Selective ensemble deep bidirectional RVFLN for landslide displacement prediction

Landslide displacement prediction is a challenging and important subject in landslide research. To improve the prediction accuracy of and reduce disasters caused by landslides, we propose a selective ensemble deep bidirectional Random Vector Functional Link Network (sedb-RVFLN) for landslide displac...

Full description

Saved in:
Bibliographic Details
Published inNatural hazards (Dordrecht) Vol. 112; no. 1; pp. 725 - 745
Main Authors Yu, Xiaoyang, Lian, Cheng, Su, Yixin, Xu, Bingrong, Wang, Xiaoping, Yao, Wei, Tang, Huiming
Format Journal Article
LanguageEnglish
Published Dordrecht Springer Netherlands 01.05.2022
Springer Nature B.V
Subjects
Accuracy
Algorithms
Automation
Civil Engineering
Deep learning
Deformation
Disasters
Displacement
Earth and Environmental Science
Earth Sciences
Earthquakes
Environmental Management
Geophysics/Geodesy
Geotechnical Engineering & Applied Earth Sciences
Hydroelectric power
Hydroelectric power stations
Hydrogeology
Landslides
Landslides & mudslides
Machine learning
Natural Hazards
Neural networks
Nodes
Original Paper
Predictions
Support vector machines
Training
Incremental learning
Landslide displacement prediction
Selective ensemble
Random Vector Functional Link Network
Online AccessGet full text

Cover

More Information
Summary:Landslide displacement prediction is a challenging and important subject in landslide research. To improve the prediction accuracy of and reduce disasters caused by landslides, we propose a selective ensemble deep bidirectional Random Vector Functional Link Network (sedb-RVFLN) for landslide displacement prediction in which each independent hidden layer is linked to a different output layer. In this paper, to reduce the number of hidden nodes without affecting the efficiency of network training, an incremental learning method is utilized to make some hidden nodes not randomly chosen. Moreover, we apply selected partial hidden layers instead of all hidden layers to construct a selective ensemble. The ensemble method adopted by sedb-RVFLN does not require training multiple independent networks, and the entire sedb-RVFLN only needs to be trained once. Finally, we conduct extensive experiments on real landslide datasets from the Huangdeng Hydropower Station in China to demonstrate the effectiveness of our model.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0921-030X
1573-0840
DOI:10.1007/s11069-021-05202-w