A Novel Model for Landslide Displacement Prediction Based on EDR Selection and Multi-Swarm Intelligence Optimization Algorithm.

Junrong Zhang,Qianyun Wang,Dwayne D Tannant,Yankun Wang,Ding Xia,Huiming Tang,Chengyuan Lin

doi:10.3390/s21248352

Abstract

With the widespread application of machine learning methods, the continuous improvement of forecast accuracy has become an important task, which is especially crucial for landslide displacement predictions. This study aimed to propose a novel prediction model to improve accuracy in landslide prediction, based on the combination of multiple new algorithms. The proposed new method includes three parts: data preparation, multi-swarm intelligence (MSI) optimization, and displacement prediction. In the data preparation, the complete ensemble empirical mode decomposition (CEEMD) is adopted to separate the trend and periodic displacements from the observed cumulative landslide displacement. The frequency component and residual component of reconstructed inducing factors that related to landslide movements are also extracted by the CEEMD and t-test, and then picked out with edit distance on real sequence (EDR) as input variables for the support vector regression (SVR) model. MSI optimization algorithms are used to optimize the SVR model in the MSI optimization; thus, six predictions models can be obtained that can be used in the displacement prediction part. Finally, the trend and periodic displacements are predicted by six optimized SVR models, respectively. The trend displacement and periodic displacement with the highest prediction accuracy are added and regarded as the final prediction result. The case study of the Shiliushubao landslide shows that the prediction results match the observed data well with an improvement in the aspect of average relative error, which indicates that the proposed model can predict landslide displacements with high precision, even when the displacements are characterized by stepped curves that under the influence of multiple time-varying factors.

Highlights

Landslides reactivated by the impoundment of a reservoir or rainfall can cause catastrophic losses such as casualties, road burying, and house damages, which seriously threaten the property and life safety of human society [1,2]
This paper aims to improve the accuracy of landslide displacement prediction by constructing a novel prediction model combined with the complete ensemble empirical mode decomposition (CEEMD) method, edit distance on real sequence (EDR) method, and multi-swarm-intelligence (MSI) algorithm
A novel prediction model for landslide displacement prediction was proposed to improve the accuracy by the combination of multiple algorithms

Summary

Introduction

Landslides reactivated by the impoundment of a reservoir or rainfall can cause catastrophic losses such as casualties, road burying, and house damages, which seriously threaten the property and life safety of human society [1,2]. In 2019, there were approximately 6181 geological hazard events in China, causing economic losses of 2.77 billion yuan. 4220 were landslides, accounting for 68% of the geological hazards [3]. The development of more accurate and effective landslide displacement prediction methods is of great significance for the early warning of catastrophic landslide movements and is an active research area [4,5,6,7]. Landslide prediction models can generally be divided into physical–mechanical and phenomenological models [8,9]. The physical–mechanical models are generally recognized as originating from the empirical formula proposed by Saito in 1965 [10], and a series of models have been developed based on creep theory in the following decades [11,12]

Objectives

Methods

Results

Discussion

Conclusion