Spatial Prediction of Flood Susceptibility in the Zarineh-Rud Watershed using a Simple Bayes Machine-Learning Model

Document Type : Research

Authors

1 Ph.D. Student, Department of Arid and Mountain Reclamation Engineering, Faculty of Natural Resources, University of Tehran, Karaj, Iran

2 Deputy of Watershed Management, General Directorate of Natural Resources and Watershed Management of Kurdistan Province, Sanandaj, Iran

10.22092/wmrj.2025.369572.1623

Abstract

Introduction and Goal
Floods cause numerous financial losses and loss of life every year, and have a devastating impact on the sustainable development of the country. However, generally, actual flood events have not been used in spatial analysis and modeling, and flood susceptibility maps have been prepared solely based on expert opinions and multi-criteria decision-making methods. On the other hand, management plans and actions of executive agencies are usually developed without considering the different flood-prone areas of watersheds. This study was conducted with the aim of utilizing observational data of flooding events and determining the efficiency of the Naive Bayes model in spatial prediction of flooding susceptibility in the Zarineh-Rud watershed.
Materials and Methods
The flood events database was prepared based on flood event information in the Zarineh-Rud watershed recorded by the Provincial Disaster Management Office and the Regional Water Company. Given that various environmental factors play a role in the formation of floods and inundation of lands adjacent to rivers, flood modeling is not possible without considering them. Therefore, after reviewing various sources, thirteen environmental factors affecting flooding were selected, including land elevation, slope direction, drainage density, land use, lithology, surface curvature, cross-sectional curvature, average annual rainfall, slope percentage, soil texture, flow power index, distance from the watercourse, and topographic moisture index. The multicollinearity of environmental factors was examined using the tolerance factor statistic. Raster layers of environmental factors were introduced as independent variables into the Naive Bayes model. The flood event locations were divided into two groups, training and validation, based on the spatial random method with a ratio of 30 and 70 %. After running the model, a flood susceptibility map of the Zarineh-Rud watershed was produced, in which each cell represents the probability of flooding in that area. The accuracy of the flood susceptibility map was evaluated using independent and threshold-dependent statistics and validation group data.
Results and Discussion
Based on the results of this study, the independent variables considered were without multicollinearity and could be used as predictors in the modeling process. The validation results based on the area under the receiver operating characteristic curve statistic showed that the flood susceptibility map has an accuracy of 93.6%. According to the threshold-dependent statistics, the efficiency of the Naive Bayes machine learning model was obtained as 85.7 based on the Accuracy statistic, 82.6% based on the Precision statistic, and 90.4% based on the Recall statistic.
Conclusion and Suggestions
The performance of the Naive Bayes machine learning model was suitable for spatial prediction of flood susceptibility at the watershed scale and various variables can be used for spatial analysis. The flood susceptibility map should be considered as the basis for planning river regulation operations (such as building coastal walls and removing bed layers), flood management (such as respecting river boundaries), and watershed management (such as building watershed management structures in the upstream of flood-prone areas) in the Zarineh-Rud watershed. Therefore, it is suggested that this model be used to prepare flood susceptibility maps based on historical flood data in other basins of the country.

Keywords

Main Subjects

References

Aalami M, Ardestani M, Malekmohammadi B. 2024. Flood potential modeling in Zarineh Rood watershed using artificial intelligence models. Watershed Management Research. 37(1): 2-17. (In Persian). DOI: 10.22092/WMRJ.2023.360973.1513
Abedi R, Costache R, Shafizadeh-Moghadam H, Pham QB. 2022. Flash-flood susceptibility mapping based on XGBoost, random forest and boosted regression trees. Geocarto International. 37(19): 5479-5496. DOI: 10.1080/10106049.2021.1920636
Arabameri A, Saha S, Mukherjee K, Blaschke T, Chen W, Ngo PTT, Band SS. 2020. Modeling spatial flood using novel ensemble artificial intelligence approaches in northern Iran. Remote Sensing. 12(20): p.3423. DOI: 10.3390/rs12203423
Arabameri A, Seyed Danesh A, Santosh M, Cerda A, Chandra Pal S, Ghorbanzadeh O, Chowdhuri I. 2022. Flood susceptibility mapping using meta-heuristic algorithms. Geomatics, Natural Hazards and Risk. 13(1): 949-974.DOI: 10.1080/19475705.2022.2060138
Barati GR, Bodagh Jamali J, Maleki N. 2012. Anticyclones and Heavy Rainfalls over Western Iran. Physical Geography Research. 44(2): 85-98. (In Persian). DOI: 10.22059/jphgr.2012.29208
Berrar, D. 2025. Bayes’ Theorem and Naive Bayes Classifier. Encyclopedia of Bioinformatics and Computational Biology (Second Edition). pp. 483-494. DOI: 10.1016/B978-0-323-95502-7.00118-4
Chan JYL, Leow SMH, Bea KT, Cheng WK, Phoong SW, Hong ZW, Chen YL. 2022. Mitigating the multicollinearity problem and its machine learning approach: A review. Mathematics. p.1283. DOI:10.3390/math10081283
Chowdhury ME, Islam AS, Zzaman RU, Khadem S. 2025. A machine learning-based approach for flash flood susceptibility mapping considering rainfall extremes in the northeast region of Bangladesh. Advances in Space Research. 75(2):1990-2017. DOI: 10.1016/j.asr.2024.10.047
Chen J, Huang G, Chen W. 2021. Towards better flood risk management: Assessing flood risk and investigating the potential mechanism based on machine learning models. Journal of Environmental Management. p.112810. DOI: 10.1016/j.jenvman.2021.112810
Chen W, Li Y, Xue W, Shahabi H, Li S, Hong H, Wang X, Bian H, Zhang S, Pradhan B, Ahmad BB. 2020. Modeling flood susceptibility using data-driven approaches of naïve bayes tree, alternating decision tree, and random forest methods. Science of the Total Environment. p.134979. DOI: 10.1016/j.scitotenv.2019.134979
Choubin B, Hosseini FS, Rahmati O, Youshanloei MM. 2023. A step toward considering the return period in flood spatial modeling. Natural Hazards. 115(1): 431-460. DOI: 10.1007/s11069-022-05561-y
Choubin B, Sajedi Hosseini F, Rahmati O. 2025. Spatial Analysis of Vulnerability in Zarrinehrood Watershed to Flood Occurrence. Iranian Journal of Watershed Management Science 18(67): 73-86. (In Persian). DOI: 10.22034/18.67.6
Dutta P, Deka S. 2024. A novel approach to flood risk assessment: Synergizing with geospatial based MCDM-AHP model, multicollinearity, and sensitivity analysis in the Lower Brahmaputra Floodplain, Assam. Journal of Cleaner Production. p.142985. DOI: 10.1016/j.jclepro.2024.142985
Frattini P, Crosta G, Carrara A. 2010. Techniques for evaluating the performance of landslide susceptibility models. Engineering geology. 111(1-4): 62-72. DOI: 10.1016/j.enggeo.2009.12.004
Habibi A, Delavar MR, Sadeghian MS, Nazari B. 2023. Flood Susceptibility Mapping and Assessment Using Regularized Random Forest and NAÏVE Bayes Algorithms. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 10: 241-248. DOI: 10.5194/isprs-Annals-X-4-W1-2022-241-2023
Hosseini SA, Ahmadi H, Houshyar M. 2021. Analysis of Rainfall System, Leading to Floods in July 2015 in Saghez City in Kurdistan Province. Integrated Watershed Management, 1(1): 45-62. (In Persian). DOI: 10.22034/iwm.2021.247942
Khajehnejad R, Bahremand A, Mohammadrezaei M. 2024. An overview of integrated flood management in Iran: current status and challenge. Journal of Aquifer and Qanat. 5(1): 183-202. (In Persian). DOI: 10.22077/jaaq.2024.8149.1077
Maswadi K, Ghani NA, Hamid S, Rasheed MB, 2021. Human activity classification using Decision Tree and Naïve Bayes classifiers. Multimedia Tools and Applications. 80: 21709-21726. DOI: 10.1007/s11042-020-10447-x
Moazzam MFU, Lee BG, Rahman AU, Farid N, Rahman G. 2020. Spatio-statistical analysis of flood susceptibility assessment using bivariate model in the floodplain of river swat, district charsadda, Pakistan. Journal of Geoscience and Environment Protection. 8(05): 159. DOI: 10.4236/gep.2020.85010
Pajila PB, Sheena BG, Gayathri A, Aswini J, Nalini M. 2023, September. A comprehensive survey on naive bayes algorithm: Advantages, limitations and applications. In 2023 4th International Conference on Smart Electronics and Communication (ICOSEC). pp. 1228-1234. DOI: 10.1109/ICOSEC58147.2023.10276274
Pal S, Singha P. 2022. Analyzing sensitivity of flood susceptible model in a flood plain river basin. Geocarto International. 37(24):7186-7219. DOI: 10.1080/10106049.2021.1967464
Pham BT, Phong TV, Nguyen HD, Qi C, Al-Ansari N, Amini A, Ho LS, Tuyen TT, Yen HPH, Ly HB, Prakash I. 2020. A comparative study of kernel logistic regression, radial basis function classifier, multinomial naïve bayes, and logistic model tree for flash flood susceptibility mapping. Water. p.239. DOI: 10.3390/w12010239
Qi W, Ma C, Xu H, Chen Z, Zhao K, Han H, 2021. A review on applications of urban flood models in flood mitigation strategies. Natural Hazards. 108: 31-62. DOI: 10.1007/s11069-021-04715-8
Rahmati O, Darabi H, Panahi M, Kalantari Z, Naghibi SA, Ferreira CSS, Kornejady A, Karimidastenaei Z, Mohammadi F, Stefanidis S, Tien Bui D. 2020. Development of novel hybridized models for urban flood susceptibility mapping. Scientific Reports. p.12937. DOI: 10.1038/s41598-020-69703-7
Rahmati O, Kornejady A, Choubin B, Jaafari A, Amini A. 2024. Evaluating the performance of the flexible discriminant analysis model in predicting the flooding potential of the Zarrineh-Rood Watershed. Water and Soil Management and Modelling. 4(3): 269-284. DOI: 10.22098/mmws.2023.13102.1303
Rahmati O, Kornejady A, Samadi M, Deo RC, Conoscenti C, Lombardo L, Dayal K, Taghizadeh-Mehrjardi R, Pourghasemi HR, Kumar S, Bui DT. 2019. PMT: New analytical framework for automated evaluation of geo-environmental modelling approaches. Science of the Total Environment. 664: 296-311. DOI: 10.1016/j.scitotenv.2019.02.017
Rajabizadeh Y, Ayyoubzadeh SA, Zahiri A. 2019. Flood Survey of Golestan Province in 2018-2019 and Providing Solutions for Its Control and Management in the Future. Journal of Ecohydrology. 6(4): 921-942. (In Persian). DOI: 10.22059/ije.2019.283004.1137
Samanta S, Pal DK, Palsamanta B. 2018. Flood susceptibility analysis through remote sensing, GIS and frequency ratio model. Applied Water Science. p. 66. DOI: 10.1007/s13201-018-0710-1
Seleem O, Ayzel G, de Souza ACT, Bronstert A, Heistermann M. 2022. Towards urban flood susceptibility mapping using data-driven models in Berlin, Germany. Geomatics, Natural Hazards and Risk. 13(1): 1640-1662. DOI: 10.1080/19475705.2022.2097131
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. DOI: 10.1080/10106049.2017.1316780
Sulaiman MS, Abood MM, Sinnakaudan SK, Shukor MR, You GQ, Chung XZ. 2021. Assessing and solving multicollinearity in sediment transport prediction models using principal component analysis. ISH Journal of Hydraulic Engineering. 27(sup1). pp. 343-353. DOI: 10.1080/09715010.2019.1653799
Tehrany MS, Kumar L. 2018. The application of a Dempster–Shafer-based evidential belief function in flood susceptibility mapping and comparison with frequency ratio and logistic regression methods. Environmental Earth Sciences. 77: 1-24. DOI: 10.1007/s12665-018-7667-0
Traoré K, Fowe T, Ouédraogo M, Zorom M, Bologo/Traoré M, Toé P, Karambiri H. 2024. Mapping urban flood susceptibility in Ouagadougou, Burkina Faso. Environmental Earth Sciences. p. 561. DOI: 10.1007/s12665-024-11871-0
Thapa PS, Chaudhary S, Dasgupta P. 2022. Contribution of integrated watershed management (IWM) to disaster risk reduction and community development: Lessons from Nepal. International Journal of Disaster Risk Reduction. p.103029. DOI: 10.1016/j.ijdrr.2022.103029
Wang H, Wang H, Wu Z, Zhou Y. 2021. Using multi-factor analysis to predict urban flood depth based on Naive Bayes. Water. 432. DOI: 10.3390/w13040432
Wickramasinghe I, Kalutarage H. 2021. Naive Bayes: applications, variations and vulnerabilities: a review of literature with code snippets for implementation. Soft Computing. 25(3):2277-2293. DOI: 10.1007/s00500-020-05297-6
Widya LK, Rezaie F, Lee W, Lee CW, Nurwatik N, Lee S. 2024. Flood susceptibility mapping of Cheongju, South Korea based on the integration of environmental factors using various machine learning approaches. Journal of Environmental Management. p.121291. DOI: 10.1016/j.jenvman.2024.121291
Watershed Management Research
Volume 38, Issue 4 - Serial Number 149
January 2026
Pages 108-127

Files

History

  • Receive Date: 25 May 2025
  • Revise Date: 01 June 2025
  • Accept Date: 21 June 2025

Share

How to cite

Statistics