论文部分内容阅读
地下水埋深的变化过程是一个复杂的非线性过程,这种具有复杂的非线性组合特征的序列,使用某一种模型进行预测,结果往往不理想.在分析了灰色GM(1,1)模型、灰色GM(1,1)周期性修正模型和时序AR(n)模型的优点和缺点基础上,提出了一种新的灰色时序组合预报模型.该方法利用了GM预测所需原始数据少、方法简单的优点,用周期修正方法反映其地下水位埋深周期性波动的特征,用AR(n)模型预报其地下水位埋深的随机变化.实例研究表明,这种方法方便简洁实用且预测结果接近于实际观测值,为其它地区的地下水位埋深和相关时间序列的分析研究提供参考与借鉴作用.
The process of groundwater depth change is a complicated nonlinear process, and the sequence with complex nonlinear combination features is often not ideal using a certain model.After analyzing the gray GM (1,1) model , Gray GM (1,1) Periodicity Correction Model and Time Series AR (n) Model, this paper proposes a new gray time series combination forecasting model, which uses less original data, Method is simple, the periodic variation of the groundwater table buried depth is reflected by periodic correction method, and AR (n) model is used to predict the random variation of groundwater table buried depth.Examples show that this method is simple and practical and predictive Close to the actual observed values, and provide reference and reference for the analysis and study of the groundwater table depth in other areas and related time series.