山东省油料产量的时空分析

The Spatio-temporal Analysis of Oilseed Yield of Shandong Province

在空间层面上,运用空间自相关方法分析了以农业产业为主的山东省87个县市油料产量的空间集聚特征。在时间轴上,基于ARMA模型对山东省油料总产量进行了预测。结果表明:山东省县域单元油料产量在空间上并非随机分布,油料产量比较接近的县市在空间分布上也比较邻近,呈集中分布。40个县域单元的油料产量具有显著的空间集聚特征。根据山东省1978—2008年油料产量的统计资料,建立了山东省油料产量的时间序列ARMA(2,1,2)模型,预测效果较理想,预测值与实际数值之间的平均相对误差仅为2·12%。

Spatial model from perspective, the study performed the Moran′I computerization to analyze the spatial autocorrelation characteristics of the oilseed yield on country level, based on the data about oilseed yield of 87 country units in Shandong province. Results showed that the Moran′I coefficient 40 country units with oilseed yield has obvious clustering characteristics, the autocorrelation of the other country units was not evident. On the other hand, the study also carried out to predict the total oilseed yield with ARMA (2, 1, 2) model on basis of time series data, in order to explore the trend of the total oilseed yield in Shandong province, the average relative error between observation value and prediction value is 2·12% only using statistical oilseed yield data, which were gathered annually over the course of 31 years between 1978 and 2008. In a word, Moran′I coefficient and ARMA (2, 1, 2) model can fairly clarify the spatial and temporal status of oilseed yield. What′s more, the study is to provide a better understanding of spatial and temporal patterns of oilseed yield in Shandong province.