, S. L., & Pierson, J. Formation of linear and parabolic dunes on the eastern Snake River Plain, Idaho in the nineteenth century. Geomorphology. 2003; 56(1-2): 189-200.
[27].            Chuvieco, E., Cocero, D., Riano, D., Martin, P., Martınez-Vega, J., de la Riva, J., & Perez, F. Combining NDVI and surface temperature for the estimation of live fuel moisture content in forest fire danger rating. Remote Sensing of Environment. 2004; 92(3): 322-331.
[28].            Kornejady, A., Ownegh, M., & Bahremand, A. Landslide susceptibility assessment using maximum entropy model with two different data sampling methods. Catena. 2017; 152: 144-162.
[29].            Convertino, M.; Troccoli, A.; Catani, F. Detecting fingerprints of landslide drivers: A MaxEnt model. J. Geophys. Res. Earth Surf. 2013; 118: 1367–1386.
[30].            Rezaei, S., Ndaery, S., Karami, P. Spring and summer habitat suitability modeling of wild boar (Sus scrofa) in Jassb wildlife refuge of Arak using Maximum Entropy (MaxEnt) method, Journal of Animal Environment, 2017., 9 (2): 25-36. In persian.
[31].            Baldwin R. Use of maximum entropy modeling in wildlife research. Entropy. 2009;11(4):854-66.
[32].            Elith J, Leathwick JR, Hastie T. A working guide to boosted regression trees. Journal of Animal Ecology. 2008; 77(4):802-13.
[33].            Westreich D, Lessler J, Funk MJ. Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression. Journal of clinical epidemiology. 2010; 63(8):826-33.
[34].            Guo L, Chehata N, Mallet C, Boukir S. Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests. ISPRS Journal of Photogrammetry and Remote Sensing. 2011; 66(1):56-66.
[35].            Breiman, L. Random forests. Machine Learning. 2001; 45 (1): 5-32.
[36].            Le Bris A, Chehata N, Briottet X, Paparoditis N. A random forest class memberships based wrapper band selection criterion: Application to hyperspectral. In2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). 2015; 1112-1115.
[37].            Rossiter, D. G., & Loza, A. Analyzing land cover change with logistic regression in R. University of Twente, Faculty of Geo-Information Science & Earth Observation (ITC), Enschede (NL). 2012; 71 pp.
[38].            Kanani-Sadat, Y., Arabsheibani, R., Karimipour, F., & Nasseri, M. A new approach to flood susceptibility assessment in data-scarce and ungauged regions based on GIS-based hybrid multi criteria decision-making method. Journal of Hydrology. 2019; 572, 17-31.
[39].            Faramarzi, H., Hosseini, S.M., Pourghasemi, M.R., Farnaghi, M. Evaluation of the Asian Highway Role on Golestan National Park Fire in GIS Environment. Wood and forest science and technology, 2019; 25(3): 33-48. In Persian.
[40].            Zebardast, L., Yavri, A.H., Salehi, A., Makhdum, M. Use network Effective metric in forest cover disruption analysis in road around of Golestan National Park, Ecology journal, thirty-seventh year, 2011; 58: 15-20. In Persian.
[41].            Nouruzi, H., Nadiri., A., Moghadam, A., GharahKhani, M. Prediction of Transmissivity of Malikan Plain Aquifer Using Random Forest Method, Water and Soil Scince. 2017; 27(2):61-75.In Persian.
[42].            Nandi, A., and A. Shakoor. "A GIS-based landslide susceptibility evaluation using bivariate and multivariate statistical analyses." Engineering Geology 110, no. 1-2 (2010): 11-20.
[43].            Pourghasemi, H. R., & Kerle, N. Random forests and evidential belief function-based landslide susceptibility assessment in Western Mazandaran Province, Iran. Environmental earth sciences, 75(3), 185.
[44].            the natural terrain of Lantau Island, Hong Kong. Environmental Geology. 2016; 43 (3), 381– 391.