A Hybrid VMD-BO-GRU Method for Landslide Displacement Prediction in the High-Mountain Canyon Area of China

Landslides are major geological hazards that pose serious threats to life and property, particularly in the high-mountain canyon regions of Sichuan, Yunnan, and southeastern Tibet. Displacement prediction plays a critical role in disaster prevention and mitigation. In recent years, machine learning...

Full description

Saved in:
Bibliographic Details
Main Authors: Bao Liu, Jiahuan Xu, Jiangbo Xi, Chaoying Zhao, Xiaosong Feng, Chaofeng Ren, Haixing Shang
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/11/1953
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849721809111351296
author Bao Liu
Jiahuan Xu
Jiangbo Xi
Chaoying Zhao
Xiaosong Feng
Chaofeng Ren
Haixing Shang
author_facet Bao Liu
Jiahuan Xu
Jiangbo Xi
Chaoying Zhao
Xiaosong Feng
Chaofeng Ren
Haixing Shang
author_sort Bao Liu
collection DOAJ
description Landslides are major geological hazards that pose serious threats to life and property, particularly in the high-mountain canyon regions of Sichuan, Yunnan, and southeastern Tibet. Displacement prediction plays a critical role in disaster prevention and mitigation. In recent years, machine learning methods based on InSAR data have achieved significant breakthroughs in landslide forecasting. However, models relying solely on a single data-driven approach may fail to fully capture the complex physical mechanisms of landslides, affecting both the reliability and interpretability of predictions. Therefore, developing effective landslide displacement prediction models is essential. The paper introduces a model designed to forecast the landslide displacement using Variational Mode Decomposition (VMD), Bayesian Optimization (BO), and Gated Recurrent Units (GRU). First, wavelet analysis is employed to identify the trend component in the landslide displacement data. Then, the total displacement is separated into its trend and periodic components through the application of the Variational Mode Decomposition (VMD) technique. A wide range of influencing factors is introduced, and Utilizing Grey Relational Analysis, we evaluate the interplay between contributing factors and all components of landslide displacement, both trend and periodic. Prediction models incorporate the trend and periodic terms, alongside the contributing factors, as input variables. The overall displacement is computed by summing the trend and periodic terms series using the Mianshawan landslide as a case study, experimental studies were conducted with landslide data from January 2019 to December 2022 with a Root Mean Squared Error (RMSE) of 0.402, Mean Absolute Error (MAE) of 0.187, Mean Absolute Percentage Error (MAPE) of 2.05%, and a coefficient of determination (R²) of 0.998. These findings indicate that, compared to traditional methods, our model delivers remarkable improvements in performance, offering higher prediction accuracy and greater reliability in the landslide forecasting task for the Mianshawan area.
format Article
id doaj-art-7b82f3dbc16f4eae8b3ea0f52334aba5
institution DOAJ
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-7b82f3dbc16f4eae8b3ea0f52334aba52025-08-20T03:11:32ZengMDPI AGRemote Sensing2072-42922025-06-011711195310.3390/rs17111953A Hybrid VMD-BO-GRU Method for Landslide Displacement Prediction in the High-Mountain Canyon Area of ChinaBao Liu0Jiahuan Xu1Jiangbo Xi2Chaoying Zhao3Xiaosong Feng4Chaofeng Ren5Haixing Shang6College of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, ChinaCollege of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, ChinaCollege of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, ChinaCollege of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, ChinaCollege of Resources and Civil Engineering, Northeastern University, Shenyang 110819, ChinaCollege of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, ChinaNorthwest Engineering Corporation Limited, Power China Group, Xi’an 710065, ChinaLandslides are major geological hazards that pose serious threats to life and property, particularly in the high-mountain canyon regions of Sichuan, Yunnan, and southeastern Tibet. Displacement prediction plays a critical role in disaster prevention and mitigation. In recent years, machine learning methods based on InSAR data have achieved significant breakthroughs in landslide forecasting. However, models relying solely on a single data-driven approach may fail to fully capture the complex physical mechanisms of landslides, affecting both the reliability and interpretability of predictions. Therefore, developing effective landslide displacement prediction models is essential. The paper introduces a model designed to forecast the landslide displacement using Variational Mode Decomposition (VMD), Bayesian Optimization (BO), and Gated Recurrent Units (GRU). First, wavelet analysis is employed to identify the trend component in the landslide displacement data. Then, the total displacement is separated into its trend and periodic components through the application of the Variational Mode Decomposition (VMD) technique. A wide range of influencing factors is introduced, and Utilizing Grey Relational Analysis, we evaluate the interplay between contributing factors and all components of landslide displacement, both trend and periodic. Prediction models incorporate the trend and periodic terms, alongside the contributing factors, as input variables. The overall displacement is computed by summing the trend and periodic terms series using the Mianshawan landslide as a case study, experimental studies were conducted with landslide data from January 2019 to December 2022 with a Root Mean Squared Error (RMSE) of 0.402, Mean Absolute Error (MAE) of 0.187, Mean Absolute Percentage Error (MAPE) of 2.05%, and a coefficient of determination (R²) of 0.998. These findings indicate that, compared to traditional methods, our model delivers remarkable improvements in performance, offering higher prediction accuracy and greater reliability in the landslide forecasting task for the Mianshawan area.https://www.mdpi.com/2072-4292/17/11/1953displacement predictiontime seriesgated cycle unitmianshawan landslide
spellingShingle Bao Liu
Jiahuan Xu
Jiangbo Xi
Chaoying Zhao
Xiaosong Feng
Chaofeng Ren
Haixing Shang
A Hybrid VMD-BO-GRU Method for Landslide Displacement Prediction in the High-Mountain Canyon Area of China
Remote Sensing
displacement prediction
time series
gated cycle unit
mianshawan landslide
title A Hybrid VMD-BO-GRU Method for Landslide Displacement Prediction in the High-Mountain Canyon Area of China
title_full A Hybrid VMD-BO-GRU Method for Landslide Displacement Prediction in the High-Mountain Canyon Area of China
title_fullStr A Hybrid VMD-BO-GRU Method for Landslide Displacement Prediction in the High-Mountain Canyon Area of China
title_full_unstemmed A Hybrid VMD-BO-GRU Method for Landslide Displacement Prediction in the High-Mountain Canyon Area of China
title_short A Hybrid VMD-BO-GRU Method for Landslide Displacement Prediction in the High-Mountain Canyon Area of China
title_sort hybrid vmd bo gru method for landslide displacement prediction in the high mountain canyon area of china
topic displacement prediction
time series
gated cycle unit
mianshawan landslide
url https://www.mdpi.com/2072-4292/17/11/1953
work_keys_str_mv AT baoliu ahybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT jiahuanxu ahybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT jiangboxi ahybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT chaoyingzhao ahybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT xiaosongfeng ahybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT chaofengren ahybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT haixingshang ahybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT baoliu hybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT jiahuanxu hybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT jiangboxi hybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT chaoyingzhao hybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT xiaosongfeng hybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT chaofengren hybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina
AT haixingshang hybridvmdbogrumethodforlandslidedisplacementpredictioninthehighmountaincanyonareaofchina