Landslide Displacement Prediction Model Based on Time Series and CNN-GRU

Landslide displacement prediction is an important basis for early landslide warning.This paper proposes a prediction model of landslide moving states based on time series and convolutional gated recurrent unit (CNN-GRU) to deal with the shortcomings of previous prediction models.Firstly,after employ...

Full description

Saved in:
Bibliographic Details
Main Authors: FU Zhentao, LI Limin, WANG Lianxia, REN Ruibin, CUI Chengtao, FENG Qingqing
Format: Article
Language:zho
Published: Editorial Office of Pearl River 2024-01-01
Series:Renmin Zhujiang
Subjects:
Online Access:http://www.renminzhujiang.cn/thesisDetails#10.3969/j.issn.1001-9235.2024.02.001
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850091973315133440
author FU Zhentao
LI Limin
WANG Lianxia
REN Ruibin
CUI Chengtao
FENG Qingqing
author_facet FU Zhentao
LI Limin
WANG Lianxia
REN Ruibin
CUI Chengtao
FENG Qingqing
author_sort FU Zhentao
collection DOAJ
description Landslide displacement prediction is an important basis for early landslide warning.This paper proposes a prediction model of landslide moving states based on time series and convolutional gated recurrent unit (CNN-GRU) to deal with the shortcomings of previous prediction models.Firstly,after employing wavelet analysis to determine the displacement of the trend term,the exponential smoothing method is adopted to decompose the cumulative displacement to obtain two displacement types of the trend term and the periodic term,and the trend term is fitted by a five-order polynomial.Then,the autocorrelation function is utilized to test the periodic displacement characteristics,and the gray correlation method is applied to determine the correlation degree between each factor and the periodic term.Meanwhile,the periodic term and the influencing factor are input into the CNN-GRU model for prediction,and finally the predicted cumulative displacement value is obtained by superposition.By taking the Baishui River landslide in the Three Gorges Reservoir area as an example,this paper selects the data from January 2004 to December 2012 for study,and the average absolute error percentage of the final prediction results is only 0.525%,with RMSE of 9.614 and R<sup>2</sup> of 0.993.Experimental results show that CNN-GRU has higher prediction accuracy.
format Article
id doaj-art-b3ee8cc72bf2417a80545f375ab2b892
institution DOAJ
issn 1001-9235
language zho
publishDate 2024-01-01
publisher Editorial Office of Pearl River
record_format Article
series Renmin Zhujiang
spelling doaj-art-b3ee8cc72bf2417a80545f375ab2b8922025-08-20T02:42:14ZzhoEditorial Office of Pearl RiverRenmin Zhujiang1001-92352024-01-014550118327Landslide Displacement Prediction Model Based on Time Series and CNN-GRUFU ZhentaoLI LiminWANG LianxiaREN RuibinCUI ChengtaoFENG QingqingLandslide displacement prediction is an important basis for early landslide warning.This paper proposes a prediction model of landslide moving states based on time series and convolutional gated recurrent unit (CNN-GRU) to deal with the shortcomings of previous prediction models.Firstly,after employing wavelet analysis to determine the displacement of the trend term,the exponential smoothing method is adopted to decompose the cumulative displacement to obtain two displacement types of the trend term and the periodic term,and the trend term is fitted by a five-order polynomial.Then,the autocorrelation function is utilized to test the periodic displacement characteristics,and the gray correlation method is applied to determine the correlation degree between each factor and the periodic term.Meanwhile,the periodic term and the influencing factor are input into the CNN-GRU model for prediction,and finally the predicted cumulative displacement value is obtained by superposition.By taking the Baishui River landslide in the Three Gorges Reservoir area as an example,this paper selects the data from January 2004 to December 2012 for study,and the average absolute error percentage of the final prediction results is only 0.525%,with RMSE of 9.614 and R<sup>2</sup> of 0.993.Experimental results show that CNN-GRU has higher prediction accuracy.http://www.renminzhujiang.cn/thesisDetails#10.3969/j.issn.1001-9235.2024.02.001displacement predictiontime seriesconvolutional gated recurrent unitBaishui River landslide
spellingShingle FU Zhentao
LI Limin
WANG Lianxia
REN Ruibin
CUI Chengtao
FENG Qingqing
Landslide Displacement Prediction Model Based on Time Series and CNN-GRU
Renmin Zhujiang
displacement prediction
time series
convolutional gated recurrent unit
Baishui River landslide
title Landslide Displacement Prediction Model Based on Time Series and CNN-GRU
title_full Landslide Displacement Prediction Model Based on Time Series and CNN-GRU
title_fullStr Landslide Displacement Prediction Model Based on Time Series and CNN-GRU
title_full_unstemmed Landslide Displacement Prediction Model Based on Time Series and CNN-GRU
title_short Landslide Displacement Prediction Model Based on Time Series and CNN-GRU
title_sort landslide displacement prediction model based on time series and cnn gru
topic displacement prediction
time series
convolutional gated recurrent unit
Baishui River landslide
url http://www.renminzhujiang.cn/thesisDetails#10.3969/j.issn.1001-9235.2024.02.001
work_keys_str_mv AT fuzhentao landslidedisplacementpredictionmodelbasedontimeseriesandcnngru
AT lilimin landslidedisplacementpredictionmodelbasedontimeseriesandcnngru
AT wanglianxia landslidedisplacementpredictionmodelbasedontimeseriesandcnngru
AT renruibin landslidedisplacementpredictionmodelbasedontimeseriesandcnngru
AT cuichengtao landslidedisplacementpredictionmodelbasedontimeseriesandcnngru
AT fengqingqing landslidedisplacementpredictionmodelbasedontimeseriesandcnngru