Assessment of urban flood susceptibility using semi-supervised machine learning model.

In order to identify flood-prone areas with limited flood inventories, a semi-supervised machine learning model-the weakly labeled support vector machine (WELLSVM)-is used to assess urban flood susceptibility in this study. A spatial database is collected from metropolitan areas in Beijing, including flood inventories from 2004 to 2014 and nine metrological, geographical, and anthropogenic explanatory factors. Urban flood susceptibility is mapped and compared using logistic regression, artificial neural networks, and a support vector machine. Model performances are evaluated using four evaluation indices (accuracy, precision, recall, and F-score) as well as the receiver operating characteristic curve. The results show that WELLSVM can better utilize the spatial information (unlabeled data), and it outperforms all comparison models. The high-quality WELLSVM flood susceptibility map is thus applicable to efficient urban flood management.

[1]  Colin Arrowsmith,et al.  Topography Wetness Index Application in Flood-Risk-Based Land Use Planning , 2016 .

[2]  K. Beven,et al.  A physically based, variable contributing area model of basin hydrology , 1979 .

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

[4]  Megan Mehaffey,et al.  Development of a spatially complete floodplain map of the conterminous United States using random forest , 2018, The Science of the total environment.

[5]  Zenglin Xu,et al.  Simple and Efficient Multiple Kernel Learning by Group Lasso , 2010, ICML.

[6]  Zongxue Xu,et al.  Flood Risk Zoning by Using 2D Hydrodynamic Modeling: A Case Study in Jinan City , 2017 .

[7]  Shanzhen Yi,et al.  Incorporating probabilistic approach into local multi-criteria decision analysis for flood susceptibility assessment , 2018, Stochastic Environmental Research and Risk Assessment.

[8]  Volker Meyer,et al.  Integrated urban flood risk assessment – adapting a multicriteria approach to a city , 2009 .

[9]  B. Mohammadi,et al.  A comparison between the application of empirical and ANN methods for estimation of daily global solar radiation in Iran , 2018, Theoretical and Applied Climatology.

[10]  Wei Wei,et al.  Potential reduction in urban runoff by green spaces in Beijing: A scenario analysis , 2015 .

[11]  Stephen P. Boyd,et al.  A minimax theorem with applications to machine learning, signal processing, and finance , 2007, 2007 46th IEEE Conference on Decision and Control.

[12]  A. Goonetilleke,et al.  Understanding the role of land use in urban stormwater quality management. , 2005, Journal of environmental management.

[13]  P. Burrough,et al.  Principles of geographical information systems , 1998 .

[14]  Rafid Alkhaddar,et al.  Flood risk assessment for urban water system in a changing climate using artificial neural network , 2015, Natural Hazards.

[15]  Edward R. Dougherty,et al.  Effect of separate sampling on classification accuracy , 2014, Bioinform..

[16]  Vinay Kumar Dadhwal,et al.  Multi-Criteria Decision Making Approach for Watershed Prioritization Using Analytic Hierarchy Process Technique and GIS , 2013, Water Resources Management.

[17]  Philippe Gourbesville,et al.  Citywide multi-grid urban flood modelling: the July 2012 flood in Beijing , 2015 .

[18]  Ivor W. Tsang,et al.  Convex and scalable weakly labeled SVMs , 2013, J. Mach. Learn. Res..

[19]  A J Saul,et al.  Flooding in the future--predicting climate change, risks and responses in urban areas. , 2005, Water science and technology : a journal of the International Association on Water Pollution Research.

[20]  Robert D. Nowak,et al.  Unlabeled data: Now it helps, now it doesn't , 2008, NIPS.

[21]  J. Guldmann,et al.  Spatial regression models of park and land-use impacts on the urban heat island in central Beijing. , 2018, The Science of the total environment.

[22]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[23]  J. N. Fernandes,et al.  Key issues for sustainable urban stormwater management. , 2012, Water research.

[24]  J. Aerts,et al.  Flood risk and adaptation strategies under climate change and urban expansion: A probabilistic analysis using global data. , 2015, The Science of the total environment.

[25]  E. Forgy,et al.  Cluster analysis of multivariate data : efficiency versus interpretability of classifications , 1965 .

[26]  Biswajeet Pradhan,et al.  Application of a neuro-fuzzy model to landslide-susceptibility mapping for shallow landslides in a tropical hilly area , 2011, Comput. Geosci..

[27]  Zongxue Xu,et al.  Statistical Downscaling of Temperature with the Random Forest Model , 2017 .

[28]  Biswajeet Pradhan,et al.  Landslide susceptibility assessment and factor effect analysis: backpropagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modelling , 2010, Environ. Model. Softw..

[29]  Shahaboddin Shamshirband,et al.  Coupling a firefly algorithm with support vector regression to predict evaporation in northern Iran , 2018 .

[30]  T. Kavzoglu,et al.  Landslide susceptibility mapping using GIS-based multi-criteria decision analysis, support vector machines, and logistic regression , 2014, Landslides.

[31]  Baozhu Pan,et al.  An urban storm-inundation simulation method based on GIS , 2014 .

[32]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[33]  D. Cox.  The Regression Analysis of Binary Sequences , 1958 .

[34]  Xiaohong Chen,et al.  Scenario-based projections of future urban inundation within a coupled hydrodynamic model framework: A case study in Dongguan City, China , 2017 .

[35]  Manish Kumar Goyal,et al.  Downscaling of surface temperature for lake catchment in an arid region in India using linear multiple regression and neural networks , 2012 .

[36]  Mark A. Hall,et al.  Correlation-based Feature Selection for Discrete and Numeric Class Machine Learning , 1999, ICML.

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

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

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

[40]  H. Pourghasemi,et al.  Flood susceptibility mapping using novel ensembles of adaptive neuro fuzzy inference system and metaheuristic algorithms. , 2018, The Science of the total environment.

[41]  Mustafa Neamah Jebur,et al.  Flood susceptibility analysis and its verification using a novel ensemble support vector machine and frequency ratio method , 2015, Stochastic Environmental Research and Risk Assessment.

[42]  Ayhan Demiriz,et al.  Semi-Supervised Support Vector Machines , 1998, NIPS.

[43]  Xiaohong Chen,et al.  Flood hazard risk assessment model based on random forest , 2015 .

[44]  Donald H. Burn,et al.  Cluster Analysis as Applied to Regional Flood Frequency , 1989 .

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

[46]  Mustafa Neamah Jebur,et al.  Flood susceptibility mapping using integrated bivariate and multivariate statistical models , 2014, Environmental Earth Sciences.

[47]  Paul D. Bates,et al.  A comparison of three parallelisation methods for 2D flood inundation models , 2010, Environ. Model. Softw..

[48]  Dihua Li,et al.  Spatial characteristics of local floods in Beijing urban area , 2014 .

[49]  Zifa Wang,et al.  Effect of urbanization on the winter precipitation distribution in Beijing area , 2009 .

[50]  Paul D. Bates,et al.  Evaluating scale and roughness effects in urban flood modelling using terrestrial LIDAR data , 2013 .

[51]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[52]  Zongxue Xu,et al.  Mapping flood susceptibility in mountainous areas on a national scale in China. , 2018, The Science of the total environment.

[53]  Zongxue Xu,et al.  Impact of urbanization on rainfall-runoff processes: case study in the Liangshui River Basin in Beijing, China , 2016 .

[54]  E. Irwin,et al.  The evolution of urban sprawl: Evidence of spatial heterogeneity and increasing land fragmentation , 2007, Proceedings of the National Academy of Sciences.

[55]  Dieu Tien Bui,et al.  A novel hybrid artificial intelligence approach for flood susceptibility assessment , 2017, Environ. Model. Softw..