Generative probabilistic prediction of precipitation induced landslide deformation with variational autoencoder and gated recurrent unit

被引:6
|
作者
Cai, Wencheng [1 ]
Lan, Fuan [1 ]
Huang, Xianhao [2 ]
Hao, Junfeng [2 ]
Xia, Weifeng [2 ]
Tang, Ran [3 ]
Feng, Peng [3 ]
Li, Huajin [3 ]
机构
[1] Sichuan Lexi Expressway Co Ltd, Chengdu, Sichuan, Peoples R China
[2] Sichuan Intelligent Expressway Technol Co Ltd, Chengdu, Sichuan, Peoples R China
[3] Chengdu Univ, Sch Architecture & Civil Engn, Chengdu, Sichuan, Peoples R China
关键词
landslide deformation; probabilistic prediction; gated recurrent unit; VAE-GRU; variational autoencoder; NETWORK;
D O I
10.3389/feart.2024.1394129
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
Landslides, prevalent in mountainous areas, are typically triggered by tectonic movements, climatic changes, and human activities. They pose catastrophic risks, especially when occurring near settlements and infrastructure. Therefore, detecting, monitoring, and predicting landslide deformations is essential for geo-risk mitigation. The mainstream of the previous studies have often focused on deterministic models for immediate landslide prediction. However, in most of them, the aspect of prediction uncertainties are not sufficiently addressed. This paper introduces an innovative probabilistic prediction method using a Variational Autoencoder (VAE) combined with Gated Recurrent Unit (GRU) to forecast landslide deformations from a generative standpoint. Our approach consists of two main elements: firstly, training the VAE-GRU model to maximize the variational lower bound on the likelihood of historical precipitation data; secondly, using the learned approximated posterior distribution to predict imminent deformations from a generative angle. To assess the prediction quality, we use four widely-used metrics: Prediction Interval Coverage Probability (PICP), Prediction Interval Normalized Average Width (PINAW), Coverage Width-Based Criterion (CWC), and Prediction Interval Normalized Root Mean Square Width (PINRW). The results demonstrate that our proposed VAE-GRU framework surpasses traditional state-of-the-art (SOTA) probabilistic deformation prediction algorithms in terms of accuracy and reliability.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] A Generative Adversarial Gated Recurrent Unit Model for Precipitation Nowcasting
    Tian, Lin
    Li, Xutao
    Ye, Yunming
    Xie, Pengfei
    Li, Yan
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2020, 17 (04) : 601 - 605
  • [2] Generative Probabilistic Wind Speed Forecasting: A Variational Recurrent Autoencoder Based Method
    Zheng, Zhong
    Wang, Long
    Yang, Luoxiao
    Zhang, Zijun
    IEEE TRANSACTIONS ON POWER SYSTEMS, 2022, 37 (02) : 1386 - 1398
  • [3] An Autoencoder Gated Recurrent Unit for Remaining Useful Life Prediction
    Lu, Yi-Wei
    Hsu, Chia-Yu
    Huang, Kuang-Chieh
    PROCESSES, 2020, 8 (09)
  • [4] Displacement prediction of Jiuxianping landslide using gated recurrent unit (GRU) networks
    Wengang Zhang
    Hongrui Li
    Libin Tang
    Xin Gu
    Luqi Wang
    Lin Wang
    Acta Geotechnica, 2022, 17 : 1367 - 1382
  • [5] Displacement prediction of Jiuxianping landslide using gated recurrent unit (GRU) networks
    Zhang, Wengang
    Li, Hongrui
    Tang, Libin
    Gu, Xin
    Wang, Luqi
    Wang, Lin
    ACTA GEOTECHNICA, 2022, 17 (04) : 1367 - 1382
  • [6] Landslide Displacement Prediction With Gated Recurrent Unit and Spatial-Temporal Correlation
    Ma, Wenli
    Dong, Jianhui
    Wei, Zhanxi
    Peng, Liang
    Wu, Qihong
    Chen, Chunxia
    Wu, Yuanzao
    Xie, Feihong
    FRONTIERS IN EARTH SCIENCE, 2022, 10
  • [7] Electrocardiogram prediction based on variational mode decomposition and a convolutional gated recurrent unit
    HongBo Wang
    YiZhe Wang
    Yu Liu
    YueJuan Yao
    EURASIP Journal on Advances in Signal Processing, 2024
  • [8] Electrocardiogram prediction based on variational mode decomposition and a convolutional gated recurrent unit
    Wang, HongBo
    Wang, YiZhe
    Liu, Yu
    Yao, YueJuan
    EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2024, 2024 (01)
  • [9] Improved Landslide Deformation Prediction Using Convolutional Neural Network-Gated Recurrent Unit and Spatial-Temporal Data
    Yang, Honglei
    Liu, Youfeng
    Han, Qing
    Xu, Linlin
    Zhang, Tengjun
    Wang, Zeping
    Yan, Ao
    Zhao, Songxue
    Han, Jianfeng
    Wang, Yuedong
    REMOTE SENSING, 2025, 17 (04)
  • [10] Reservoir Production Prediction Based on Variational Mode Decomposition and Gated Recurrent Unit Networks
    Wang, Fuhao
    Zhang, Dongmei
    Min, Geyong
    Li, Jianxin
    IEEE ACCESS, 2021, 9 : 53317 - 53325