摘要
为了提高滑坡变形预测工作中的预测精度,采取基于S型增长曲线的组合预测方法,通过最优权重来组合滑坡预警预报中常用的Verhulst模型、Pearl模型,并将组合预测模型应用于历史滑坡的变形预测中进行验证研究。结果表明:单一预测模型中,Verhulst模型的预测效果较Pearl模型好,但拟合效果则是Pearl模型较佳;而基于最优权重的组合预测模型能充分利用单一预测模型的优势,能有效地提高滑坡变形预测的精确性。
In order to improve the prediction accuracy of landslide deformation prediction,the combination forecasting method based on S-shaped growth curve is adopted,which consist of the Verhulst model and Pearl model commonly used in landslide early warning and forecasting by the optimal weight,and the combination forecasting model is applied to the deformation prediction of historical landslides.The results show that in the single prediction model,the prediction effect of Verhulst model is better than that of Pearl model,but the fitting effect of Pearl model is better.However,the combination forecasting model based on optimal weight can make full use of the advantages of a single prediction model and can effectively improve the accuracy of landslide deformation prediction.
作者
彭鑫
贺小黑
贺鑫焱
彭必建
PENG Xin;HE Xiaohei;HE Xinyan;PENG Bijian(School of Water Resources&Environmental Engineering,East China University of Technology,330013,Nanchang,PRC;Institute of Engineering Design,Academy of People’s Armed Police,100012,Beijing,PRC;Beijing Guoxinhuayuan Technology Co.,Ltd.,100055,Beijing,PRC;Yunnan Geological Engineering Survey and Design Institute,650041,Kunming,PRC)
出处
《江西科学》
2022年第2期335-340,共6页
Jiangxi Science
关键词
滑坡
变形预测
预测精度
S型增长曲线
组合预测模型
landslides
deformation prediction
prediction accuracy
S-shaped growth curves
combination prediction model
