Application of Levenberg-Marquardt Algorithm Based Neural Network as Mrater Quality Assessment Tool for Surface Waters
In the past decades, scientific research has focused on the preservation of water resources, and in particular, on the water quality assessment and management of natural surface waters. The LevenbergMarquardt algorithm is a very popular curve-fitting algorithm used in many neural network models for solving generic curve-fitting problems. Here we test the applicability of this model as an assessment tool for surface waters in Shiyanghe river basin. We conclude that the model is able to reproduce observed water quality parameters adequately under a wide range of conditions. Study results show that the Levenberg-Marquardt algorithm based neural network is able to assess several indicators with reasonable accuracy, suggesting that the neural network is a valuable tool for reservoir management in Shiyanghe river basin.
neural networks water quality assessment surface water LevenbergMarquardt
JIAN Yaping MA Zongren
School of Environmental and Municipal Engineering, Lanzhou Jiaotong University, Lanzhou, 730070,Chin School of Environmental and Municipal Engineering, Lanzhou Jiaotong University, Lanzhou, 730070,Chin
国际会议
西安
英文
617-619
2010-10-11（万方平台首次上网日期，不代表论文的发表时间）