基于时间序列的地下水开采中地面沉降预测方法  

Prediction Method of Ground Subsidence in Groundwater Exploitation Based on Time Series

作　　者：雷长彪 Lei Changbiao(Guangxi General Team of China Construction Materials Industry Geological Exploration Center,Guilin,China)

机构地区：[1]中国建筑材料工业地质勘查中心广西总队,广西桂林

出　　处：《科学技术创新》2024年第9期147-150,共4页Scientific and Technological Innovation

摘　　要：传统的地下水开采中地面沉降预测方法,只能收集历史地面沉降数据,不能消除其异常值,导致地面沉降量预测值与实测值相差较大,因此设计一种基于时间序列的地下水开采中地面沉降预测方法。首先对收集到的地面沉降数据进行预处理,消除异常值和数据间的量纲差异。将地面沉降数据转换为垂直向沉降速率,基于时间序列和历史数据建立地面沉降预测模型,并根据模型的预测结果分析未来的沉降趋势。实验结果表明,设计的基于时间序列的地下水开采中地面沉降预测方法,地面沉降量预测值与实测值基本一致,最小仅为0.9 mm。证明其方法更准确,具有实用性。Traditional methods for predicting ground subsidence in groundwater exploitation can only collect historical ground subsidence data and cannot eliminate its outliers,resulting in a significant difference between the predicted and measured ground subsidence values.Therefore,a time series based method for predicting ground subsidence in groundwater exploitation is designed.Firstly,preprocess the collected ground subsidence data to eliminate outliers and dimensional differences between the data.Convert ground subsidence data into vertical subsidence rate,establish a ground subsidence prediction model based on time series and historical data,and analyze future subsidence trends based on the predicted results of the model.The experimental results show that the designed time series based method for predicting ground subsidence in groundwater extraction has a predicted value of ground subsidence that is basically consistent with the measured value,with a minimum of only 0.9mm.Prove that its method is more accurate and practical.

关 键 词：时间序列 地下水 开采 地面沉降预测 

分 类 号：TU433[建筑科学—岩土工程]