Time Series Prediction of Pore Water Pressure on Earth Dam Slopes Based on Recurrent Neural Network

DOI

10.2991/978-94-6463-449-5_66How to use a DOI?

Keywords

Slop; Recurrent neural network; Pore-water pressure; Long short-term memory; Gated recurrent unit; Bidirectional recurrent neural network

Abstract

Landslides are common geologic hazards in engineering, often causing serious destructive consequences. The study of pore water pressure distribution on slopes has a positive effect on mitigating the hazards of landslides, but due to the limitations of the complex physical mechanisms in engineering practice, the variability of natural space, etc., which leads to the existing theoretical studies can not completely reflect the law of pore water pressure, many scholars began to use machine learning methods applied to the prediction of pore water pressure. This paper mainly uses the recurrent neural network and its three variants to predict the pore water pressure monitored in the actual project, and compares the performance of the four models. The study shows that the four models have good performance, in which the integrated training time and training effect of Gated recurrent unit model is relatively better, while the adjustment of parameters can effectively improve the training effect of the model as well as the training time.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Lin Wang
AU  - Junrui Chai
PY  - 2024
DA  - 2024/06/30
TI  - Time Series Prediction of Pore Water Pressure on Earth Dam Slopes Based on Recurrent Neural Network
BT  - Proceedings of the 2024 8th International Conference on Civil Architecture and Structural Engineering (ICCASE 2024)
PB  - Atlantis Press
SP  - 675
EP  - 686
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-449-5_66
DO  - 10.2991/978-94-6463-449-5_66
ID  - Wang2024
ER  -