摘要
滑坡位移预测是滑坡预警的重要依据之一。针对以往预测模型在预测精度上存在的不足,提出了一种基于时间序列与卷积门控循环单元(CNN-GRU)的滑坡位移动态预测模型。首先,利用小波分析确定存在趋势项位移后,利用指数平滑法对累计位移分解得到趋势项与周期项位移,将趋势项采用五次多项式拟合;之后,采用自相关函数检验位移的周期特征,利用灰色关联法判断各因子与周期项之间的关联度,并将周期项与影响因子一起输入CNN-GRU模型进行预测;最终,叠加得到累计位移预测值。以三峡库区白水河滑坡为例,选取2004年1月至2012年12月数据进行研究,最终预测结果平均绝对误差百分比仅为0.525%,RMSE为9.614、R^(2)为0.993。试验结果表明,CNN-GRU具有更高的预测精度。
Landslide displacement prediction is an important basis for early landslide warning.This paper proposes a prediction model of landslide moving states based on time series and convolutional gated recurrent unit(CNN-GRU)to deal with the shortcomings of previous prediction models.Firstly,after employing wavelet analysis to determine the displacement of the trend term,the exponential smoothing method is adopted to decompose the cumulative displacement to obtain two displacement types of the trend term and the periodic term,and the trend term is fitted by a five-order polynomial.Then,the autocorrelation function is utilized to test the periodic displacement characteristics,and the gray correlation method is applied to determine the correlation degree between each factor and the periodic term.Meanwhile,the periodic term and the influencing factor are input into the CNN-GRU model for prediction,and finally the predicted cumulative displacement value is obtained by superposition.By taking the Baishui River landslide in the Three Gorges Reservoir area as an example,this paper selects the data from January 2004 to December 2012 for study,and the average absolute error percentage of the final prediction results is only 0.525%,with RMSE of 9.614 and R^(2) of 0.993.Experimental results show that CNN-GRU has higher prediction accuracy.
作者
符振涛
李丽敏
王莲霞
任瑞斌
崔成涛
封青青
FU Zhentao;LI Limin;WANG Lianxia;REN Ruibin;CUI Chengtao;FENG Qingqing(School of Electronics and Information,Xi an Polytechnic University,Xi an 710600,China)
出处
《人民珠江》
2024年第2期1-8,共8页
Pearl River
基金
国家自然科学基金项目(62203344)
陕西省技术创新引导专项(2020CGXNG-009、2020CGXNX-009)
陕西省自然科学基础研究计划(2022JM-322)
陕西省教育厅服务地方专项(2022JM-322)。
关键词
位移预测
时间序列
卷积门控循环单元
白水河滑坡
displacement prediction
time series
convolutional gated recurrent unit
Baishui River landslide
