摘要
根据西安市291监测井2000—2008年逐月地下水位埋深资料,分别采用SARIMA模型、BP神经网络模型及组合模型建模预测。结果表明,组合模型发挥了SARIMA模型良好的线性拟合能力与BP神经网络模型强大的非线性映射能力,其预测准确率高于单一模型的准确率,在地下水位埋深预测中将有较好的应用发展前景。
Based on the groundwater level data of 291 observation well of every month from the year 2000 to 2008, modeling prediction was carried out with SARIMA model, back propagation neural network model and combination model. The result showed that the combination model had both the good linear fitting ability of SARIMA model and the great nonlinear mapping ability of BPNN model. The prediction accuracy rate was higher than that of any single model. Therefore, the application of the combination model in the prediction of groundwater level was effective and feasible.
出处
《人民珠江》
2015年第4期112-115,共4页
Pearl River
基金
陕西省自然科学基金(2014JM1030)
中国地质调查局地质调查项目(12120113004800)
关键词
地下水位埋深
SARIMA模型
BP神经网络
时间序列预测
Groundwater Level
Seasonal Autoregressive Integrated Moving Average Model
Back Propagation Neural Network
Time Series Prediction
