摘要
研究水质变化趋势是水质监测的重要内容。水质变化过程是一个连续的过程,只是我们监测到的数据是离散的。由于水质监测数据具有不等时间观测、非线性变化的特点以及其数据内部表现出的函数性特征,考虑采用函数型数据分析方法进行研究。在本文中,我们在对样本数据进行函数化处理的基础上,本文将函数型回归模型应用于松花江肇源段的水质分析中,预测效果良好,为该地区的水质监测提供参考。
Studying the variation trend of water quality is an important part of water quality monitoring. Though the data we got via monitoring is discrete, the variation process of water quality is continuous. Considering the monitoring data of water quality has the characteristics of unequal time observation, nonlinear change and functional feature, we selected functional data analysis. Based on the functional processing of sample data, we used functional multiple regression method to predict water quality of Zhaoyuan section of Songhua River. And the cluster was carried out according to principal components scores. The results show that the functional data analysis method is effective. This method provides a reference for water quality monitoring in this area.
出处
《建模与仿真》
2022年第5期1352-1357,共6页
Modeling and Simulation
