论文部分内容阅读
利用气象因子计算ET0时,各气象因子之间经常存在多重相关性现象,从而导致所建多元回归模型失真,预测精度低。本文以新疆塔里木盆地北缘区的尉犁县为例,采用偏最小二乘回归建立ET0模型,利用主成分分析与典型相关分析思想,采用成分提取的方法,有效解决了各气象因子间的多重相关性问题,所建ET0模型取得较好效果。
When meteorological factors are used to calculate ET0, there are often multiple correlations among meteorological factors, which leads to distortion of the constructed multiple regression model and low prediction accuracy. Taking Yuli County in northern margin of Tarim Basin, Xinjiang as an example, partial least-squares regression was used to establish ET0 model. Principal component analysis and Canonical Correlation Analysis were used to extract the constituents, which effectively solved the multiple correlations among meteorological factors Sexual issues, the ET0 model built to achieve better results.