Research and analysis of the TCN-Multihead-Attention prediction model of landslide deformation in the Three Gorges Reservoir area, China

Landslide deformation prediction is a crucial task in geotechnical engineering and disaster prevention. Developing an accurate and reliable landslide displacement prediction model is vital for effective landslide warning systems. This paper proposes a TCN-Multihead-Attention prediction model for lan...

Full description

Saved in:
Bibliographic Details
Main Authors: Huan Chen, Yixuan Li, Yimin Liu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Earth Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/feart.2025.1587623/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850156840490369024
author Huan Chen
Huan Chen
Yixuan Li
Yimin Liu
author_facet Huan Chen
Huan Chen
Yixuan Li
Yimin Liu
author_sort Huan Chen
collection DOAJ
description Landslide deformation prediction is a crucial task in geotechnical engineering and disaster prevention. Developing an accurate and reliable landslide displacement prediction model is vital for effective landslide warning systems. This paper proposes a TCN-Multihead-Attention prediction model for landslide deformation based on temporal convolutional networks (TCNs). We collected 8 years of monitoring data from the Huangniba Dengkan landslide in the Three Gorges Reservoir area, including surface deformation (horizontal displacement and elevation), rainfall, and reservoir levels. A comprehensive analysis was conducted to assess the effects of rainfall, reservoir levels, and elevation on landslide horizontal displacement. Utilizing the multi-input and single-output characteristics of the long-period time series dataset, we developed the TCN-Multihead-Attention prediction model of landslide deformation. Model evaluation demonstrated that the coefficient of determination (R2) for the test set reached 0.995, with MAPE and RMSE at only 0.482 and 7.180, respectively, indicating high accuracy. Additionally, we developed other prediction models based on single TCN, Attention-based Transformer, RNN-based LSTM, and the hybrid CNN-BiLSTM for comparison. Compared with existing models, the TCN-Multihead-Attention model integrates dilated causal convolutions from TCN with multi-head attention to effectively fuse nonlinear interactions of multi-source environmental factors, capture long-term evolutionary trends, and accurately identify local mutation patterns, demonstrating superior reliability for landslide deformation forecasting in reservoir regions.
format Article
id doaj-art-9e5d15b05c8a478aab3e518ab804d915
institution OA Journals
issn 2296-6463
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Earth Science
spelling doaj-art-9e5d15b05c8a478aab3e518ab804d9152025-08-20T02:24:22ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632025-06-011310.3389/feart.2025.15876231587623Research and analysis of the TCN-Multihead-Attention prediction model of landslide deformation in the Three Gorges Reservoir area, ChinaHuan Chen0Huan Chen1Yixuan Li2Yimin Liu3School of Intelligent Manufacturing, Chengdu Technological University, Chengdu, ChinaInstitute of Exploration Technology, CGS, Chengdu, ChinaSchool of Information Science, Japan Advanced Institute of Science and Technology, Nomi, JapanSchool of Intelligent Manufacturing, Chengdu Technological University, Chengdu, ChinaLandslide deformation prediction is a crucial task in geotechnical engineering and disaster prevention. Developing an accurate and reliable landslide displacement prediction model is vital for effective landslide warning systems. This paper proposes a TCN-Multihead-Attention prediction model for landslide deformation based on temporal convolutional networks (TCNs). We collected 8 years of monitoring data from the Huangniba Dengkan landslide in the Three Gorges Reservoir area, including surface deformation (horizontal displacement and elevation), rainfall, and reservoir levels. A comprehensive analysis was conducted to assess the effects of rainfall, reservoir levels, and elevation on landslide horizontal displacement. Utilizing the multi-input and single-output characteristics of the long-period time series dataset, we developed the TCN-Multihead-Attention prediction model of landslide deformation. Model evaluation demonstrated that the coefficient of determination (R2) for the test set reached 0.995, with MAPE and RMSE at only 0.482 and 7.180, respectively, indicating high accuracy. Additionally, we developed other prediction models based on single TCN, Attention-based Transformer, RNN-based LSTM, and the hybrid CNN-BiLSTM for comparison. Compared with existing models, the TCN-Multihead-Attention model integrates dilated causal convolutions from TCN with multi-head attention to effectively fuse nonlinear interactions of multi-source environmental factors, capture long-term evolutionary trends, and accurately identify local mutation patterns, demonstrating superior reliability for landslide deformation forecasting in reservoir regions.https://www.frontiersin.org/articles/10.3389/feart.2025.1587623/fulllandslide deformation predictionTCN-Multihead-Attention modeldeep learningthe three gorges reservoir areaenvironmental factors
spellingShingle Huan Chen
Huan Chen
Yixuan Li
Yimin Liu
Research and analysis of the TCN-Multihead-Attention prediction model of landslide deformation in the Three Gorges Reservoir area, China
Frontiers in Earth Science
landslide deformation prediction
TCN-Multihead-Attention model
deep learning
the three gorges reservoir area
environmental factors
title Research and analysis of the TCN-Multihead-Attention prediction model of landslide deformation in the Three Gorges Reservoir area, China
title_full Research and analysis of the TCN-Multihead-Attention prediction model of landslide deformation in the Three Gorges Reservoir area, China
title_fullStr Research and analysis of the TCN-Multihead-Attention prediction model of landslide deformation in the Three Gorges Reservoir area, China
title_full_unstemmed Research and analysis of the TCN-Multihead-Attention prediction model of landslide deformation in the Three Gorges Reservoir area, China
title_short Research and analysis of the TCN-Multihead-Attention prediction model of landslide deformation in the Three Gorges Reservoir area, China
title_sort research and analysis of the tcn multihead attention prediction model of landslide deformation in the three gorges reservoir area china
topic landslide deformation prediction
TCN-Multihead-Attention model
deep learning
the three gorges reservoir area
environmental factors
url https://www.frontiersin.org/articles/10.3389/feart.2025.1587623/full
work_keys_str_mv AT huanchen researchandanalysisofthetcnmultiheadattentionpredictionmodeloflandslidedeformationinthethreegorgesreservoirareachina
AT huanchen researchandanalysisofthetcnmultiheadattentionpredictionmodeloflandslidedeformationinthethreegorgesreservoirareachina
AT yixuanli researchandanalysisofthetcnmultiheadattentionpredictionmodeloflandslidedeformationinthethreegorgesreservoirareachina
AT yiminliu researchandanalysisofthetcnmultiheadattentionpredictionmodeloflandslidedeformationinthethreegorgesreservoirareachina