Dynamic prediction of landslide life expectancy using ensemble system incorporating classical prediction models and machine learning

扫码查看

原文链接

万方数据
维普

外文摘要：With the development of landslide monitoring system,many attempts have been made to predict land-slide failure-time utilizing monitoring data of displacements.Classical models(e.g.,Verhulst,GM(1,1),and Saito models)that consider the characteristics of landslide displacement to determine the failure-time have been investigated extensively.In practice,monitoring is continuously implemented with mon-itoring data-set updated,meaning that the predicted landslide life expectancy(i.e.,the lag between the predicted failure-time and time node at each instant of conducting the prediction)should be re-evaluated with time.This manner is termed"dynamic prediction".However,the performances of the classical mod-els have not been discussed in the context of the dynamic prediction yet.In this study,such performances are investigated firstly,and disadvantages of the classical models are then reported,incorporating the monitoring data from four real landslides.Subsequently,a more qualified ensemble model is proposed,where the individual classical models are integrated by machine learning(ML)-based meta-model.To evaluate the quality of the models under the dynamic prediction,a novel indicator termed"discredit index(β)"is proposed,and a higher value of β indicates lower prediction quality.It is found that Verhulst and Saito models would produce predicted results with significantly higher β,while GM(1,1)model would indicate results with the highest mean absolute error.Meanwhile,the ensemble models are found to be more accurate and qualified than the classical models.Here,the performance of decision tree regression-based ensemble model is the best among the various ML-based ensemble models.

外文关键词：

Dynamic predictionLandslide life expectancyMachine learningEnsemble system

作者：

Lei-Lei Liu、Hao-Dong Yin、Ting Xiao、Lei Huang、Yung-Ming Cheng

展开 >

作者单位：

Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Monitoring,Ministry of Education,School of Geosciences and Info-Physics,Central South University,Changsha 410083,China

College of Civil Engineering and Architecture,Wenzhou University,Wenzhou 325035,China

Key Laboratory of Engineering and Technology for Soft Soil Foundation and Tideland Reclamation of Zhejiang Province,Wenzhou 325035,China

Wenzhou Key Laboratory of Traffic Piezoelectric Engineering Technology,Wenzhou 325035,China

Zhejiang International Science and Technology Cooperation Base of Ultra-soft Soil Engineering and Smart Monitoring,Wenzhou 325035,China

School of Civil Engineering,Qingdao University of Technology,Qingdao 266033,China

展开 >

基金：

湖南省自然科学基金湖南省自然科学基金Special Fund for Safety Production Prevention and Emergency of Hunan ProvinceResearch Project of Geological Bureau of Hunan ProvinceResearch Project of Geological Bureau of Hunan ProvinceFund of Wenzhou Municipal Science and Technology BureauFundamental Research Funds for Central Universities of the Central South University

项目编号：

2020JJ57042022JJ200582021YJ009HNGSTP202106HNGSTP2022022022G00152023ZZTS0470

出版年：

2024

DOI：

10.1016/j.gsf.2023.101758

地学前缘(英文版)

中国地质大学（北京）北京大学

地学前缘(英文版)

CSTPCD

影响因子：0.576

ISSN：1674-9871

年,卷(期)：2024.15(2)

参考文献量62