A Hybrid Neural Network and Genetic Algorithm Model for Predicting Dissolved Oxygen in an Aquaculture Pond

The prediction for dissolved oxygen (DO) in aquaculture ponds is a problem of multi-variables, nonlinearity and long-time lag. Neural networks (NNs) have become one of ideal tools in modeling nonlinear relationship between inputs and outputs. In this work, GA-LM, a neural network model combining Levenberg–Marquardt(LM) algorithm and Genetic Algorithm (GA) was developed for predicting DO in an aquaculture pond at Dalian, China. LM was used to train NNs, showing faster convergence rate. The network architecture was optimized by GA. The performance of GA-LM has been compared with that of conventional Back-Propagation (BP) algorithm and Levenberg–Marquardt(LM) algorithm. The comparison indicates that the predicted DO values using GA-LM model are in good agreement with the measured data. It is demonstrated here that the model is capable of predicting DO accurately, and can offer stronger and better performance than conventional neural networks when used as a quick interpolation and extrapolation tool.

[1]  H. Ishigami,et al.  Structure optimization of fuzzy neural network by genetic algorithm , 1995 .

[2]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[3]  Changhui Deng,et al.  Application of Neural Network Based on PSO Algorithm in Prediction Model for Dissolved Oxygen in Fishpond , 2006, 2006 6th World Congress on Intelligent Control and Automation.

[4]  Ali Yazici,et al.  A neural network-based approach for calculating dissolved oxygen profiles in reservoirs , 2003, Neural Computing & Applications.

[5]  S. Ilhan,et al.  Application of multivariate statistical techniques in the assessment of surface water quality in Uluabat Lake, Turkey , 2008, Environmental monitoring and assessment.

[6]  Durdu Ömer Faruk.  A hybrid neural network and ARIMA model for water quality time series prediction , 2010, Eng. Appl. Artif. Intell..

[7]  Dingjiang Chen,et al.  Artificial neural network modelling of concentrations of nitrogen, phosphorus and dissolved oxygen in a non‐point source polluted river in Zhejiang Province, southeast China , 2009 .

[8]  A. E. Greenberg,et al.  Standard methods for the examination of water and wastewater : supplement to the sixteenth edition , 1988 .

[9]  Ill-Soo Kim,et al.  A study on genetic algorithm to select architecture of a optimal neural network in the hot rolling process , 2004 .

[10]  L. Xie,et al.  A Soft-sensing Method Based on BP Neural Network for Improving Dissolved Oxygen Measurement , 2006, 2006 1ST IEEE Conference on Industrial Electronics and Applications.

[11]  Awwa,et al.  Standard Methods for the examination of water and wastewater , 1999 .

[12]  Heinz G. Stefan,et al.  Simulation of dissolved oxygen profiles in a transparent, dimictic lake , 1995 .

[13]  Roberto Revelli,et al.  Stochastic modelling of DO and BOD components in a stream with random inputs , 2006 .

[14]  Bernhard H. Schmid,et al.  Artificial Neural Network Modeling of Dissolved Oxygen in a Wetland Pond: The Case of Hovi, Finland , 2006 .

[15]  Jasna Radulović,et al.  Neural network modeling of dissolved oxygen in the Gruža reservoir, Serbia , 2010 .

[16]  Fang Zhi.  Changes of main environmental factors of composite culture system in Xinglin shrimp pond , 2001 .

[17]  Ashraf Aboshosha,et al.  Genetic Algorithms Theories and Applications: Evolutionary Algorithms, Optimization Techniques, Heuristics, Artificial Intelligence, Biologically inspired Algorithms , 2012 .