农业工程学报Issue(18)：142-150,9.DOI:10.3969/j.issn.1002-6819.2014.18.018
基于模糊神经算法的区域地下水盐分动态预测
Regional groundwater salinity dynamics forecasting based on neuro-fuzzy algorithm
摘要
Abstract
The study conducted a detailed analysis of the modeling processes and performances of 2 types of different neural network models including back propagation artificial neural network (BP-ANN) and neuro-fuzzy (NF), in the groundwater salinity dynamics forecasting. Firstly, the classical statistical analysis was used to determine the dominant driving factors of groundwater salinity dynamics and to reveal the available model inputs combinations. Then, the optimal neural network model structures were determined by the trial-and-error method and used to effectively forecast the mid-long term groundwater salinity dynamics. By our research, the idea of necessity in selecting the optimal NF model parameters of transfer functions, rule numbers and iteration steps was innovatively proposed, and the mechanism of differences involved in the model inputs for different groundwater salinity dynamics forecasts was demonstrated. At estuarine Yinyang site, the optimal NF forecast model structure was NF(5-gbellmf-160) with 1 input of the precipitation dynamics, which denotes the optimal rule numbers of 5, the bell type transfer function and the iteration steps of 160. The optimal BP-ANN forecast model structure was ANN(2-2-1), which denotes 2 inputs of precipitation and river water EC dynamics, 2 hidden layers and 1 output. As for estuarine Daxing site, the optimal NF forecast model structure was NF(4-gaussmf-100) with 2 inputs of precipitation and inland water EC dynamics, which denotes the optimal rule numbers of 4, the gauss type transfer function and the iteration steps of 100. The optimal BP-ANN forecast model structure was BP-ANN(1-3-1), which denotes 1 input of inland river EC dynamics, 3 hidden layers and 1 output. As the dominant groundwater recharge resource, the precipitation dynamics was the major impact factor on estuarine groundwater salinity dynamics. On the other hand, the groundwater salinity dynamics at Yinyang site was also affected by the high river water salinity, while at Daxing site was influenced by the inland water salinity, because Yinyang site was much closer to the sea than Daxing site and the shallower groundwater table at Yinyang site made the groundwater salinity dynamics be more directly influenced by the river water salinity. In addition, different models have different abilities to extract the dominant impact factors on the groundwater salinity dynamics. Results showed that the forecast performances of the neural network models (NF and BP-ANN) were better than the conventional linear model that simply combined all the impact factors and added their correlations with dependent variable to forecast groundwater salinity. For Yinyang site’s forecast, the predicted r values of NF, BP-ANN and liner models were 0.565, 0.445 and 0.261, respectively. For Daxing site’s forecast, the predictedr values of NF, BP-ANN and liner models were 0.886, 0.784 and 0.543, respectively. In particularly, the NF algorithm showed prominent capabilities in simulating and error correcting, which consequently led the NF model to perfectly extract the dominant impact factors affecting the groundwater salinity dynamics and effectively simulate the small-scale details and extreme values of groundwater salinity dynamics. Compared with the BP-ANN and liner models, the prediction errors using NF models could be decreased by more than 30% and 50% at Yinyang and Daxing sites, respectively. The presented ideas in constructing the optimal NF model and using it to forecast the regional groundwater salinity dynamics provide a new and practical approach for studies on regional water-salt system health.关键词
水/盐分/土壤/地下水盐分动态/人工神经网络/模糊神经算法/最优模型参数/中长期预测Key words
water/salts/soils/groundwater salinity dynamics/artificial neural network/neuro-fuzzy algorithm/optimal model parameter/mid-long term forecast分类
农业科技引用本文复制引用
余世鹏,杨劲松,刘广明,姚荣江,王相平..基于模糊神经算法的区域地下水盐分动态预测[J].农业工程学报,2014,(18):142-150,9.基金项目
国家自然科学基金资助项目（41101518、41171181）；江苏省产学研联合创新资助项目（BY2013062）；江苏省自然科学基金资助项目 （）
