The e ective stress parameter () is applied to obtain the shear strength of unsaturated soils. In this study, two Adaptive Neuro-Fuzzy Inference System (ANFIS) models, including SC-FIS model (created by subtractive clustering) and FCM-FIS model (created by Fuzzy c-means (FCM) clustering), are presented for prediction of , and the results are compared. The soil-water characteristic curve tting parameter (), the con ning pressure, the suction, and the volumetric water content in dimensionless forms are used as input parameters for these two models. By using a trial-and-error process, a series of analyses were performed to determine the optimum methods. The ANFIS models were constructed, trained, and validated to predict the value of . The quality of the ANFIS prediction ability was quanti ed in terms of the determination coe cient (R 2 ), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). These two ANFIS models are able to e ectively predict the value of with reasonable values of R 2 , RMSE, and MAE. Sensitivity analysis was implemented to determine the e ect of input parameters on prediction, and the results revealed that the con ning pressure and the volumetric water content parameters had the most in uence on prediction.
A B S T R A C TIn this paper, using synthetic and real data, we tested the capability of surface wavebased methods for detecting subsoil lateral variations across an inclined slope. Simplified soil structures at different inclination angles were considered following an advanced 2D finite-element modelling approach. Different values of inclination angle (10°-170°at 10°steps), spatial sampling rate and synthetic array length were used in different subsoil models to see the effects. It was found that, as low inclination angles (smaller than 40°with respect to the horizontal axis) are not detectable using the surface wave methods based on offset-phase angle (X-φ), such methods are not able to correctly recognize the location of possible lateral variations at such inclination angles. On the other hand, for intermediate inclination angles (i.e. between 40°and 140°), the X-φ approach was successfully used to determine the exact location of the lateral variations for a wide range of frequencies, thereby opening new perspectives for the application of surface waves for detecting laterally inclined layers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.