A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Spatiotemporal pore-water pressure prediction using multi-input long short-term memory
Abstract The increase in pore-water pressure (PWP) in slopes due to extreme rainfall is one of the major triggering factors for landslides. In recent years, machine learning (ML) techniques have been proposed to predict PWP response under heavy rainfall for slope stability analysis. However, most of these methods neglect the spatiotemporal nature of the problem by treating the PWP dataset as a univariate time-series problem. As such, the trained model remains valid for the given sensor and fails to predict the response when used for other locations. In this paper, a novel multivariate long short-term memory (M-LSTM) is proposed to predict the PWP response by simultaneously using the spatial and temporal PWP data from multiple measurement locations. The choice of optimal measurement locations for model training is made using the principal component analysis (PCA) and silhouette value analysis. The performance of the proposed model is evaluated using five different performance indicators named (i) mean absolute error (MAE), (ii) mean square error (MSE), (iii) root mean square error (RMSE), (iv) coefficient of determination (R2), and (v) Pearson correlation coefficient (PCC). The results obtained with M-LSTM are compared with the predictions from the univariate LSTM algorithm. The comparison shows that the univariate LSTM model is only valid for the location used for training and cannot be applied to other locations, implying the loss of generality of the model. In contrast, the proposed M-LSTM is not hamstrung by the foregoing issue and accurately predicts the PWP response for non-training sensor locations, which can also incorporate the spatial and temporal variation within the data.
Highlights A variant of LSTM (i.e., MI-LSTM) was applied to predict the PWP of a field site. The model can consider multi-inputs, outputs and the spatiotemporal nature of data. PCA analysis is performed to make clusters and find the optimal input for training. Influences of cluster numbers are investigated by using silhouette analysis.
Spatiotemporal pore-water pressure prediction using multi-input long short-term memory
Abstract The increase in pore-water pressure (PWP) in slopes due to extreme rainfall is one of the major triggering factors for landslides. In recent years, machine learning (ML) techniques have been proposed to predict PWP response under heavy rainfall for slope stability analysis. However, most of these methods neglect the spatiotemporal nature of the problem by treating the PWP dataset as a univariate time-series problem. As such, the trained model remains valid for the given sensor and fails to predict the response when used for other locations. In this paper, a novel multivariate long short-term memory (M-LSTM) is proposed to predict the PWP response by simultaneously using the spatial and temporal PWP data from multiple measurement locations. The choice of optimal measurement locations for model training is made using the principal component analysis (PCA) and silhouette value analysis. The performance of the proposed model is evaluated using five different performance indicators named (i) mean absolute error (MAE), (ii) mean square error (MSE), (iii) root mean square error (RMSE), (iv) coefficient of determination (R2), and (v) Pearson correlation coefficient (PCC). The results obtained with M-LSTM are compared with the predictions from the univariate LSTM algorithm. The comparison shows that the univariate LSTM model is only valid for the location used for training and cannot be applied to other locations, implying the loss of generality of the model. In contrast, the proposed M-LSTM is not hamstrung by the foregoing issue and accurately predicts the PWP response for non-training sensor locations, which can also incorporate the spatial and temporal variation within the data.
Highlights A variant of LSTM (i.e., MI-LSTM) was applied to predict the PWP of a field site. The model can consider multi-inputs, outputs and the spatiotemporal nature of data. PCA analysis is performed to make clusters and find the optimal input for training. Influences of cluster numbers are investigated by using silhouette analysis.
Spatiotemporal pore-water pressure prediction using multi-input long short-term memory
Ng, Charles Wang Wai (author) / Usman, Muhammad (author) / Guo, Haowen (author)
Engineering Geology ; 322
2023-05-24
Article (Journal)
Electronic Resource
English
Water Level Forecasting Using Spatiotemporal Attention-Based Long Short-Term Memory Network
| DOAJ | 2022
Prediction of long-term settlement and evaluation of pore water pressure using particle filter
| British Library Online Contents | 2019
Prediction of long-term settlement and evaluation of pore water pressure using particle filter
| British Library Online Contents | 2019