Adaptive surrogate modeling for optimization of flood control detention dams

Real world optimization problems commonly require complex computationally demanding models which use in practice could be limited. To address this drawback, different meta-modeling approaches have been proposed in the literature. This study represents an adaptive meta-modeling framework to solve a high dimensional design problem by coupling a hydrodynamic model, a multi objective genetic algorithm and artificial neural network as the surrogate model. The proposed dynamic learning approach includes special space filling techniques and control strategies to periodically update surrogate model and keep the fidelity level of solutions as the optimization progresses. An experimental application on flood management based on a case study in Iran was carried out in order to test the efficiency of the proposed approach. Results showed the approach provides a 74% time saving while maintaining the quality of solutions when compared with those of the original simulation model indicating the viability of the approach. We proposed a methodology to determine optimal design of multiple detention dams.A new adaptive surrogate model is used to decrease computational times.The methodology captures inherent flood uncertainties and their correlations within MCS.The algorithm integrates NSGA-II, hydrological and hydraulic models and ANN.

[1]  Weng Tat Chan,et al.  Derivation of Pareto front with genetic algorithm and neural network , 2001 .

[2]  Andrea Castelletti,et al.  Data-driven dynamic emulation modelling for the optimal management of environmental systems , 2012, Environ. Model. Softw..

[3]  Soon-Thiam Khu,et al.  A general framework for flood risk-based storm sewer network design , 2011 .

[4]  Carlos A. Coello Coello,et al.  A Review of Techniques for Handling Expensive Functions in Evolutionary Multi-Objective Optimization , 2010 .

[5]  D. Solomatine,et al.  Automatic calibration of groundwater models using global optimization techniques , 1999 .

[6]  Luigi Berardi,et al.  Computationally Efficient Modeling Method for Large Water Network Analysis , 2012 .

[7]  K Vairavamoorthy,et al.  Multi-objective optimisation of cost-benefit of urban flood management using a 1D2D coupled model. , 2011, Water science and technology : a journal of the International Association on Water Pollution Research.

[8]  D. P. Solomatine.  Neural Network Approximation of a Hydrodynamic Model in Optimizing Reservoir Operation , 2006 .

[9]  Arthur van Dam,et al.  Flood inference simulation using surrogate modelling for the Yellow River multiple reservoir system , 2014, Environ. Model. Softw..

[10]  Joseph H. A. Guillaume,et al.  Characterising performance of environmental models , 2013, Environ. Model. Softw..

[11]  Holger R. Maier,et al.  Optimal operation of complex water distribution systems using metamodels. , 2010 .

[12]  Motahareh Saadatpour,et al.  Particle Swarm Optimization for Automatic Calibration of Large Scale Water Quality Model (CE-QUAL-W2): Application to Karkheh Reservoir, Iran , 2011 .

[13]  Avi Ostfeld,et al.  A hybrid genetic—instance based learning algorithm for CE-QUAL-W2 calibration , 2005 .

[14]  Zoran Kapelan,et al.  Artificial Intelligence Techniques for Flood Risk Management in Urban Environments , 2014 .

[15]  Frank Kursawe,et al.  A Variant of Evolution Strategies for Vector Optimization , 1990, PPSN.

[16]  António Gaspar-Cunha,et al.  A Multi-Objective Evolutionary Algorithm Using Neural Networks to Approximate Fitness Evaluations , 2005, Int. J. Comput. Syst. Signals.

[17]  J. Yazdi,et al.  A Simulation-Based Optimization Model for Flood Management on a Watershed Scale , 2012, Water Resources Management.

[18]  J. Stiffler.  Reliability estimation , 1996 .

[19]  Andrea Castelletti,et al.  Emulation techniques for the reduction and sensitivity analysis of complex environmental models , 2012, Environ. Model. Softw..

[20]  D. Savić,et al.  Multiobjective design of water distribution systems under uncertainty , 2005 .

[21]  Kalyanmoy Deb,et al.  A Fast Elitist Non-dominated Sorting Genetic Algorithm for Multi-objective Optimisation: NSGA-II , 2000, PPSN.

[22]  Zoran Kapelan,et al.  Reducing the Complexity of Multiobjective Water Distribution System Optimization through Global Sensitivity Analysis , 2012 .

[23]  Rui Zou,et al.  An adaptive neural network embedded genetic algorithm approach for inverse water quality modeling , 2007 .

[24]  Dan Cornford,et al.  Managing uncertainty in integrated environmental modelling: The UncertWeb framework , 2013, Environ. Model. Softw..

[25]  Joshua D. Knowles,et al.  ParEGO: a hybrid algorithm with on-line landscape approximation for expensive multiobjective optimization problems , 2006, IEEE Transactions on Evolutionary Computation.

[26]  George Kourakos,et al.  Pumping optimization of coastal aquifers based on evolutionary algorithms and surrogate modular neural network models , 2009 .

[27]  George Kuczera,et al.  Monte Carlo assessment of parameter uncertainty in conceptual catchment models: the Metropolis algorithm , 1998 .

[28]  P. P. Mujumdar,et al.  Fuzzy Waste Load Allocation Model: Simulation-Optimization Approach , 2004 .

[29]  Micha Werner,et al.  Reduction of Monte-Carlo simulation runs for uncertainty estimation in hydrological modelling , 2003 .

[30]  Holger R. Maier,et al.  Water Distribution System Optimization Using Metamodels , 2005 .

[31]  Bryan A. Tolson,et al.  Review of surrogate modeling in water resources , 2012 .

[32]  Albert S. Chen,et al.  Calibration of a 1D/1D urban flood model using 1D/2D model results in the absence of field data. , 2011, Water science and technology : a journal of the International Association on Water Pollution Research.

[33]  Mohammad Karamouz,et al.  A stochastic conflict resolution model for water quality management in reservoir–river systems , 2007 .

[34]  K. Beven,et al.  Model Calibration and Uncertainty Estimation , 2006 .

[35]  Mitchell J. Small,et al.  State Water Pollution Control Policy Insights from a Reduced-Form Model , 2004 .

[36]  Jun Xia,et al.  An efficient integrated approach for global sensitivity analysis of hydrological model parameters , 2013, Environ. Model. Softw..

[37]  Mitchell J. Small,et al.  Evaluating response surface designs for uncertainty analysis and prescriptive applications of a large-scale water quality model , 2006 .

[38]  Kourosh Behzadian,et al.  Stochastic sampling design using a multi-objective genetic algorithm and adaptive neural networks , 2009, Environ. Model. Softw..

[39]  Graeme C. Dandy,et al.  Optimization of Water Distribution Systems Using Online Retrained Metamodels , 2014 .

[40]  Roland K. Price,et al.  Multiobjective Evolutionary Approach to Rehabilitation of Urban Drainage Systems , 2010 .

[41]  Raghavan Srinivasan,et al.  Approximating SWAT Model Using Artificial Neural Network and Support Vector Machine 1 , 2009 .

[42]  Barbara S. Minsker,et al.  Optimal groundwater remediation design using an Adaptive Neural Network Genetic Algorithm , 2006 .

[43]  Slobodan P. Simonovic,et al.  A three‐dimensional fuzzy methodology for flood risk analysis , 2011 .

[44]  Mohammad Hossein Niksokhan,et al.  Optimal prioritisation of watershed management measures for flood risk mitigation on a watershed scale , 2013 .

[45]  Carlos M. Fonseca,et al.  Multiobjective genetic algorithms with application to control engineering problems. , 1995 .

[46]  Pebesma Edzer,et al.  Managing uncertainty in integrated environmental modelling frameworks: The UncertWeb framework , 2012 .

[47]  Barbara S. Minsker,et al.  Applying Dynamic Surrogate Models in Noisy Genetic Algorithms to Optimize Groundwater Remediation Designs , 2011 .

[48]  Stefan M. Wild,et al.  Bayesian Calibration and Uncertainty Analysis for Computationally Expensive Models Using Optimization and Radial Basis Function Approximation , 2008 .

[49]  H. Madsen,et al.  Simulation and optimisation modelling approach for operation of the Hoa Binh Reservoir, Vietnam , 2007 .

[50]  Luceno Distributed Data.  RELIABILITY ESTIMATION FROM , 2003 .

[51]  Christine A. Shoemaker,et al.  Comparison of function approximation, heuristic, and derivative‐based methods for automatic calibration of computationally expensive groundwater bioremediation models , 2005 .

[52]  Alberto Montanari,et al.  What do we mean by ‘uncertainty’? The need for a consistent wording about uncertainty assessment in hydrology , 2007 .

[53]  S. Murty Bhallamudi,et al.  Non-Uniform Flow Effect on Optimal Waste Load Allocation in Rivers , 2006 .

[54]  Andy J. Keane,et al.  Engineering Design via Surrogate Modelling - A Practical Guide , 2008 .

[55]  Dragan Savic,et al.  Attribution of flood risk in urban areas , 2008 .

[56]  Mojtaba Shourian,et al.  Adaptive sequentially space‐filling metamodeling applied in optimal water quantity allocation at basin scale , 2010 .

[57]  H. Madsen,et al.  A fast Evolutionary-based Meta-Modelling Approach for the Calibration of a Rainfall-Runoff Model , 2004 .

[58]  Dimitri Solomatine,et al.  A novel method to estimate model uncertainty using machine learning techniques , 2009 .

[59]  Dragan Savic,et al.  Comparison of 1D/1D and 1D/2D Coupled (Sewer/Surface) Hydraulic Models for Urban Flood Simulation , 2009 .

[60]  Lothar Thiele,et al.  Comparison of Multiobjective Evolutionary Algorithms: Empirical Results , 2000, Evolutionary Computation.

[61]  Virginia M. Johnson,et al.  Accuracy of Neural Network Approximators in Simulation-Optimization , 2000 .

[62]  Angus R. Simpson,et al.  Application of two ant colony optimisation algorithms to water distribution system optimisation , 2006, Math. Comput. Model..

[63]  Marc Schoenauer,et al.  A Steady Performance Stopping Criterion for Pareto-based Evolutionary Algorithms , 2004 .

[64]  Zoran Kapelan,et al.  Using high performance techniques to accelerate demand-driven hydraulic solvers , 2013 .