摘要
Abstract
Five interpolation methods including inverse distance weighted method(IDW),global polynomial method(GPI),local polynomial method(LPI),simple Kriging method(SK)and empirical Bayesian Kriging method(EBK)were used to interpolate rainstorm in Heyuan.By conducting cross validation and comparing the accuracy of interpolation results based on mean absolute error(MAE),root mean square error(RMSE),and coefficient of determination(R2).The results showed that the five interpolation methods could basically reflect the spatial distribution of rainstorm,and the IDW interpolation results exhibited the phenomenon of"concentric circles";the interpolation results of LPI and GPI were smoother,but they were susceptible to extreme values;and the interpolation effect of SK and EBK was generally good.According to the accuracy evaluation index results,GPI had the worst accuracy;EBK had the highest accuracy and the smallest error,which made it the optimal interpolation method among the five interpolation methods.关键词
空间插值/暴雨/交叉验证Key words
spatial interpolation/rainstorm/cross validation分类
天文与地球科学
