Particle Swarm Optimization for Identifying Rainfall-Runoff Relationships

Rainfall-runoff processes can be considered a single input-output system where the observed rainfall and runoff are inputs and outputs, respectively. Conventional models of these processes cannot simultaneously identify unknown structures of the system and estimate unknown parameters. This study applied a combinational optimization and Particle Swarm Optimization (PSO) for simultaneous identification of system structure and parameters of the rainfall-runoff relationship. Subsystems in proposed model are modeled using combinations of classic models. Classic models are used to transform the system structure identification problem into a combinational optimization and can be selected from those typically used in the hydrological field. A PSO is then applied to select the optimized subsystem model with the best data fit. The parameters are estimated simultaneously. The proposed model is tested in a case study of daily rainfall-runoff for the upstream Kee-Lung River. Comparison of the proposed method with simple linear model (SLM) shows that, in both calibration and validation, the PSO simulates the time of peak arrival more accurately compared to the SLM. Analytical results also confirm that the PSO accurately identifies the system structure and parameters of the rainfall-runoff relationship, which are a useful reference for water resource planning and application.

[1]  Kwok-wing Chau,et al.  Particle Swarm Optimization Training Algorithm for ANNs in Stage Prediction of Shing Mun River , 2006 .

[2]  Chuntian Cheng,et al.  Optimizing Hydropower Reservoir Operation Using Hybrid Genetic Algorithm and Chaos , 2008 .

[3]  Wang Feng.  A System Identification Method Using Particle Swarm Optimization , 2009 .

[4]  Chuntian Cheng,et al.  Combining a fuzzy optimal model with a genetic algorithm to solve multi-objective rainfall–runoff model calibration , 2002 .

[5]  Yan Li,et al.  Comparison of Several Flood Forecasting Models in Yangtze River , 2005 .

[6]  Raghavan Srinivasan,et al.  Evaluation of global optimization algorithms for parameter calibration of a computationally intensive hydrologic model , 2009 .

[7]  E. Wilson.  Engineering Hydrology , 1974 .

[8]  Lin Qiu,et al.  Support Vector Machine with Particle Swarm Optimization for Reservoir Annual Inflow Forecasting , 2010, 2010 International Conference on Artificial Intelligence and Computational Intelligence.

[9]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[10]  Luis A. Bastidas,et al.  Multiobjective particle swarm optimization for parameter estimation in hydrology , 2006 .

[11]  Bhagu R. Chahar,et al.  Analytic elements method and particle swarm optimization based simulation–optimization model for groundwater management , 2011 .

[12]  Kwok-wing Chau.  A split-step particle swarm optimization algorithm in river stage forecasting , 2007 .

[13]  Hsin-Chuan Kuo,et al.  PARTICLE SWARM OPTIMIZATION FOR GLOBAL OPTIMIZATION PROBLEMS , 2006 .

[14]  Chuntian Cheng,et al.  Using support vector machines for long-term discharge prediction , 2006 .

[15]  Chuntian Cheng,et al.  A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series , 2009 .

[16]  罗祎青,et al.  Global Optimization for the Synthesis of Integrated Water Systems with Particle Swarm Optimization Algorithm , 2008 .

[17]  Alexander Lattermann.  System-Theoretical Modelling in Surface Water Hydrology , 1991 .

[18]  K. Chau,et al.  Predicting monthly streamflow using data‐driven models coupled with data‐preprocessing techniques , 2009 .