针对复杂水域水质变化机理难以掌握、水质预测建模困难且预测精度低的问题,将时间序列分析方法与机器学习方法引入水质预测领域,提出了基于差分自回归移动平均(ARIMA)与支持向量回归(SVR)组合模型的水质预测方法。数据经过预处理后先由ARIMA模型对其进行线性拟合,然后通过SVR模型预测残差以补偿其中的非线性变化。选择巢湖水域2004—2015年间的pH和溶解氧监测数据作为试验样本,通过Hodrick-Prescott(HP)滤波方法分析,结果表明2组数据具有不同的趋势特性和波动特性。根据精度评价指标对比分析模型的预测效果,结果表明组合模型预测精度显著提高,pH和溶解氧预测值与观测值间的相关系数均达到了0.99,均方根误差分别为0.20和0.61,平均绝对百分比误差分别为2.2%和6.6%。本研究所建立的组合预测方法具有较高的预测精度和较强的泛化能力,适用于复杂水域的水质预测。
Abstract
The research aims to tackle the difficulty in obtaining the mechanism of water quality change in complex waters and modeling water quality prediction as well as the low accuracy of prediction. A water quality prediction method integrating Autoregressive Integrated Moving Average (ARIMA) model and Support Vector Machine Regression (SVR) model is established. After pretreatment, the data are linearly fitted by ARIMA model, and then the residual is predicted by SVR model to compensate for the non-linear change. The monitoring data of pH value and dissolved oxygen in Chaohu Lake basin from 2004 to 2015 are selected as experimental samples. Analysis by HP filtering method shows that the two sets of data have different trends and fluctuation characteristics. The prediction effect of the hybrid model is analyzed through comparative study on evaluation indicators. The results conclude that the present model has high accuracy with the correlation coefficients between predicted values and observed values of pH value and dissolved oxygen both reaching 0.99, the root mean square error 0.20 and 0.61, and the mean absolute percentage error 2.2% and 6.6%, respectively. The ARIMA-SVR hybrid model is of high prediction accuracy and strong generalization ability, suitable for water quality prediction in complex waters.
关键词
水质预测 /
差分自回归移动平均 /
支持向量回归 /
组合模型 /
溶解氧
Key words
water quality prediction /
ARIMA /
SVR /
hybrid model /
dissolved oxygen
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李如忠. 水质预测理论模式研究进展与趋势分析[J]. 合肥工业大学学报(自然科学版),2006,29(1):26-29.
[2] 周彦辰,胡铁松,陈 进,等. 耦合动态方程的神经网络模型在水质预测中的应用[J].长江科学院院报,2017,34(9):1-5.
[3] 周志青,邹国防,王 磊,等. 基于ARIMA/RBF-NN的时间序列水质预测模型研究[J]. 科技通报,2017,33(9):236-240.
[4] 吴 静,李振波,朱 玲,等. 融合ARIMA模型和GAWNN的溶解氧含量预测方法[J]. 农业机械学报,2017,48(增刊):205-210.
[5] TAN Q F,LEI X H,WANG X,et al. An Adaptive Middle and Long-term Runoff Forecast Model Using EEMD-ANN Hybrid Approach[J]. Journal of Hydrology, 2018, 567: 767-780.
[6] 王军栋,齐维贵. 基于EMD-SVM的江水浊度预测方法研究[J]. 电子学报,2009,37(10):2130-2133.
[7] 黄 鹤,卢文喜,姜 雪. 支持向量机在水质评价及水位动态预测中的应用[J]. 中国农村水利水电,2012(9):30-33.
[8] RAUF A U, GHUMMAN A R, AHMAD S, et al. Performance Assessment of Artificial Neural Networks and Support Vector Regression Models for Stream Flow Predictions[J]. Environmental Monitoring and Assessment, doi: 10.1007/s10661-018-7012-9.
[9] 孙轶轩,邵春福,计 寻,等. 基于ARIMA与信息粒化SVR组合模型的交通事故时序预测[J]. 清华大学学报(自然科学版),2014,54(3):348-353.
[10]宋国君,国潇丹,杨 啸,等. 沈阳市PM2.5浓度ARIMA-SVM 组合预测研究[J].中国环境科学,2018,38(11):4031-4039.
[11]董国庆,孙伯寅,李 峥,等. 时间序列模型在水源水化学耗氧量预测中的应用[J]. 环境与健康杂志,2018,35(3):234-237.
[12]刘潭秋,王巧玲. 基于 ARIMA 模型的湘江流域 DO 和 NH4+-N 含量贝叶斯预测[J]. 湖南农业大学学报(自然科学版),2017,43(5):575-580.
[13]戴青松,王沛芳,王 超,等. 基于LWCA-SVM模型对
洪泽湖饮用水源地二河闸断面水质的预测分析[J]. 中国农村水利水电,2017(7):62-66.
[14]黄红梅.应用时间序列分析[M].北京:清华大学出版社,2016.
[15]张 森,石为人,石 欣,等. 基于偏最小二乘回归和SVM的水质预测[J].计算机工程与应用,2015,51(15):249-254.
[16]周志华.机器学习[M].北京:清华大学出版社,2016.
[17]赵志刚,张纯杰,苟向锋,等. 基于粒子群优化支持向量机的太阳电池温度预测[J]. 物理学报,2015,64(8):1-7.
基金
国家自然科学基金项目(51205005);北京市科技创新能力建设项目(PXM2017-014212-000013)
PDF(4598 KB)
