| 北斗监测滑坡及其梯度增强多元回归位移预测北大核心CSCD |
| |
| 引用本文： | 明璐璐,高品红,刘宇航,王鹏,涂梨平,柯福阳.北斗监测滑坡及其梯度增强多元回归位移预测北大核心CSCD[J].测绘通报,2022,0(10):7-12. |
| |
| 作者姓名： | 明璐璐 高品红 刘宇航 王鹏 涂梨平 柯福阳 |
| |
| 作者单位： | 1. 南京信息工程大学遥感与测绘工程学院, 江苏 南京 210440;2. 浙江华东建设工程有限公司, 浙江 杭州 310014;3. 西宁市测绘院, 青海 西宁 810001;4. 西宁市国土勘测规划研究院, 青海 西宁 810000;5. 江西核工业测绘院集团有限公司, 江西 南昌 330038;6. 南京信息工程 大学无锡研究院, 江苏 无锡 214000 |
| |
| 基金项目： | 江西省重点研发计划(20201BBG71001);无锡市科技发展资金项目(N20201011) |
| |
| 摘 要： | 山体滑坡位移量预测精度主要受预测模型和参量的影响,而基于回归模型和灰度预测模型的传统滑坡预测模型主要存在模型预测结构单调、引入的预测影响参量不全面、长期性预测精度低等问题,因此,本文基于北斗数据提出了一种基于梯度增强多元回归算法的滑坡预测方法。梯度增强多元回归模型在考虑多重因素的前提下,使用如降水量、土壤湿度、地形参数等滑坡主影响因子作为回归模型参量,同时结合梯度增强方法,可以增强预测模型的有效结构,提升数据的使用率,进而提高长、短期的滑坡位移量预测精度。最后以西宁市南山寺滑坡带为例,考虑降水、地面沉降、地形地貌等诱发滑坡的关键因素,分别基于梯度增强多元回归模型、贝叶斯岭回归模型、弹性网络回归模型及支持向量机回归模型进行试验。结果表明,梯度增强多元回归模型的方差(EV)结果为0.99 mm^(2),均方差(MSE)结果为0.04 mm,平均绝对误差(MAE)结果为0.15 mm,且利用梯度增强多元回归模型对2020年12月的表面位移量进行预测,发现相对误差区间为(-0.8%,0.8%],预测精度最高。因此,相对而言,梯度增强多元回归预测模型精度更优、效率更高,更能准确反映滑坡表面位移量的变化状态,精确地对滑坡体进行全天候监控、预警,保障滑坡体周边环境的安全。
|
| 关 键 词： | 滑坡位移 北斗监测 预测 梯度增强多元回归模型 |
| 收稿时间： | 2022-06-21 |
Landslide monitoring in BeiDou and displacement prediction based on GBR |
| |
| MING Lulu,GAO Pinhong,LIU Yuhang,WANG Peng,TU Liping,KE Fuyang.Landslide monitoring in BeiDou and displacement prediction based on GBR[J].Bulletin of Surveying and Mapping,2022,0(10):7-12. |
| |
| Authors: | MING Lulu GAO Pinhong LIU Yuhang WANG Peng TU Liping KE Fuyang |
| |
| Abstract: | The accurate prediction of landslide displacement is mainly affected by the prediction model and parameters. Traditional landslide prediction models, such as regression model and grey prediction model, have the shortcomings of single factor and low accuracy of long-term prediction. However, gradient enhanced multiple regression model can realize long-term prediction of landslide surface displacement on the basis of considering multiple factors, which can effectively make up for the above shortcomings. At last, it will be used in nanshan landslide in xining city as an example, based on the various influence factors of landslide, merit-based landslide induced key factors (precipitation, geological structure, topography). And a variety of methods are used for comparative analysis, including gradient boosting regression, Bayesian ridge, elastic net and support vector regression of four model. Experimental results show that the EV, MSE and MAE of GBR are 0.99 mm2, 0.04 mm and 0.15 mm, respectively. In addition, GBR is used to predict the surface displacement in December 2020, and the relative error is found in the range from-0.8% to 0.8%. The prediction accuracy is the highest. Therefore, the gradient enhanced multiple regression prediction model is relatively more accurate and efficient. It can accurately reflect the change state of landslide surface displacement, accurately monitor and warn the landslide body all day long, and ensure the safety of the surrounding environment of the landslide body. |
| |
| Keywords: | landslide BeiDou monitoring prediction gradient boosting regression |
| 本文献已被 维普 等数据库收录！ |
| 点击此处可从《测绘通报》浏览原始摘要信息 |
| 点击此处可从《测绘通报》下载免费的PDF全文 |
|
