تهیه نقشه حساسیت سیل با استفاده از دو مدل یادگیری ماشین جنگل تصادفی و مدل خطی تعمیم یافته بیزین

نوع مقاله: یادداشت فنی

نویسندگان

1 دانشجوی دکتری علوم و مهندسی آبخیزداری، دانشکده منابع طبیعی و علوم دریایی، دانشگاه تربیت مدرس. تهران. ایران

2 دانشیار گروه علوم و مهندسی آبخیزداری، دانشکده منابع طبیعی و علوم دریایی، دانشگاه تربیت مدرس. تهران. ایران

3 استادیار گروه مدیریت جهانگردی، دانشکده علوم انسانی و اجتماعی، دانشگاه مازندران. بابلسر. ایران

10.22034/jewe.2020.220593.1351

چکیده

امروزه پدیده­ی سیل یکی از پیچیده­ترین رخدادهای مخاطره­آمیز است که بیش از سایر بلایای طبیعی دیگر، همه‌ساله در نقاط مختلف دنیا منجر به ایجاد خسارت­های جانی و مالی و تخریب اراضی کشاورزی می­شود؛ بنابراین تهیه نقشه حساسیت به وقوع سیلاب نخستین گام در برنامه مدیریت سیلاب است. هدف از این پژوهش شناسایی مناطق حساس به سیل با استفاده از دو مدل یادگیری ماشین جنگل تصادفی (RF) و خطی تعمیم‌یافته بیزین (GLMbayesian) در حوزه آبخیز تجن در استان مازندران، شهرستان ساری بود. نقشه پراکنش سیلاب­های گذشته به‌منظور پیش­بینی سیلاب در آینده تهیه شد. از بین 263 رخداد سیلاب، 80% (210 رخداد سیل) به‌منظور مدل‌سازی و 20% (53 رخداد سیل) به‌منظور اعتبارسنجی استفاده شد. با بررسی مطالعات قبلی و پیمایش منطقه موردمطالعه 13 عامل مؤثر به‌منظور پهنه­بندی سیلاب انتخاب و تهیه شد. نتایج نشان داد که سه فاکتور ارتفاع (55/21)، فاصله از رودخانه (28/15) و شیب (18/11) به­ترتیب بیش­ترین تأثیر را در سیل گیری منطقه موردمطالعه دارند. همچنین نتایج ارزیابی خروجی مدل­ها نشان داد که مقدار AUC در مدل RF و GLMbayesian به­ترتیب 91/0 و 847/0 بود که نشان‌دهنده برتری مدل RF و دقت بیش­تر این مدل در تهیه نقشه حساسیت به وقوع سیل در منطقه موردمطالعه می­باشد. بیش­ترین مساحت حساسیت به سیل در مدل RF مربوط به طبقه خیلی کم و در مدل GLMbayesian مربوط به طبقه زیاد است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Flood Susceptibility Mapping Using Random Forest Machine Learning and Generalized Bayesian Linear Model

نویسندگان [English]

  • Mohammad taghi Avand 1
  • Hamid Reza Moradi 2
  • Mehdi Ramazanzadeh 3
1 PhD Scholar, Department of Watershed Management Engineering, Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Tehran, Iran
2 Assoc. Professor, Department of Watershed Management Engineering, Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Tehran, Iran
3 Assist. Professor, Department of Tourism Management, Faculty of Humanities and Social Sciences, University of Mazandaran, Babolsar, Iran
چکیده [English]

Today, the phenomenon of flooding is one of the most complex hazardous events that, more than any other natural disaster, causes deaths and finances every year in different parts of the world. Therefore, flood susceptibility mapping is the first step in a flood management program. The purpose of this study was to identify flood susceptible areas using two methods of random forest (RF) and Bayesian generalized linear model (GLMbayesian) machine learning in the Tajan watershed in Mazandaran province, Sari. Past flood distribution maps were prepared to predict future floods. Of the 263 flood locations, 80% (210 flood locations) was used for modeling and 20% (53 flood locations) was used for validation. Based on previous studies and surveying of the study area, 13 conditional factors were selected for flood zoning. The results showed that three factors of elevation (21.55), distance from the river (15.28) and slope (11.18) had the highest impact on flood occurrence in the study area, respectively. The results also showed that the AUC values for RF and GLMbayesian models were 0.91 and 0.847, respectively, indicating the superiority of the RF model and the accuracy of this model in flood susceptibility mapping in the study area. The highest flood susceptibility area in the RF model is in the very low class and the high class in the GLMbayesian model.

کلیدواژه‌ها [English]

  • Flood damage
  • GLMbayesian Model
  • RF Model
  • ROC curve
  • Tajan Watershed
Alizadeh A. (2007). Principles of applied hydrology. Mashhad, Twenty-third Edition, Astan Qods Razavi Publications, p. 808 [In Persian].

Al-Juaidi A. E. M., Nassar A. M. and Al-Juaidi O. E. M. (2018) Evaluation of flood susceptibility mapping using logistic regression and GIS conditioning factors. Arab. J. Geosci. 11, 765.

Arab Ameri A., Pourghasemi H. R. and Shirani K. (2017). Flood susceptibility zoning using a new hybrid Bayesian theory-hierarchical analysis process (Case study: Neka Watershed, Mazandaran Province). Ecohydrol., 4(2), 447-462 [In Persian].

Avand M., Janizadeh S., Tien Bui D., Pham V. H., Ngo P. T. T. and Nhu V. H. (2020). A tree-based intelligence ensemble approach for spatial prediction of potential groundwater. Int. J. Digit. Earth, 1-22.

Breiman L. (2001). Random forests. Machine Learn., 45(l), 5-32.

Costache R. (2019) Flood susceptibility assessment by using bivariate statistics and machine learning models-A useful tool for flood risk management. Water Resour. Manag., 33, 3239-3256.

Darabi H., Shahedi K. and Mardian M. (2016). Flood susceptibility and probability mapping using frequency ratio method in Pol-Doab Shazand watershed. J. Eng. Watershed Manage., 8(1), 79-68 [In Persian].

Darabi H., Shahedi K., Solaimani K. and Miryaghoubzadeh M. (2014). Prioritization of subwatersheds based on flooding conditions using hydrological model, multivariate analysis and remote sensing technique. Water Environ. J., 28(3), 382-392.

Fernandez D. S. and Lutz M. A. (2010). Urban flood hazard zoning in Tucuman Province, Argentina, using GIS and multicriteria decision analysis. Eng. Geol., 111, 90-98.

Hastie T., Tibshirani R. and Friedman J. (2009). The elements of statistical learning: data mining, inference, and prediction. Springer Science & Business Media.

Hazarika N., Barman D., Das A. K., Sarma A. K. and Borah S. B. (2018). Assessing and mapping fl ood hazard, vulnerability and risk in the Upper Brahmaputra River valley using stakeholders’ knowledge and multicriteria evaluation (MCE). 11(52), 5700-5716.

Janizadeh S., Avand M., Jaafari A., Phong T., Bayat M., Ahmadisharaf E., Prakash I., Pham B. T. and Lee S. (2019). Prediction success of machine learning methods for flash flood susceptibility mapping in the Tafresh Watershed, Iran. Sustain., 11(19), 5426.

Kamata A. (2001). Item analysis by the hierarchical generalized linear model. J. Edu. Measure., 38(1), 79-93.

Kanani-Sadat Y., Arabsheibani R., Karimipour F. and Nasseri M. (2019). A new approach to flood susceptibility assessment in data-scarce and ungauged regions based on GIS-based hybrid multi criteria decision-making method. J. Hydrol., 572, 17–31.

Khairizadeh M., Maleki J. and Amunia H. (2014). Potential zoning of flood risk in Mardegh Chai catchment using ANP model. J. Quant. Geomorphol. Res., 1(3), 39-65 [In Persian].

Khairizadeh M., Maleki J. and Amounia H. (2013). Flood hazard zoning using ANP model in watershed, case study: Mardaghchay Watershed. Quant. Geomorphol. Res., 3, 39-56 [In Persian].

Lee Sunmin Kim J. C., Jung H. S., Lee M. J. and Lee S. (2017). Spatial prediction of flood susceptibility using random-forest and boosted-tree models in Seoul metropolitan city, Korea. Geomat. Nat. Hazard. Risk, 8, 1185–1203.

Luu C. and Meding J. V. (2018). A flood risk assessment of Quang Nam, Vietnam. Water, 10(4), 461.

Motevalli A. and Vafakhah M. (2016). Flood hazard mapping using synthesis hydraulic and geomorphic properties at watershed scale. Stoch. Environ. Res. Risk Assess., 30, 1889–1900.

Mukerji A., Chatterjee C. and Raghuwanshi N.S. (2009). Flood forecasting using ANN, neuro-fuzzy, and neuro-GA models. J. Hydrol. Eng., 647–652.

Pham B. T., Avand M., Janizadeh S., Phong T. V., Al-Ansari N., Ho L. S., Das S., Le H. V., Amini A., Khosrobeigi Bozchaloei S., Jafari F. and Prakash I. (2020). GIS based hybrid computational approaches for flash flood susceptibility assessment. Water, 12(3), 683.

Rahmati O., Pourghasemi H. R. and Zeinivand H. (2016). Flood susceptibility mapping using frequency ratio and weights-of-evidence models in the Golastan Province, Iran. Geocarto. Int., 31, 42–70.

Pradhan B., Hagemann U., Tehrany Shafapour M. and Prechte 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.

Razavi Termeh S. V., Kornejady A., Pourghasemi H. R. and Keesstra S. (2018). Flood susceptibility mapping using novel ensembles of adaptive neuro fuzzy inference system and metaheuristic algorithms. Sci Total Environ., 615, 438–451.

Siahkamri S. and Zainivand H. (2016). Potential of flood prone areas using statistical index model and weight of evidence (Case study: Madarsoo Watershed, Golestan). Remote Sens. GIS Nat. Resour., 7(4),0-0 [In Persian].

Souissi D., Zouhri L., Hammami S., Msaddek M. H., Zghibi A. and Dlala M. (2019). GIS-based MCDM-AHP modeling for flood susceptibility mapping of arid areas, southeastern Tunisia. Geocarto. Int., 1–27.

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

Tehrany Shafapour M., Pradhan B. Mansor S. H. and Noordin A. (2015). Flood susceptibility assessment using GIS-based support vector machine model with different kernel types. Catena., 125, 91-101.

Vojtek M. and Vojteková J. (2019). Flood Susceptibility Mapping on a National Scale in Slovakia Using the Analytical Hierarchy Process. Water 11:364, Multidisciplinary Digital Publishing Institute.

Wang Y., Hong H., Chen W., Li S., Pamučar D., Gigović L., Drobnjak S., Bui D. T. and Duan H. (2019). A hybrid GIS multi-criteria decision-making method for flood susceptibility mapping at Shangyou, China. Remote Sens., 11(1), 62.

West M., Harrison P. J. and Migon H. S. (1985). Dynamic generalized linear models and Bayesian forecasting. J. Am. Stat.Assoc., 80(389), 73-83.

Zhao G., Pang B., Xu Z., Yue J. and Tu T. (2018). Science of the Total Environment Mapping fl ood susceptibility in mountainous areas on a national scale in China. Sci. Total Environ., 615, 1133–1142.