Water Resources Management

, Volume 33, Issue 13, pp 4621–4636 | Cite as

Performance Evaluation of a Fuzzy Hybrid Clustering Technique to Identify Flood Source Areas

  • Naser Dehghanian
  • S. Saeid Mousavi NadoushaniEmail author
  • Bahram Saghafian
  • Ruhangiz Akhtari


Prioritization of flood source areas (FSAs) is of paramount importance in flood management to adopt proportional measures within a watershed. Unit Flood Response (UFR) approach has been proposed to identify FSAs at subwatershed and/or cell scale. In this study, a distributed modified Clark (ModClark) model coupled with Muskingum flow routing method was used for hydrological simulations. Furthermore, SOMFCM clustering techniques involving Self-Organizing Feature Maps (SOFM) and Fuzzy C-Means algorithm (FCM) were used to identify Hydrologic Homogenous Regions (HHRs). The case studies were two semi-arid watersheds including Tangrah in northeastern Iran and eastern part of Walnut Gulch Experimental Watershed (WGEW) in Arizona. DEM-derived geomorphological and hydrological features were entered into Factor Analysis (FA) to determine the most effective variables in runoff generation. The optimum SOMFCM resulted in clustered HHRs map which was generally similar to that of the UFR-delineated FSAs at cell scale, especially in cases of maximum flood index values for both watersheds. Although clustering techniques, such as SOMFCM, cannot directly provide a map of FSAs involving absolute values of flood index, most dominant watershed physical features may be used to identify the most critical, or effective FSAs through clustered HHRs. Application of SOMFCM in two semi-arid watersheds demonstrated that SOMFCM provides a simple and useful tool to qualitatively identify the ranking of FSAs across a watershed. Therefore, the clustered HHRs involving higher ranks of FSAs that represent the most flood active regions, are expected to assist policymakers for effective management of floods.


Flood source areas (FSAs) Fuzzy C-means algorithm (FCM) Hydrologic homogenous regions (HHRs) Distributed ModClark Self-organizing feature maps (SOFM) Unit flood response (UFR) 



The authors appreciate the data provided by the USDA-ARS Southwest Watershed Research Center in Tucson Arizona, USA. The authors would also like to offer their special thanks to Dr. Mohammad Elmi for his help in software development.

Compliance with Ethical Standards

Conflict of Interest



  1. Ahani A, Nadoushani SSM, Moridi A (2018) A feature weighting and selection method for improving the homogeneity of regions in regionalization of watersheds. Hydrol Process 32:2084–2095. CrossRefGoogle Scholar
  2. Araghinejad S (2014) Data-driven modeling: using MATLAB® in water resources and environmental engineering. WSTL, vol. 67. Springer, Dordrecht. CrossRefGoogle Scholar
  3. Agarwal A, Maheswaran R, Kurths J, Khosa R (2016) Wavelet Spectrum and self-organizing maps-based approach for hydrologic regionalization -a case study in the Western United States. Water Resour Manag 30:4399–4413. CrossRefGoogle Scholar
  4. Basu B, Srinivas VV (2015) Analytical approach to quantile estimation in regional frequency analysis based on fuzzy framework. J Hydrol 524:30–43CrossRefGoogle Scholar
  5. Bezdek JC (1974) Cluster validity with fuzzy sets. J Cybernet 3:58–74CrossRefGoogle Scholar
  6. Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum Press, New YorkCrossRefGoogle Scholar
  7. Bloschl G, Sivapalan M (1995) Scale issues in hydrological modelling: a review. Hydrol Process 9:251–290CrossRefGoogle Scholar
  8. Burrough PA, van Gaans PFM, Hootsmans R (1997) Continuous classification in soil survey: spatial correlation, confusion and boundaries. Geoderma 77:115–135CrossRefGoogle Scholar
  9. Chen J, Zhao S, Wang H (2011) Risk analysis of flood disaster based on fuzzy clustering method. Energy Procedia 5:1915–1919CrossRefGoogle Scholar
  10. Farsadnia F, Rostami K, Moghaddam M, Modarres R, Bray MT, Han D, Sadatinejad J (2014) Identification of homogeneous regions for regionalization of watersheds by two-level self-organizing feature maps. J Hydrol 509:387–397CrossRefGoogle Scholar
  11. Foda RF, Awadallah AG, Gad MA (2017) A fast semi distributed rainfall runoff model for engineering applications in arid and semi-arid regions. Water Resour Manag 31(15):4941–4955CrossRefGoogle Scholar
  12. Fukuyama Y, Sugeno M (1989) A new method of choosing the number of clusters for the fuzzy c-means method. In: Proceedings of the fifth fuzzy systems symposium, Ankara, Turkey: 247–250Google Scholar
  13. Golian S, Saghafian B, Maknoon R (2010) Derivation of probabilistic thresholds of spatially distributed rainfall for flood forecasting. Water Resour Manag 24(13):3547–3559CrossRefGoogle Scholar
  14. Gopakumar R, Takara K, James EJ (2007) Hydrologic data exploration and river flow forecasting of a humid Tropical River basin using artificial neural networks. Water Resour Manag 21:1915–1940. CrossRefGoogle Scholar
  15. Huff FA (1967) Time distribution of rainfall in heavy storms. Water Resour Res 3(4):1007–1019. CrossRefGoogle Scholar
  16. Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 43:59–69CrossRefGoogle Scholar
  17. Kull DW, Feldman AD (1998) Evaluation of Clark’s unit graph method to spatially distributed runoff. ASCE J Hydrol Eng 3(1):9–19. CrossRefGoogle Scholar
  18. Kwon SH (1998) Cluster validity index for fuzzy clustering. Electron Lett 34(22):176–2177CrossRefGoogle Scholar
  19. Nadoushani SSM, Dehghanian N, Saghafian B (2018) A fuzzy hybrid clustering method for identifying hydrologic homogeneous regions. J Hydroinf 20(6):1367–1386. CrossRefGoogle Scholar
  20. Nourani V, Alami MT, Daneshvar F (2015) Self-organizing map clustering technique for ANN-based spatiotemporal modeling of groundwater quality parameters. J Hydroinform 18(2):288–309CrossRefGoogle Scholar
  21. Pal NR, Bezdek JC (1995) on cluster validity for fuzzy c-means model. IEEE Trans Fuzzy Syst 3:370–379CrossRefGoogle Scholar
  22. Rao AR, Srinivas VV (2006) Regionalization of watersheds by fuzzy cluster analysis. J Hydrol 318(1–4):57–79CrossRefGoogle Scholar
  23. Rao AR, Srinivas VV (2008) Regionalization of watersheds - an approach based on cluster analysis. Water science and technology library, Vol. 58. Springer Netherlands, science+business media B. V., pp. 248Google Scholar
  24. Rousseeuw PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53–65CrossRefGoogle Scholar
  25. Saadat H, Adamowski J, Bonnell R, Sharifi F, Namdar M, Ale-Ebrahim S (2011) Land use and land cover classification over a large area in Iran based on single date analysis of satellite imagery. ISPRS J Photogramm Remote Sens 66(5):608–619CrossRefGoogle Scholar
  26. Saghafian B, Khosroshahi M (2005) Unit response approach for priority determination of flood source areas. ASCE J Hydrol Eng 25:270–277. CrossRefGoogle Scholar
  27. Saghafian B, Golian S, Ghasemi A (2014) Flood frequency analysis based on simulated peak discharges. Nat Hazards 71:403–417. CrossRefGoogle Scholar
  28. Saghafian B, Meghdadi A (2015) Sima S (2015) application of the WEPP model to determine sources of run-off and sediment in a forested watershed. Hydrol Process 29:481–497CrossRefGoogle Scholar
  29. Sanyal J, Densmore AL, Caronneau P (2014) Analyzing the effect of land-use/cover changes at sub-catchment levels on downstream flood peaks: a semi-distributed modelling approach with sparse data. Catena 118:28–40. CrossRefGoogle Scholar
  30. Singh KK, Singh A (2017) Identification of flooded area from satellite images using hybrid Kohonen fuzzy C-means sigma classifier. Egypt J Remote Sens Space Sci 20 (147–155). doi: CrossRefGoogle Scholar
  31. Srinivas VV, Tripathi S, Rao AR, Govindaraju RS (2008) Regional flood frequency analysis by combining self-organizing feature map and fuzzy clustering. J Hydrol 348:148–166CrossRefGoogle Scholar
  32. United States Army Corps of Engineers (USACE) (2006) Hydrologic modeling system HEC-HMS user’s manual. Hydrologic Engineering Center, Davis, CAGoogle Scholar
  33. USDA, United States Department of Agriculture (2007) Agricultural Research Service, Southwest Watershed Research Center, Tucson, Arizona. <> (Aug. 17, 2018)
  34. Ward JH Jr (1963) Hierarchical grouping to optimize an objective function. J Am Stat Assoc 58:236–244CrossRefGoogle Scholar
  35. Weiss A (2001) Topographic position and landforms analysis. ESRI User Conference, San Diego, CAGoogle Scholar

Copyright information

© Springer Nature B.V. 2019

Authors and Affiliations

  • Naser Dehghanian
    • 1
  • S. Saeid Mousavi Nadoushani
    • 1
    Email author
  • Bahram Saghafian
    • 2
  • Ruhangiz Akhtari
    • 3
  1. 1.Department of Water Resources Management, Faculty of Civil, Water and Environmental EngineeringShahid Beheshti UniversityTehranIslamic Republic of Iran
  2. 2.Department of Technical and Engineering, Science and Research BranchIslamic Azad UniversityTehranIslamic Republic of Iran
  3. 3.Soil Conservation and Watershed Management Research Institute (SCWMRI)TehranIslamic Republic of Iran

Personalised recommendations