A novel artificial intelligence approach based on Multi-layer Perceptron Neural Network and Biogeography-based Optimization for predicting coefficient of consolidation of soil.

Abstract Coefficient of consolidation (C v) is a measure of compressibility of soil. This coefficient is an important parameter which is used in the design of foundation of civil engineering structures and also in the slope stability analysis. In this study, the main objective is to propose a hybrid machine learning approach named MLP-BBO for the prediction of the coefficient of consolidation of soft soil. This method is based on Multi-layer Perceptron Neural Network (MLP) and Biogeography-based Optimization (BBO). For this, a total number of 164 soil samples were collected from the Tan Vu–Lach Huyen highway project and Ha Noi–Hai Phong highway project sites. In the modeling, input parameters used include clay (%), moisture content (%), liquid limit (%), plastic limit (%), plasticity index (%), and liquidity index (%). To validate performance of the models, standard methods such as Root-Mean-Square Error (RMSE), Mean Absolute Error (MAE), and correlation coefficient (r) were used. For the comparison of performance of the models, popular machine learning methods were used namely Backpropagation Multi-layer Perceptron Neural Networks (Bp-MLP Neural Nets), Radial Basis Functions Neural Networks (RBF-Neural Nets), Gaussian Process (GP), M5 Tree, and Support Vector Regression (SVR). Results of the model study indicate that the proposed method MLP-BBO has the highest predictive capability (RMSE = 0.397, MAE = 0.302 and r = 0.827), followed by the SVR (RMSE = 0.403, MAE = 0.299 and r = 0.819), the Bp-MLP Neural Nets (RMSE = 0.478, MAE = 0.398 and r = 0.805), the RBF-Neural Nets (RMSE = 0.412, MAE = 0.281 and r = 0.804), the GP (RMSE = 0.440, MAE = 0.301 and r = 0.777), and the M5 Tree (RMSE = 0.494, MAE = 0.322 and r = 0.728), in the prediction of C v, respectively. Therefore, it can be concluded that though performance of all applied models is good in the prediction of the coefficient of consolidation of soil but performance of the MLP-BBO is the best. Highlights • Coefficient of consolidation (C v) is an important geotechnical factor of the soil. • Hybrid machine learning approach MLP-BBO was developed for prediction of the C v. • Machine learning named SVR, ANN, GP, and M5 Tree were selected for comparison. • Results show that the MLP-BBO is the best compared with others. [ABSTRACT FROM AUTHOR]