扎龙湿地发展趋势的ARIMA分析  

Forecast of non-stationary time series for Zhalong wetland area of development

作　　者：郭龙珠[1] 王福林[1] 郭龙胜[2] 王志兴[2] 

机构地区：[1]东北农业大学工程学院,黑龙江哈尔滨150030 [2]黑龙江省水利水电勘测设计研究院,黑龙江哈尔滨150080

出　　处：《农业系统科学与综合研究》2005年第4期280-282,共3页System Sciemces and Comprehensive Studies In Agriculture

基　　金：国家自然科学基金项目(30370825);教育部重点项目(02049)

摘　　要：湿地面积发展模型不仅是非平稳序列,而且是非发散的季节周期相关序列,季节序列的特点是季节时滞处强相关。应用非平稳时间序列分析扎龙湿地面积演化动态,可有效地剔除用于预测的历史数据中的野值及奇异点,修正了预测结果,对湿地面积演化有较好的解释能力,利于建模和预测。结果表明,该方法用于湿地发展面积预测建模速度快、预测精度高,是一种行之有效的方法。图4,表3,参3。Wetland area development model is not only a non-stationary time series, but also a non-divergence seasonal period correlate series, and its character is strong correlate at seasonal time lag. Using non-stationary time series analyze Zhalong wetland area development, can pick up the outliers and singular values effectively in the historical data for the prediction and may correct the prediction results.The results of calculation example from a real wetland area development forecast show that this method is effectual, with high modeling speed and high forecasting accuracy can be obtained.

关 键 词：非平稳时间序列分析 扎龙湿地 湿地面积 季节周期 

分 类 号：F323.213[经济管理—产业经济]