A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Prediction of Liquified Soil Settlement Based on Artificial Neural Network
Severe seismic movements caused certain special types of soil, such as loose sands or poorly gravelly soil, to liquefaction, which is referred to as soil liquefaction and led to ground settlements. Over the past few decades, laboratory or in-situ testing approaches have mainly been applied to investigate these settlements. The aim of this study was to use an artificial neural network (ANN) to predict ground settlement due to the Pohang earthquake. An ANN algorithm was implemented to the soil dataset for this purpose. Various variables of soil characteristics were considered as input parameters namely unit weight, soil layer depth, standard penetration test blow counts, and cyclic stress ratio. Furthermore, different prediction errors of mean average error (MAE), mean squared error (MSE), root mean squared error (RMSE) and the coefficient of determination or R-squared were employed in this study to evaluate the model performance. The testing results revealed that the difference between the original and predicted values using MAE, MSE, and RMSE was 0.209, 0.106 and 0.325, respectively. Besides, the R-squared value of 0.868 was achieved by predicted results and actual values of ground settlements. It concluded the feasibility of the proposed ANN model with the high R-squared value for predicting liquefaction-induced settlements.
Prediction of Liquified Soil Settlement Based on Artificial Neural Network
Severe seismic movements caused certain special types of soil, such as loose sands or poorly gravelly soil, to liquefaction, which is referred to as soil liquefaction and led to ground settlements. Over the past few decades, laboratory or in-situ testing approaches have mainly been applied to investigate these settlements. The aim of this study was to use an artificial neural network (ANN) to predict ground settlement due to the Pohang earthquake. An ANN algorithm was implemented to the soil dataset for this purpose. Various variables of soil characteristics were considered as input parameters namely unit weight, soil layer depth, standard penetration test blow counts, and cyclic stress ratio. Furthermore, different prediction errors of mean average error (MAE), mean squared error (MSE), root mean squared error (RMSE) and the coefficient of determination or R-squared were employed in this study to evaluate the model performance. The testing results revealed that the difference between the original and predicted values using MAE, MSE, and RMSE was 0.209, 0.106 and 0.325, respectively. Besides, the R-squared value of 0.868 was achieved by predicted results and actual values of ground settlements. It concluded the feasibility of the proposed ANN model with the high R-squared value for predicting liquefaction-induced settlements.
Prediction of Liquified Soil Settlement Based on Artificial Neural Network
Lecture Notes in Civil Engineering
Reddy, J. N. (editor) / Wang, Chien Ming (editor) / Luong, Van Hai (editor) / Le, Anh Tuan (editor) / Nguyen, Tan-No (author) / Tran, Luc V. (author) / Cuong, Phan Viet (author) / Tran, Thanh Danh (author)
The International Conference on Sustainable Civil Engineering and Architecture ; 2023 ; Da Nang City, Vietnam
Proceedings of the Third International Conference on Sustainable Civil Engineering and Architecture ; Chapter: 128 ; 1208-1214
2023-12-12
7 pages
Article/Chapter (Book)
Electronic Resource
English
Pile Behaviour in Liquified Soil
| British Library Conference Proceedings | 1995
Prediction of Settlement of Shallow Foundation on Cohesionless Soil Using Artificial Neural Network
| Springer Verlag | 2022
Prediction of Liquefaction-Induced Settlement Using Artificial Neural Network
| Springer Verlag | 2024