Prediction of Nitrogen Concentration in Taihu Lake Based on AdaBoost Machine Learning Model
-
摘要: 市政污水处理厂出水是自然水体的重要污染来源,处理后的生活污水排入水体,对受纳水体水质产生重要的影响。为实现对太湖总氮浓度的准确预测,收集并分析了太湖水体水质监测数据和太湖流域212个污水处理厂的实时运行监测数据,采用皮尔逊相关系数(Pearson correlation coefficient)分析了太湖水体总氮浓度与市政污水处理厂相关运行指标的相关性,结合相关性较高的前五项指标与太湖水质监测数据,利用临近算法(KNN),决策树以及AdaBoost三种机器学习模型对太湖水体总氮浓度月平均值进行了预测。其中AdaBoost的精度更高、准确性更好,拟合优度为0.84,平均绝对误差在14.08%以内。模型特征重要性分析表明,太湖硝态氮,氨氮和总磷等指标对总氮浓度预测有重要的影响。
-
关键词:
- 皮尔逊相关系数 /
- 市政污水处理厂 /
- N排放 /
- AdaBoost机器学习
Abstract: Domestic waste water is an important source of natural water pollution. The treated domestic waste water is discharged into natural water bodies through the pipe network,which has a serious impact on the quality of the receiving water body. The water quality monitoring data from Taihu Lake and the plant-resolved and actual operation data of 212 waste water treatment plants in Taihu Lake from 2007 to 2015 are collected and analyzed in order to accurately predict the total nitrogen in Taihu Lake. The Pearson correlation coefficient is used to calculate the relationship between Taihu Lake water quality and the WWTP effluent indexes. For the top five items with high correlation,three machine learning models,K-Nearest Neighbors(KNN),Decision Tree,and AdaBoost are used to predict the monthly average TN in Taihu Lake. In general,AdaBoost has higher precision and better accuracy,with a goodness-of-fit index of 0.84 and a root mean square error less than 14.08%,which establishes a good mathematical model for predicting of TN concentration of Taihu Lake. Meanwhile,the model finds that NO3-N,NH4-N,TP in Taihu Lake and NH4-N in effluent of WWTP can cause an important impact on the TN concentration of Taihu Lake. -
-
[1] YU C,HUANG X,CHEN H,et al. Managing nitrogen to restore water quality in China[J]. Nature,2019,567(7 749):516-520.
[2] TONG Y,WANG M,PENUELAS J,et al. Improvement in municipal wastewater treatment alters lake nitrogen to phosphorus ratios in populated regions[J]. Proc Natl Acad Sci U S A,2020,117(21):11 566-11 572.
[3] WANG J L,FU Z S,QIAO H X,et al. Assessment of eutrophication and water quality in the estuarine area of Lake Wuli,Lake Taihu,China[J]. Science of the Total Environment,2019,650:1 392-1 402.
[4] FAN C,WANG W-S,LIU K F-R,et al. Sensitivity Analysis and Water Quality Modeling of a Tidal River Using a Modified StreeterPhelps Equation with HEC-RAS-Calculated Hydraulic Characteristics[J]. Environmental Modeling&Assessment,2012,17(6):639-651.
[5] 李军,张明华. WASP富营养化水质模型在GIS中的完全集成研究[J].长江流域资源与环境,2012,21:93-98. [6] ZHANG Y,XIA J,SHAO Q,et al. Water quantity and quality simulation by improved SWAT in highly regulated Huai River Basin of China[J]. Stochastic Environmental Research and Risk Assessment,2011,27(1):11-27.
[7] 胡志洋,李翠梅,薛天一.基于灰色关联和ABC-BP神经网络的叶绿素a浓度预测[J].水电能源科学,2021:55-58. [8] 成浩科,沈菲.基于随机森林的河流总磷预测模型及影响因素分析[J].环境保护科学,2021:62-67. [9] 付泰然,刘广鑫,万全元,等.基于栈式自编码BP神经网络预测水体亚硝态氮浓度模型[J].水产学报,2019:958-967. [10] 李修竹,苏荣国,张传松,等.基于支持向量机的长江口及其邻近海域叶绿素a浓度预测模型[J].中国海洋大学学报(自然科学版),2019,49(1):69-76. [11] 闵屾,钱荣树,朱广伟,等. 2007-2015年太湖水体理化监测数据集[J].中国科学数据(中英文网络版),2020,5(1):85-93. [12] ZENKO B,TODOROVSKI L,DZEROSKI S. A comparison of stacking with meta decision trees to bagging,boosting,and stacking with other methods[M]. Los Alamitos:IEEE Computer Soc,2001:669-670.
[13] 庞聪,江勇,廖成旺,等.基于AdaBoost集成学习的强震动观测抗干扰技术研究[J].四川地震,2020:14-18. [14] 赵刚,黄汉明,卢欣欣,等.基于BP-Adaboost方法的天然地震和人工爆炸事件波形信号分类识别研究[Z].地震工程学报,2017:557-563. [15] ABEYWICKRAMATENINDRA, MUHAMMAD AAMIR CHEEMA,TANIARDAVID. k-Nearest Neighbors on Road Networks:A Journey in Experimentation and In-Memory Implementation[J].Proceedings of the VLDB Endowment,2016,9:492-503.
[16] WANG P,SHEN C,BARNES N,et al. Fast and robust object detection using asymmetric totally corrective boosting[J]. IEEE Trans Neural Netw Learn Syst,2012,23(1):33-46.
[17] 殷小伟,强志民,贲伟伟,等.污水厂不同生物处理工艺对抗生素的去除效果[J].中国给水排水,2012,28(22):22-26. [18] 汪峰,钱庄,张周,等.污水处理厂尾水对排放河道水质的影响[J].安徽农业科学,2016,44(14):65-68. [19] CHEN K Y,CHEN H X,ZHOU C L,et al. Comparative analysis of surface water quality prediction performance and identification of key water parameters using different machine learning models based on big data[J]. Water Research,2020,171(115 454):1-10.
[20] TIYASHA,TUNG T M,YASEEN Z M. A survey on river water quality modelling using artificial intelligence models:2000-2020[J]. Journal of Hydrology,2020,585:124 670.
[21] 嵇晓燕,杨凯,陈亚男,等.基于ARIMA和Prophet的集成学习模型在水质预测中的应用研究[J/OL].水资源保护,2021:1-11.[2022-03-28]. http://kns. cnki. net/kcms/detail/32.1356. TV.20211008.1634.022.html. [22] 王凯翔.基于多元回归和神经网络途径的太湖富营养化指标分析与预测[J].南京师范大学学报,2017,17(2):70-74. [23] YANG X Y,LIU Q,LUO X Z,et al. Spatial Regression and Prediction of Water Quality in a Watershed with Complex Pollution Sources[J]. Scientific Reports,2017,7(1):8 318.
[24] 邓延慧,王正文.湖泊沉积物氮磷赋存转化研究进展[J].绿色科技,2021,23(6):66-71. [25] LU J Y,WANG X M,LIU H Q,et al. Optimizing operation of municipal wastewater treatment plants in China:The remaining barriers and future implications[J]. Environment International,2019,129:273-278.
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0