Risk analysis for real-time flood control operation of a multi-reservoir system using a dynamic Bayesian network

Abstract This paper proposes a model for risk analysis of real-time flood control operation of a multi-reservoir system using a dynamic Bayesian network. The proposed model consists of three components: Monte Carlo simulations, dynamic Bayesian network establishing, and risk-informed inference for decision making. The Monte Carlo simulations provide basic data inputs for the dynamic Bayesian network establishing using the historical floods and operation models of the multi-reservoir system. The dynamic Bayesian network is built with expert knowledge and the relationships among the uncertainties. The component of risk-informed inference for decision making is to provide risk information about the operation schedules using the trained dynamic Bayesian network. We apply the proposed model to a multi-reservoir system in China. The results show that the proposed method has a capability for bi-directional inferences and can be served as a risk-informed decision-making tool under uncertainties in the real-time flood control operation of a multi-reservoir system.

[1]  David Heckerman,et al.  Learning Gaussian Networks , 1994, UAI.

[2]  YanFang Diao,et al.  Risk analysis of flood control operation mode with forecast information based on a combination of risk sources , 2010 .

[3]  Maria Gheorghe,et al.  Non-parametric Bayesian networks for parameter estimation in reservoir simulation: a graphical take on the ensemble Kalman filter (part I) , 2013, Computational Geosciences.

[4]  Zhang Li.  Application of dynamic Bayesian networks in hydrologic forecast , 2010 .

[5]  Larry W. Mays,et al.  Risk models for flood levee design , 1981 .

[6]  Shenglian Guo,et al.  Estimation of reservoir flood control operation risks with considering inflow forecasting errors , 2014, Stochastic Environmental Research and Risk Assessment.

[7]  Gregory F. Cooper,et al.  A Multivariate Discretization Method for Learning Bayesian Networks from Mixed Data , 1998, UAI.

[8]  Qiong Li,et al.  Research on flood risk analysis and evaluation method based on variable fuzzy sets and information diffusion , 2012 .

[9]  M. Pulido‐Velazquez,et al.  Dynamic Bayesian Networks as a Decision Support Tool for assessing Climate Change impacts on highly stressed groundwater systems , 2013 .

[10]  Y. Tung,et al.  Assessment of design rainfall uncertainty for hydrologic engineering applications in Hong Kong , 2013, Stochastic Environmental Research and Risk Assessment.

[11]  R. Rackwitz,et al.  Structural reliability under combined random load sequences , 1978 .

[12]  Gemma Manache,et al.  Sensitivity Analysis of a Water-Quality Model using Latin Hypercube Sampling , 2004 .

[13]  M. Stone,et al.  Spatially implemented Bayesian network model to assess environmental impacts of water management , 2014 .

[14]  W. McAnally,et al.  Composite Risk Assessment for the Sacramento–San Joaquin Delta Levee System , 2014 .

[15]  Shuhai Jiang.  Application of stochastic differential equations in risk assessment for flood releases , 1998 .

[16]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[17]  Hector Malano,et al.  A Bayesian network approach to knowledge integration and representation of farm irrigation: 3. Spatial application: KNOWLEDGE INTEGRATION OF FARM IRRIGATION, 3 , 2009 .

[18]  Juan Chen,et al.  A decomposition‐integration risk analysis method for real‐time operation of a complex flood control system , 2017 .

[19]  Quan J. Wang,et al.  A Bayesian network approach to knowledge integration and representation of farm irrigation: 2. Model validation , 2009 .

[20]  C. S. Melching.  An improved first-order reliability approach for assessing uncertainties in hydrologic modeling , 1992 .

[21]  Feilin Zhu,et al.  Multi-criteria group decision making under uncertainty: Application in reservoir flood control operation , 2018, Environ. Model. Softw..

[22]  H. Ross,et al.  Participatory development of a Bayesian network model for catchment‐based water resource management , 2010 .

[23]  Yeou-Koung Tung,et al.  Risk analysis for flood-control structure under consideration of uncertainties in design flood , 2011 .

[24]  Shao-Zhong Zhang,et al.  Construction and application of Bayesian networks in flood decision supporting system , 2002, Proceedings. International Conference on Machine Learning and Cybernetics.

[25]  V. Guinot,et al.  Uncertainty analysis of river flooding and dam failure risks using local sensitivity computations , 2012, Reliab. Eng. Syst. Saf..

[26]  Pan Liu,et al.  Dynamic control of flood limited water level for reservoir operation by considering inflow uncertainty , 2010 .

[27]  Mohammad Reza Nikoo,et al.  Developing real time operating rules for trading discharge permits in rivers: Application of Bayesian Networks , 2009, Environ. Model. Softw..

[28]  Xinlong Feng,et al.  A hybrid Bayesian network approach for trade-offs between environmental flows and agricultural water using dynamic discretization , 2017 .

[29]  Huicheng Zhou,et al.  An optimization based sampling approach for multiple metrics uncertainty analysis using generalized likelihood uncertainty estimation , 2016 .

[30]  Reza Kerachian,et al.  Developing monthly operating rules for a cascade system of reservoirs: Application of Bayesian Networks , 2009, Environ. Model. Softw..

[31]  Jurate Kriauciuniene,et al.  Estimation of uncertainty sources in the projections of Lithuanian river runoff , 2013, Stochastic Environmental Research and Risk Assessment.

[32]  B. J. Williams,et al.  Mining monitored data for decision-making with a Bayesian network model , 2013 .

[33]  Yeou-Koung Tung,et al.  Evaluation of dam overtopping probability induced by flood and wind , 2011 .