文献类型：期刊文献

英文题名：Using a Backpropagation Artificial Neural Network to Predict Nutrient Removal in Tidal Flow Constructed Wetlands

作者：Li, Wei[1,2,3] Cui, Lijuan[1,2,3] Zhang, Yaqiong[1,2,3] Cai, Zhangjie[1,2,3] Zhang, Manyin[1,2,3] Xu, Weigang[1,2,3] Zhao, Xinsheng[1,2,3] Lei, Yinru[1,2,3] Pan, Xu[1,2,3] Li, Jing[1,2,3] Dou, Zhiguo[1,2,3]

第一作者：Li, Wei;李卫

通信作者：Cui, LJ[1];Cui, LJ[2];Cui, LJ[3]

机构：[1]Chinese Acad Forestry, Inst Wetland Res, Beijing 100091, Peoples R China;[2]Beijing Key Lab Wetland Ecol Funct & Restorat, Beijing 100091, Peoples R China;[3]Beijing Hanshiqiao Natl Wetland Ecosyst Res Stn, Beijing 101399, Peoples R China

年份：2018

卷号：10

期号：1

外文期刊名：WATER

收录：;EI(收录号：20180404676911);Scopus(收录号：2-s2.0-85040775496);WOS:【SCI-EXPANDED(收录号:WOS:000424397400080)】；

基金：This study was supported by the Fundamental Research Funds for the Central Non-Profit Research Institution of CAF (CAFYBB2014QA029) and "The Lecture and Study Program for Outstanding Scholars from Home and Abroad" (CAFYBB2011007). We thank Alex Boon, PhD, and Deborah Ballantine, PhD, from Liwen Bianji, Edanz Group China (www.liwenbianji.cn/ac), for editing the English text of a draft of this manuscript.

语种：英文

外文关键词：tidal flow; constructed wetlands; nutrients removal; BP neural network

摘要：Nutrient removal in tidal flow constructed wetlands (TF-CW) is a complex series of nonlinear multi-parameter interactions. We simulated three tidal flow systems and a continuous vertical flow system filled with synthetic wastewater and compared the influent and effluent concentrations to examine (1) nutrient removal in artificial TF-CWs, and (2) the ability of a backpropagation (BP) artificial neural network to predict nutrient removal. The nutrient removal rates were higher under tidal flow when the idle/reaction time was two, and reached 90 +/- 3%, 99 +/- 1%, and 58 +/- 13% for total nitrogen (TN), ammonium nitrogen (NH4+-N), and total phosphorus (TP), respectively. The main influences on nutrient removal for each scenario were identified by redundancy analysis and were input into the model to train and verify the pollutant effluent concentrations. Comparison of the actual and model-predicted effluent concentrations showed that the model predictions were good. The predicted and actual values were correlated and the margin of error was small. The BP neural network fitted best to TP, with an R-2 of 0.90. The R-2 values of TN, NH4+-N, and nitrate nitrogen (NO3--N) were 0.67, 0.73, and 0.69, respectively.