摘要
通过建立基于自适应搜索权重的滑坡位移组合预测模型,对滑坡位移进行预测,提高了预测精度。以三峡库区店子湾滑坡为例,对GPS监测累积水平位移进行预测,同时构建平方和误差(SSE)、平均绝对误差(MAE)、均方误差(MSE)、平均绝对百分比误差(MAPE)和均方百分比误差(MSPE)等5个评价指标进行全方位评价。计算结果可知,该模型预测的平均绝对误差(MAE)为3.354 6,均方误差(MSE)为1.254 1,平均绝对百分比误差(MAPE)为5.53%,均方百分比误差(MSPE)为2.07%,全面优于单预测方法,取得较好的效果。
By establishing the combination model based on adaptive weight searching to forecast landslide displacement, the forecast accuracy will be provided. Taking the Dianziwan landslide in Three Gorges reservoir area as an example, the model is used to predict the GPS monitoring cumulative horizontal displacement, and at the same time, five evaluation indexes include the sum squared error （SSE）, the mean absolute error （ MAE）, the mean square error （ MSE）, the mean absolute percentage error （MAPE） and the mean square error percentage （MSPE） are built to make comprehensive evaluation. It can be known by the calculation results that the MAE is 3. 354 6, the MSE is 1. 254 1, the MAPE is 5.53% and the MSPE is 2.07%. The results are better than that of single prediction method.
出处
《水力发电》
北大核心
2016年第2期26-28,37,共4页
Water Power
基金
国家自然科学基金资助项目(41172298
41302260)
湖北省自然科学基金创新群体项目(2012FFA040)
关键词
滑坡
位移
组合预测模型
自适应搜索
权重
landslide
displacement
combination forecasting model
adaptive searching
weight
