Remote Sensing and GIS Applications in Environmental Sciences

Flood risk Analysis of Watersheds Using Machine Learning Algorithms and Hydrogeomorphological Factors (Case study: Eastern Catchment Area of Lake Urmia)

Document Type : Original Article

Authors

1 Assistant professor, Department of Civil Engineering, Tabriz Branch, Islamic Azad University, Tabriz, Iran

2 Associate Professor, Department of Civil Engineering, Tabriz Branch, Islamic Azad University, Tabriz, Iran

10.22034/rsgi.2023.54585.1037

Abstract

Flood zoning maps provide valuable information about the nature of flood and its effect on floodplain lands. A set of effective factors must be defined to map flood susceptibility or, in general, to develop a model for assessing natural disaster risk. The factors affecting flood were used in eastern catchment area of lake Urmia which include altitude, slope, distance from the river, topographic moisture index, topographic position index, roughness index, curvature level, topographic curvature section, total curvature, NDVI index, land use, lithology and rainfall according to the experiences of experts and researchers reported in previous studies. After preparing the effective layers on the flood and the point layer of the flood points, as well as performing the linear test, five methods including Multiple Linear Regression, Partial Least Squares Model, Quantile Regression, Ridge Regression and Robust Regression were used for modeling and predictions. Then the ROC curve was used to validate the results. The results of this validation showed that the partial least squares (PLS) and multiple linear regression (MLR) models with the maximum area under the curve (AUC) (0.983 and 0.997, respectively) and the lowest standard deviation (0.015 and 0.018, respectively) ) have performed better. Among these two models, PLS has slightly better results than MLR. Finally, a random forest model was used to determine the importance of the input factors, and it was found that the factors of height, distance from the waterway and slope percentage are the most influential factors on floods in the study area.

Keywords

Main Subjects

نقشه‌های پهنه‌بندی سیل اطلاعات ارزشمندی را در رابطه با طبیعت سیلاب‌ها و اثرات آن بر اراضی دشت سیلابی ارائه می‌دهند. برای تهیه نقشه حساسیت به وقوع سیل، مجموعه­ای از عوامل مؤثر باید تعریف شود .مجموعه عوامل مؤثر بر سیلاب با استفاده از 13 عامل شامل ارتفاع، شیب، فاصله از رودخانه، شاخص رطوبت توپوگرافی، شاخص موقعیت توپوگرافی، شاخص زبری، سطح  انحنای طولی یا عرضی، مقطع انحنای توپوگرافی، انحنای کلی،شاخص نرمال شده تفاوت پوشش گیاهی (NDVI)، کاربری اراضی، سنگ شناسی و بارندگی با توجه به استفاده از تجربیات کارشناسان و پژوهشگران در بررسی‌های صورت­گرفته، در حوضه شرقی آبریز دریاچه اورمیه استفاده شد. بعد ازآماده سازی لایه‌های موثر بر سیلاب و لایه نقطه­ای نقاط سیل­خیز، و نیز انجام آزمون­ هم‌خطی، در مرحله بعد از پنج روش رگرسیون خطی چندگانه، مدل حداقل مربعات جزئی،  رگرسیون چندکی،  رگرسیون ستیغی و رگرسیون با ثبات برای مدلسازی و پیش‌بینی استفاده شد. از منحنی مشخصه عملکرد (ROC)برای اعتبارسنجی نتایج استفاده گردید. نتایج این اعتبار سنجی نشان داد که مدلهای حداقل مربعات جزئی PLS)) و مدل رگرسیون خطی چندگانه ( MLR) با دارا بودن حداکثر مساحت زیرمنحنی  (AUC)، ( به ترتیب 0.983و 0.997) و کمترین میزان انحراف معیار( به ترتیب 0.015و  0.018)  بهتر عمل کرده اند. در بین این دو مدل هم PLS دارای نتایج کمی بهتر نسبت به MLR می‌باشد. در نهایت فاصله از آبراهه و  درصد شیب تاثیر­گذارترین عوامل روی سیلاب منطقه مورد مطالعه می­باشند.

Al-Abadi, A. M., Al-Temmeme, A. A., & Al-Ghanimy, M. A. 2016. A GIS-based combining of frequency ratio and index of entropy approaches for mapping groundwater availability zones at Badra–Al Al-Gharbi–Teeb areas, Iraq. Sustainable Water Resources Management, 2, 265-283.
Amiri, F., & Tabatabaie, F. 2020. Integration of GIS, remote sensing and Multi-Criteria Evaluation tools in the search for healthy walking paths. Journal of Civil Engineering, 22(1), 279-291. doi:https://doi.org/10.1007/s11104-009-0053-7. (In Persian).
Assaf, A. G., M. Tsionas, & Tasiopoulos, A. 2019. Diagnosing and correcting the effects of multicollinearity: Bayesian implications of ridge regression. Tourism Management, 71, 1-8.
Avand, M.T., Moradi, H.R., & Ramazanzadeh, M. 2020. Preparation of flood sensitivity map using two random forest machine learning models and Bayesian generalized linear model. Environment and Water Engineering, 6(1), 83-95. DOI: 10.22094/joeee.2020.108812.1791.
Bakhtiari,B., Pourghasemi, H.,R., Khorshiddoost, N., Fakheri Fard, A., Mosavi, A. 2017. Flood hazard zoning using process-based and stochastic modeling approaches. Natural Hazards, 2, 1159-1179.
Balan, B., Mohaghegh, S., & Ameri, S. 1995. State-of-the-art in permeability determination from well log data: Part 1-A comparative study, model development. In SPE Eastern Regional Meeting. OnePetro.
Bedini, M., Piroozi, A., Aghayari, L., & Ostadi, A. 2018. Flood risk zoning in Meshkinshahr city using Vikor model. Geography of the Land, 14. OPA: 0.22059/JGEL.2018.250727.1007473.
Buitendag, S., Beirlant, J. & de Wet, T. 2019. Ridge regression estimators for the extreme value index. Extremes, 22(2), 271-292. doi:10.1007/s10687-018-0320-8.
Constantin, M., Bednarik, M., Jurchescu, M. C., & Vlaicu, M. 2011. Landslide susceptibility assessment using the bivariate statistical analysis and the index of entropy in the Sibiciu Basin (Romania). Environmental earth sciences, 63, 397-406.                                                                                                     
Darabi, H., Shahedi, K., Solaimani, K., & Miryaghoubzadeh, M. 2014. Prioritization of subwatersheds based on flooding conditions using hydrological model, multivariate analysis and remote sensing technique. Water and environment journal, 28(3), 382-392.
Ebrahimipour, M., & Ziari, K. 2019. Zoning of urban lands against flood risk with physical resilience approach (Case study: Cheshmeh Kileh river). New Attitudes in Human Geography (Human Geography), 11(1), 83-104.
Esmaeili, H., Akhond Ali, A. M., Zarei, H., & Taghian, M. 2018. Regional Flood Analysis Via Comparison of The M5 Decision Tree Algorithm and Regression Models. Irrigation Sciences and Engineering, 40(4), 183-195.
Faramarzi, H., Hosseini, S. M., Pourghasemi, H. R., & Farneghi, M. 2019. Assessment and Zoning of Flood Risk in Golestan National Park. Iranian journal of Ecohydrology, 6(4), 1055-1068.
Garthwaite, P.H., Jolliffe, I.T. & Jones, B. 1995. Statistical Inference. Prentice-Hall.
Ghanavati, E., Karam, A., & Aghaalikhani, M. 2013. Flood risk zonation in the farahzad basin (Tehran) using Fuzzy model. Geography and Environmental Planning, 23(4), 121-138.
Goodarzi, M., & Fatehifar, A. 2019. Flood risk zoning due to climate change under RCP 8.5 scenario using hydrologic model SWAT in Gis (Azarshahr basin). Journal of Applied Researches in Geographical Sciences, 19(53), 99-117.
Guo, L., Liu, R., Men, C., Wang, Q., Miao, Y., & Zhang, Y. 2019. Quantifying and simulating landscape composition and pattern impacts on land surface temperature: A decadal study of the rapidly urbanizing city of Beijing, China. Science of The Total Environment, 654, 430-440. doi:https://doi.org/10.1007/s11104-009-0053-7.
Hejazi, A., & Khodayee Geshlag, F. 2020. Flood risk zoning in the Varkash Chay catchment using the HEC-RAS model and the HEC-GEO-RAS supplement. Applied Research in Geographical Sciences (Geographical Sciences), 19(53), 75-89.
Jothibasu, A., & Anbazhagan, S. 2016. Modeling groundwater probability index in Ponnaiyar River basin of South India using analytic hierarchy process. Modeling Earth Systems and Environment, 2, 1-14.
Kanani-Sadat, Y., Arabsheibani, R., Karimipour, F., & 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. Journal of hydrology, 572, 17-31.
Khosravi, K., Pham, B. T., Chapi, K., Shirzadi, A., Shahabi, H., Revhaug, I., & 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, 744-755.
Koenker, R. 2005. Quantile Regression. Economic Society Monographs No 38, ed. by Chesher A and Jackson M.
Lin, M., Song, X., Qian, Q., Li, H., Sun, L., Zhu, S., & Jin, R. 2019. Robust gaussian process regression for real-time high precision GPS signal enhancement. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 2838-2847)
Liu, A., G. Shi, S. J. Chung, A. Anandkumar, & Y. Yue. 2019. Robust regression for safe exploration in control. arXiv preprint arXiv:1906.05819.
Malazehi, A., M. Pudineh, M. Khosravi, M. Armesh, & A. Dehvari. 2020. Flood risk potential assessment in Sarbaz catchment. Applied Research in Geographical Sciences (Geographical Sciences), 20 (58).
Moore I.D., R.B. Grayson, A.R. Ladson. 1991. Digital terrain modelling: a review of hydrological, geomorphological, and biological applications. Hydrological processes, 5(1), 3-30.
Naghibi, S. A., Pourghasemi, H. R., Pourtaghi, Z. S., & Rezaei, A. 2015. Groundwater qanat potential mapping using frequency ratio and Shannon’s entropy models in the Moghan watershed, Iran. Earth Science Informatics, 8, 171-186.
Nouri, H., Ildoromi, A., Sepehri, M., & Artimani, M. 2019. Comparing Three Main Methods of Artificial Intelligence in Flood Estimation in Yalphan Catchment. Geography and Environmental Planning, 29(4), 35-50.
Rahimi, L., Saboori, S., & Bordbar, H. 2019. Investigating the effect of flood risk perception on preventive behaviors through the attachment to place component (Case Study: Babol city). Geography and Development, 17(57), 49-68.
Rajabi, M., Roostaei, S., Barzkar, M. 2022. Evaluation of flood potential under basins based on morphometric parameters and correlation test(Case: Zab catchment to Mirabad), Journal of Geography and Planning, 26(79), 127-139. magiran.com/p2431487
Rezvani Faezifar, R., Safari, A., Bahroudi, A., & Ramouz, S. 2022. Feasibility study of forecasting the flood occurrence using GRACE satellite gravity data in the Karun river basin, Iran. Iranian Journal of Geophysics, 16(1), 103-117.
Rostami Khalaj, M., Hesami, D., Salmani, H., & Tymoriyan, T. 2020. Urban Flood Hazard Zoning Using Multicriteria Decision Analysis (Emam Ali town, Mashhad city). Journal of Environmental Science and Technology, 21(11), 
Salehi, A., Rafiei, Y., Farzad Behtash, M. & Aghababaei, M. 2014. Urban flood risk zoning using GIS and fuzzy hierarchical analysis process (Case study: Tehran). Environmental Science, 39(3).
Sattari, M., Abdollah Pourazad, M. & Mir Abbasi Najafabadi, R. 2017. Technical report: Predicting hourly floods of Ahrachai river using machine learning methods. Watershed Engineering and Management, 8(1).
Sharifi Garmadreh, E., Vafakhah, M., Eslamian, S. S. 2020. Evaluation of the efficiency of support vector machine systems and artificial neural network in flood zone analysis (Case study: Salt Lake watershed). Journal of Soil and Water Sciences, 23(1), 351-366.
Siahkamari, S., Haghizadeh, A., Zeinivand, H., Tahmasebipour, N., & Rahmati, O. 2018. Spatial prediction of flood-susceptible areas using frequency ratio and maximum entropy models. Geocarto international, 33(9), 927-941.
Tehrany, M. S., B. Pradhan, S. Mansor, & N. Ahmad. 2015. Flood susceptibility assessment using GIS-based support vector machine model with different kernel types. Catena, 125, 91-101.
Yesilnacar, E.K.2005. The application of computational intelligence to landslide susceptibility mapping
Remote Sensing and GIS Applications in Environmental Sciences
Volume 3, Issue 7 - Serial Number 6
July 2023
Pages 55-24
  • Receive Date: 02 January 2023
  • Revise Date: 24 September 2023
  • Accept Date: 06 November 2023