基于GM-GWO-SVR模型的斜坡形变预测
Forecasting the Surface Deformation of Slope Based on GM-GWO-SVR Model
丁德民 1向莉 2徐晨希 3徐元进4
作者信息
- 1. 武汉综合交通研究院有限公司,湖北 武汉 430015
- 2. 中国地质调查局长沙自然资源综合调查中心,湖南 宁乡 410600
- 3. 中国地质大学(武汉)地理与信息工程学院,湖北 武汉 430074
- 4. 中国地质大学(武汉)资源学院,湖北 武汉 430074
- 折叠
摘要
选取湖北省秭归县屈家坪斜坡作为研究区,使用 56 期 Sentinel-1 数据,采用 SBAS-InSAR 技术提取斜坡形变信息,分析发现斜坡呈现三处明显负形变,与降雨集中时段相吻合.在此基础上,建立了非等距 GM(1,2)、GM-SVR、GM-GWO-SVR预测模型,并对研究区进行形变预测,预测结果经 MAE、RMSE、MAPE和 SSE四个指标评估,结果表明 GM-GWO-SVR模型的预测效果最佳.
Abstract
This article selects the Qujiaping slope in Zigui County,Hubei Province as the study area,and extracts the information of slope deformation by SBAS-InSAR technology,using Sentinel-1 data of 56 periods.An analysis shows that the slope exhibits three obvious negative deformations,which are consistent with the concentrated rainfall periods.So non-equidistant GM(1,2)model,GM-SVR model and GM-GWO-SVR model are established,and deformation prediction is carried out.The prediction re-sults are evaluated by four indicators(MAE,RMSE,MAPE,and SSE).The results show that the GM-GWO-SVR model is better than the other two models,and is very effective.
关键词
形变预测/GM-GWO-SVR/斜坡/SBAS-InSARKey words
Deformation forecaste/GM-GWO-SVR/Slope/SBAS-InSAR引用本文复制引用
基金项目
湖北省交通厅科技项目(2022-11-4-8)
出版年
2024