Artificial Neural Networks for Flood Susceptibility Mapping in Data-Scarce Urban Areas

Abstract Floods are natural hazards with potentially huge consequences on the environment, economy, and human life and property. Therefore, emerging engineering approaches, such as the detection of areas most susceptible to flooding, are of great importance for flood management. This study applies an artificial neural network model for mapping flood inundation areas of Emam-Ali township in Mashhad city, Khorasan Razavi Province, Iran. Thematic layers of flood conditioning factors including elevation, slope angle, distance from drainage, drainage network density, and land use, alongside a flood inventory map of the study area were prepared. All the contributing factors were overlaid with training points of the flood inventory map in Neuralnet package and R statistic. The accuracy of the generated flood inundation map was assessed utilizing the receiver operating characteristic (ROC) curve approach. Area under the ROC curve values of 94.6% (training) and 92.0% (validation) indicate that, overall, the presented approach provides a good indicator of flood inundation areas in the study area.

[1]  Omid Rahmati,et al.  Spatial prediction of flood-susceptible areas using frequency ratio and maximum entropy models , 2018 .

[2]  Ebrahim Ahmadisharaf,et al.  Evaluating the Effects of Inundation Duration and Velocity on Selection of Flood Management Alternatives Using Multi-Criteria Decision Making , 2015, Water Resources Management.

[3]  Paulin Coulibaly,et al.  Improving groundwater level forecasting with a feedforward neural network and linearly regressed projected precipitation , 2008 .

[4]  Giuseppe T. Aronica,et al.  Probabilistic flood inundation mapping at ungauged streams due to roughness coefficient uncertainty in hydraulic modelling , 2017 .

[5]  Arleen A. Hill,et al.  A GIS-based model for urban flood inundation , 2009 .

[6]  Mahyat Shafapour Tehrany,et al.  Flood susceptibility assessment using GIS-based support vector machine model with different kernel types , 2015 .

[7]  B. Pradhan,et al.  Application of fuzzy logic and analytical hierarchy process (AHP) to landslide susceptibility mapping at Haraz watershed, Iran , 2012, Natural Hazards.

[8]  C. Özkan,et al.  Comparison of maximum likelihood classification method with supervised artificial neural network algorithms for land use activities , 2004 .

[9]  H. Pourghasemi,et al.  Identification of Critical Flood Prone Areas in Data-Scarce and Ungauged Regions: A Comparison of Three Data Mining Models , 2017, Water Resources Management.

[10]  V. Merwade,et al.  Comparison of one-dimensional HEC-RAS with two-dimensional FESWMS model in flood inundation mapping , 2008 .

[11]  Narendra Singh Raghuwanshi,et al.  Flood Forecasting Using ANN, Neuro-Fuzzy, and Neuro-GA Models , 2009 .

[12]  Chandranath Chatterjee,et al.  Uncertainty assessment and ensemble flood forecasting using bootstrap based artificial neural networks (BANNs) , 2010 .

[13]  Nguyen Mai Dang,et al.  Evaluation of food risk parameters in the Day River Flood Diversion Area, Red River Delta, Vietnam , 2011 .

[14]  H. Pourghasemi,et al.  Application of GIS-based data driven random forest and maximum entropy models for groundwater potential mapping: A case study at Mehran Region, Iran , 2016 .

[15]  B. Pradhan.  Flood susceptible mapping and risk area delineation using logistic regression, GIS and remote sensing , 2010 .

[16]  Dong Hyawn Kim,et al.  Artificial neural network based breakwater damage estimation considering tidal level variation , 2014 .

[17]  A. R. Mahmud,et al.  An artificial neural network model for flood simulation using GIS: Johor River Basin, Malaysia , 2012, Environmental Earth Sciences.

[18]  C. Price,et al.  Flash flood prediction using an uncalibrated hydrological model and radar rainfall data in a Mediterranean watershed under changing hydrological conditions , 2010 .

[19]  Mohammad H. Tayebi,et al.  Sub pixel mapping of alteration minerals using SOM neural network model and hyperion data , 2015, Earth Science Informatics.

[20]  H. Pourghasemi,et al.  Flood susceptibility mapping using frequency ratio and weights-of-evidence models in the Golastan Province, Iran , 2016 .

[21]  Duc Truong Pham,et al.  Control chart pattern recognition using learning vector quantization networks , 1994 .

[22]  Charles M. Bachmann,et al.  Neural Networks and Their Applications , 1994 .

[23]  Ebrahim Ahmadisharaf,et al.  Spatial probabilistic multi-criteria decision making for assessment of flood management alternatives , 2016 .

[24]  Jenq-Neng Hwang,et al.  Neural network architectures for robotic applications , 1989, IEEE Trans. Robotics Autom..

[25]  Seyed Amir Naghibi,et al.  GIS-based groundwater potential mapping using boosted regression tree, classification and regression tree, and random forest machine learning models in Iran , 2015, Environmental Monitoring and Assessment.

[26]  Eric Tate,et al.  Social vulnerability to floods: Review of case studies and implications for measurement , 2015 .

[27]  Paul D. Bates,et al.  Regional flood frequency analysis at the global scale , 2015 .

[28]  Pierfranco Costabile,et al.  Enhancing river model set-up for 2-D dynamic flood modelling , 2015, Environ. Model. Softw..

[29]  Sulafa Hag Elsafi.  Artificial Neural Networks (ANNs) for flood forecasting at Dongola Station in the River Nile, Sudan , 2014 .

[30]  Ngai Weng Chan,et al.  Impacts of Disasters and Disaster Risk Management in Malaysia: The Case of Floods , 2015 .

[31]  G. Karatzas,et al.  Flood management and a GIS modelling method to assess flood-hazard areas—a case study , 2011 .

[32]  W. Botzen,et al.  Individual preferences for reducing flood risk to near zero through elevation , 2013, Mitigation and Adaptation Strategies for Global Change.

[33]  Ashish Sharma,et al.  An application of artificial neural networks for rainfall forecasting , 2001 .

[34]  E. Esu,et al.  Application of remote-sensing data to groundwater exploration: A case study of the Cross River State, southeastern Nigeria , 1998 .

[35]  Mustafa Neamah Jebur,et al.  Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS , 2014 .

[36]  P. Nagler,et al.  Roles of saltcedar (Tamarix spp.) and capillary rise in salinizing a non-flooding terrace on a flow-regulated desert river , 2012 .

[37]  John D. Nelson,et al.  An analysis of landslide susceptibility zonation using a subjective geomorphic mapping and existing landslides , 2011, Comput. Geosci..

[38]  B. Pradhan.  Groundwater potential zonation for basaltic watersheds using satellite remote sensing data and GIS techniques , 2009 .

[39]  D. Fernández,et al.  Urban flood hazard zoning in Tucumán Province, Argentina, using GIS and multicriteria decision analysis , 2010 .

[40]  Mustafa Neamah Jebur,et al.  Spatial prediction of flood susceptible areas using rule based decision tree (DT) and a novel ensemble bivariate and multivariate statistical models in GIS , 2013 .

[41]  T. Chang,et al.  Inundation simulation for urban drainage basin with storm sewer system , 2000 .

[42]  Ebrahim Ahmadisharaf,et al.  Integrating flood hazard into site selection of detention basins using spatial multi-criteria decision-making , 2016 .

[43]  Paulin Coulibaly,et al.  Groundwater level forecasting using artificial neural networks , 2005 .

[44]  L. Vasiliades,et al.  Multi-Criteria Analysis Framework for Potential Flood Prone Areas Mapping , 2014, Water Resources Management.

[45]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[46]  N. Chan.  Flood disaster management in Malaysia: an evaluation of the effectiveness of government resettlement schemes , 1995 .

[47]  Alberto González,et al.  Validation of Landslide Susceptibility Maps; Examples and Applications from a Case Study in Northern Spain , 2003 .

[48]  Fathy Abdalla.  Mapping of groundwater prospective zones using remote sensing and GIS techniques: A case study from the Central Eastern Desert, Egypt , 2012 .

[49]  Thomas R. Kjeldsen,et al.  Modelling the impact of urbanization on flood frequency relationships in the UK , 2010 .

[50]  B. Pradhan,et al.  Landslide Susceptibility Assessment in Vietnam Using Support Vector Machines, Decision Tree, and Naïve Bayes Models , 2012 .

[51]  P. Bates,et al.  Evaluation of 1D and 2D numerical models for predicting river flood inundation , 2002 .

[52]  B. Pradhan,et al.  Flash flood susceptibility assessment in Jeddah city (Kingdom of Saudi Arabia) using bivariate and multivariate statistical models , 2015, Environmental Earth Sciences.

[53]  Andrea G. Fabbri,et al.  Validation of Spatial Prediction Models for Landslide Hazard Mapping , 2003 .

[54]  H. Pourghasemi,et al.  Gully erosion susceptibility mapping: the role of GIS-based bivariate statistical models and their comparison , 2016, Natural Hazards.

[55]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[56]  F. Smedt,et al.  Flood Modeling for Complex Terrain Using GIS and Remote Sensed Information , 2005 .

[57]  Dušan Prodanović,et al.  An approach to simulation of dual drainage , 1999 .

[58]  Theo G. Schmitt,et al.  Analysis and modeling of flooding in urban drainage systems , 2004 .