Remote Sensing and GIS Applications in Environmental Sciences

Evaluation and Prediction of Flood Prone Areas Using Random Forest Algorithm

Document Type : Original Article

Authors

1 Hakim Sabzevari University - Faculty of Geography and Environmental Sciences

2 Hakim Sabzevari University - Faculty of Geography and Environmental Sciences - Department of Climate and Geomorphology

3 Department of Remote sensing and Geographic Information System, Faculty of Geography and Environmental sciences, Hakim sabzevari University, Sabzevar, Iran

10.22034/rsgi.2025.61009.1069

Abstract

Floods, as one of the three primary natural hazards in Iran, cause significant damage annually to the environment, infrastructure, and livelihoods. This study aimed to map flood hazard zones in the Davarzan region and identify the key factors contributing to flood occurrence using the Random Forest algorithm. Sixteen environmental indicators, including elevation, slope, precipitation, geology, geomorphology, land use, plan curvature, profile curvature, topographic wetness index (TWI), proximity to stream, stream density, train ruggedness index (TRI), Normalized difference vegetation index (NDVI), Stream power index (SPI), geology and soil were included in the analysis. The Information Gain Ratio (IGR) was used to determine the importance of each factor, and less significant variables were excluded from the modeling process. The results showed that elevation, precipitation, and land use were the most influential factors in flood occurrence. According to the flood hazard mapping, approximately 67% of the study area is at high risk, 5% at very high risk, 6% at moderate risk, and 22% at low to very low risk. Additionally, it was found that about 50% of urban and rural areas are in high-risk zones, emphasizing the need for preventive measures. This research demonstrated that the Random Forest algorithm, in addition to providing precise hazard mapping, serves as an effective tool for flood management. Strategies such as enhancing vegetation cover, revising land-use practices, improving drainage infrastructure, and reevaluating the location of residential areas can significantly reduce flood-related damages. The study's findings offer a valuable basis for managerial decision-making in Davarzan and similar regions.

Keywords

Main Subjects

رخداد سیل به‌عنوان یکی از سه مخاطره طبیعی اصلی در ایران، هر ساله خسارات چشمگیری به محیط‌زیست، زیرساخت‌ها، و زندگی مردم وارد می‌کند. در پژوهش حاضر، با هدف پهنه‌بندی خطر سیلاب در شهرستان داورزن و شناسایی عوامل مؤثر بر وقوع آن، از الگوریتم جنگل تصادفی و تحلیل داده‌های مکانی استفاده شد. 16 شاخص محیطی از جمله ارتفاع، شیب، بارش، زمین‌شناسی، ژئومورفولوژی، کاربری اراضی، انحنای زمین، شاخص رطوبت توپوگرافی، تراکم و فاصله از آبراهه‌ها در تحلیل‌ها گنجانده شدند. به‌منظور تعیین درجه اهمیت هر عامل، از شاخص ارزش اطلاعاتی (IGR) بهره گرفته شد و عوامل کم‌اهمیت از فرآیند مدل‌سازی حذف شدند. نتایج پژوهش نشان داد که ارتفاع، بارش و کاربری اراضی به‌ترتیب از مهم‌ترین عوامل در وقوع سیلاب هستند. بر اساس نقشه پهنه‌بندی خطر، حدود 67 درصد منطقه مورد مطالعه در معرض خطر زیاد، 5 درصد در معرض خطر بسیار زیاد، 6 درصد خطر متوسط، و 22 درصد در معرض خطر کم تا بسیار کم قرار دارند. همچنین، مشخص شد که حدود 50 درصد از مناطق شهری و روستایی در مناطق پرخطر واقع شده‌اند که این موضوع لزوم اقدامات پیشگیرانه را برجسته می‌کند. این پژوهش نشان داد که استفاده از الگوریتم جنگل تصادفی، علاوه بر ارائه پهنه‌بندی دقیق، ابزاری کارآمد برای مدیریت سیلاب و کاهش خطرات آن است. راهکارهایی مانند توسعه پوشش گیاهی، اصلاح کاربری اراضی، بهبود زیرساخت‌های زهکشی و بازنگری در جانمایی مناطق مسکونی می‌توانند نقش مؤثری در کاهش آسیب‌های ناشی از سیلاب ایفا کنند. نتایج تحقیق می‌تواند مبنای مناسبی برای تصمیم‌گیری‌های مدیریتی و توسعه پایدار در منطقه داورزن و سایر مناطق مشابه باشد.

Bostani, Alireza and Javani, Khadijah, (2013). investigation and recognition of natural hazards (earthquakes and floods) and their effects on the vulnerability of villages (a case study of villages in Darab city). P.1800-1811. the second international conference on environmental hazards, Tehran, (In Persian).
Bui, D. T., Hoang, N. D., Martínez-Álvarez, F., Ngo, P. T. T., Hoa, P. V., Pham, T. D., … & Costache, R. (2020). A novel deep learning neural network approach for predicting flash flood susceptibility: A case study at a high frequency tropical storm area. Science of the Total Environment, 701, 134413. https://doi.org/10.1016/j.scitotenv.2019.134413.
Bui, D. T., Ngo, P. T. T., Pham, T. D., Jaafari, A., Minh, N. Q., Hoa, P. V., & Samui, P. (2019). A novel hybrid approach based on a swarm intelligence optimized extreme learning machine for flash flood susceptibility mapping. Catena, 179, 184-196. https://doi.org/10.1016/j.catena.2019.04.009.
Campolo, M., Andreussi, P., & Soldati, A. (1999). River flood forecasting with a neural network model. Water resources research, 35(4), 1191-1197. https://doi.org/10.1029/1998WR900086.
Chen, W.; Zhai, G.; Fan, C.; Jin, W. and Xie, Y., (2017), A planning framework based on system Theory and GIS for urban emergency shelter system: a case of Guangzhou, China, Human and Ecological Risk Assessment, An International Journal, 23(3), 1-16. ­https://doi.org/10.1080/10807039.­2016.1185692.
Choubin, B., Khalighi-Sigaroodi, S., Malekian, A., & Kişi, Ö. (2016). Multiple linear regression, multi-layer perceptron network and adaptive neuro-fuzzy inference system for forecasting precipitation based on large-scale climate signals. Hydrological sciences journal, 61(6), 1001-1009. https://doi.org/10.1080/02626667.­2014.966721.
Darabi, H., Choubin, B., Rahmati, O., Haghighi, A. T., Pradhan, B., & Kløve, B. (2019). Urban flood risk mapping using the GARP and QUEST models: A comparative study of machine learning techniques. Journal of hydrology, 569, 142-154. https://doi.org/10.1016/j.jhydrol.2018.12.002.
Esfandiari Darabad, Fariba, Rahimi, Massoud, and Pourmorteza, Gholamreza. (2018). Flood zoning of Ajarlo Chai catchment area using L-THIA method and fuzzy logic. Quantitative Geomorphology Research, 8(2), 155-171, (in Persian with English abstract).
Firoozishahmirzadi, P., Rahimi, S., & Esmaeili Seraji, Z. (2021). Application of Machine Learning Models for flood risk assessment and producing map to identify flood prone areas: Literature Review. International Journal of Data Envelopment Analysis, 9(4), 43-88. https://doi.org/10.30495/ijdea.2022.68987.1181.
Florinsky, I. (2016). Digital terrain analysis in soil science and geology. Academic Press.
Green, C., Diepernk, G., EK, K., Hegger, D., Pettersson, M., Priest, S., Tapsell, Ghafory, M., (2005). Erthquak Risk management Strategies: the Iranian Experience, Tehran UNESCO Office and International Institte of Erthquake Engineering and seismology (IIEFS). pp. 9-1.
Hosseini, F. S., Choubin, B., Mosavi, A., Nabipour, N., Shamshirband, S., Darabi, H., & Haghighi, A. T. (2020). Flash-flood hazard assessment using ensembles and Bayesian-based machine learning models: Application of the simulated annealing feature selection method. Science of the total environment, 711, 135161. https://doi.org/10.1016/j.scitotenv.2019.135161.
Huang, Sha, et al. (2021). A commentary review on the use of normalized difference vegetation index (NDVI) in the era of popular remote sensing. Journal of Forestry Research, 32(1), 1-6. ­https://doi.org/10.1007/s­11676-­020-01155-1.
Lee, S., Kim, J. C., Jung, H. S., Lee, M. J., & Lee, S. (2017). Spatial prediction of flood susceptibility using random-forest and boosted-tree models in Seoul metropolitan city, Korea. Geomatics, Natural Hazards and Risk, 8(2), 1185-1203. https://doi.org/10.1080/19475705.2017.1308971.
Liao, Y., Wang, Z., Lai, C., & Xu, C. Y. (2023). A Framework on Fast Mapping of Urban Flood Based on a Multi-Objective Random Forest Model. International Journal of Disaster Risk Science, 1-16. https://doi.org/10.1007/s13753-023-00481-2.
Omidfarfar, Sajjad and Hosseini, Seyedah Laila and Fakhari, Zahra and Qanbari, Samaneh, (2021), Zoning and flood risk assessment in Tabriz city using Fuzzy AHP model. P.3425-3438. 2nd International Conference and 5th National Conference on Protection of Natural Resources and Environment Ardabil, (In Persian).
Patwardhan، A., (2004). The methodology for assessing natural hazard impacts. Global and planetary change, (47), 265  253. https://doi.org/10.1016/j.gloplacha.2004.10.015.
Rad, M. R. P., Toomanian, N., Khormali, F., Brungard, C. W., Komaki, C. B., & Bogaert, P. (2014). Updating soil survey maps using random forest and conditioned Latin hypercube sampling in the loess derived soils of northern Iran. Geoderma, 232, 97-106. https://doi.org/10.1016/j.geoderma.2014.04.036 .
Rahmati, O., & Pourghasemi, H. R. (2017). Identification of critical flood prone areas in data-scarce and ungauged regions: a comparison of three data mining models. Water resources management, 31, 1473-1487. https://doi.org/10.1007/s11269-017-1589-6.
Saeedi, S., & Asiaei, M. (2021). Flood Risk Zoning in Sabzevar Using Fuzzy Logic. Quarterly Journals of Urban and Regional Development Planning, 5(15), 27-49, (In Persian). https://doi.org/10.22054/urdp.2021.­61580.1348.
Shamsipour, Ali Akbar, Alavi Panah, Seyyed Kazem, & Mohammadi, Hossein. (2010). Investigating the effectiveness of NOAA-AVHRR satellite's vegetation and thermal indices in drought analysis of Kashan region. Iran Pasture and Desert Research, 17 (3), 445-465. (in Persian with English abstract).
Taha, M. M. N; Elbarbary, S. M; Naguib, D. M; El-Shamy, I. Z (2017). “Flash flood hazard zonation based on basin morphometry using remote sensing and GIS techniques: A case study of Wadi Qena basin, Eastern Desert, Egypt”. Remote Sensing Applications: Society and Environment. 8, 157–167. https://doi.org/10.1016/j.rsase.2017.08.007.
Taherkhani, M., sojasi qeydari, H., & sadeghloo, T. (2012). Comparative Assessment of Ranking Methods for Natural Disasters in Rural Regions (Case Study: Zanjan Province). Journal of Rural Research, 2(7), 31-54. (In Persian with English abstract).
Tehrany, M. S., Jones, S., & Shabani, F. (2019). Identifying the essential flood conditioning factors for flood prone area mapping using machine learning techniques. Catena, 175, 174-192. https://doi.org/10.1016/­j.catena.­2018.12.011.
Tehrany, M. S., Pradhan, B., & 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. https://doi.org/10.1016/j.jhydrol.2013.09.034.
Tehrany, M. S., Pradhan, B., & Jebur, M. N. (2014). Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS. Journal of hydrology, 512, 332-343. https://doi.org/10.1016/j.jhydrol.2014.03.008.
Termeh, S. V. R., Kornejady, A., Pourghasemi, H. R., & Keesstra, S. (2018). Flood susceptibility mapping using novel ensembles of adaptive neuro fuzzy inference system and metaheuristic algorithms. Science of the Total Environment, 615, 438-451. https://doi.org/10.1016/j.scitotenv.2017.09.262.
Tierolf, L., de Moel, H., & van Vliet, J. (2021). Modeling urban development and its exposure to river flood risk in Southeast Asia. Computers, Environment and Urban Systems, 87, 101620. https://doi.org/10.1016/j.­compenvurbsys.2021.101620.
United Nations Climate (2015). The human cost of weather-related disasters 1995- 2015. pp119.
Remote Sensing and GIS Applications in Environmental Sciences
Volume 6, Issue 18
April 2026
Pages 17-1
  • Receive Date: 27 March 2024
  • Revise Date: 01 February 2025
  • Accept Date: 23 April 2025