Affiliations: Key Laboratory of Surficial Geochemistry, MOE, Department of Hydrosciences, School of Earth Sciences and Engineering, State Key Laboratory of Pollution Control and Resource Reuse, Nanjing University, Nanjing, P.R. China | School of Geographic and Oceanographic sciences, Nanjing University, Nanjing, P.R China | School of Hydrology and Water Resources, Hohai University, Nanjing, P.R. China | State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, School of Hydrology and Water Resources, Hohai University, Nanjing, P.R. China
Note: [] Corresponding author. Dong Wang, Key Laboratory of Surficial Geochemistry, MOE, Department of Hydrosciences, School of Earth Sciences and Engineering, State Key Laboratory of Pollution Control and Resource Reuse, Nanjing University, Nanjing, P.R. China. E-mail: [email protected]
Abstract: A risk assessment for urban water hazard based on RBF artificial neural network - Cloud model (RBF-ANN-Cloud) is proposed, according to the nonlinear characteristics, randomness and fuzziness in water hazard. Four assessment factors influencing urban water hazard are selected; the ranges of risk levels are calculated according to the Pearson-III frequency curve and the comprehensive cloud model of all risk levels belonging to assessment factors are generated. Historical data of assessment factors are simulated and forecasted by RBF artificial neural network; distribution curves of certainty degrees of risk levels are drawn, which indicate the final water hazard risk. Comparative researches with ARIMA and fuzzy decision-making set showed RBF-ANN-Cloud's suitability and effectiveness in water hazard risk assessment. RBF- Cloud model provides a new way of forecast and assessment of urban water hazard.
Keywords: Risk assessment, cloud model, RBF artificial neural network, urban water hazard, time series analysis
