Estimation of effective cohesion using artificial neural networks based on index soil properties: A Singapore case

Abstract This study presents a development of a multi-layer perceptron (MLP) model to spatially estimate and analyze the variability of effective cohesion for residual soils that are commonly associated with rainfall-induced slope failures in Singapore. A number of soil data were collected from the various construction sites, and a set of qualified Nanyang Technological University (NTU) data were utilized to determine a criterion for data selection. Four index properties (i.e., percentage of fines and coarse fractions, liquid and plastic limits) were used as training parameters to estimate the effective cohesion of residual soils from different geological formations. Ordinary kriging analyses were carried out to analyze the spatial distribution and variability of effective cohesion. As a result, the appropriate effective cohesions can be estimated using the MLP model with the incorporation of the selected values of measured effective cohesion as training data and four index soil properties as input data. In the combination of estimated and measured effective cohesions, the spatial analysis using Kriging method can clearly differentiate the variations in effective cohesion with respect to the different geological formations.

[1]  H. Rahardjo,et al.  Spatial variations of air-entry value for residual soils in Singapore , 2019, CATENA.

[2]  Asaad Y. Shamseldin,et al.  Investigation of Internal Functioning of the Radial-Basis-Function Neural Network River Flow Forecasting Models , 2009 .

[3]  Jian Zhao,et al.  Division-based rainfall-runoff simulations with BP neural networks and Xinanjiang model , 2009, Neurocomputing.

[4]  Timothy C. Coburn,et al.  Geostatistics for Natural Resources Evaluation , 2000, Technometrics.

[5]  E. Leong,et al.  Effects of flux boundary conditions on pore-water pressure distribution in slope , 2013 .

[6]  Weng Tat Chan,et al.  NEURAL NETWORK: AN ALTERNATIVE TO PILE DRIVING FORMULAS , 1995 .

[7]  G. E. Blight,et al.  Mechanics of residual soils , 2012 .

[8]  Muttucumaru Sivakumar,et al.  Prediction of urban stormwater quality using artificial neural networks , 2009, Environ. Model. Softw..

[9]  D. Fredlund,et al.  Soil Mechanics for Unsaturated Soils , 1993 .

[10]  Adem Kalinli,et al.  New approaches to determine the ultimate bearing capacity of shallow foundations based on artificial neural networks and ant colony optimization , 2011 .

[11]  Yongmin Kim,et al.  Effects of hysteresis on hydro-mechanical behavior of unsaturated soil , 2018, Engineering Geology.

[12]  H. Rahardjo,et al.  A pore-size distribution function based method for estimation of hydraulic properties of sandy soils , 2018, Engineering Geology.

[13]  Xiujuan Zhang,et al.  Combined Sewer Overflow forecasting with Feed-forward Back-propagation Artificial Neural Network , 2007 .

[14]  H. Rahardjo,et al.  Effect of bimodal soil-water characteristic curve on the estimation of permeability function , 2017 .

[15]  Anthony T. C. Goh,et al.  Empirical design in geotechnics using neural networks , 1995 .

[16]  Harianto Rahardjo,et al.  Slope failures in Singapore due to rainfall , 2007 .

[17]  Saro Lee,et al.  Combining landslide susceptibility maps obtained from frequency ratio, logistic regression, and artificial neural network models using ASTER images and GIS , 2012 .

[18]  Harianto Rahardjo,et al.  Prediction of pore-water pressure using radial basis function neural network , 2012 .

[19]  Kang-Tsung Chang,et al.  Application of radar data to modeling rainfall-induced landslides , 2009 .

[20]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[21]  R. Roslee,et al.  Intergration of GIS Using GEOSTAtistical INterpolation Techniques (Kriging) (GEOSTAINT-K) in Deterministic Models for Landslide Susceptibility Analysis (LSA) at Kota Kinabalu, Sabah, Malaysia , 2012 .

[22]  H. Rahardjo,et al.  Role of unsaturated soil mechanics in geotechnical engineering , 2019, International Journal of Geo-Engineering.

[23]  R. B. Rezaur,et al.  Characteristics of residual soils in Singapore as formed by weathering , 2004 .

[24]  Harianto Rahardjo,et al.  Spatial variation of shear strength properties incorporating auxiliary variables , 2021 .

[25]  F. R. Harnas,et al.  Comprehensive Instrumentation for Real Time Monitoring of Flux Boundary Conditions in Slope , 2014 .

[26]  E. Leong,et al.  Variability of residual soil properties , 2012 .

[27]  Rui Zhao,et al.  Stress-Strain Modeling of Sands Using Artificial Neural Networks , 1995 .

[28]  N. Sivakugan,et al.  Settlement Predictions Using Neural Networks , 1998 .

[29]  H. Rahardjo,et al.  Comparison of Soil–Water Characteristic Curves from Conventional Testing and Combination of Small-Scale Centrifuge and Dew Point Methods , 2018, Geotechnical and Geological Engineering.

[30]  E. Harp,et al.  A method for producing digital probabilistic seismic landslide hazard maps , 2000 .

[31]  Gholamreza Khanlari,et al.  Prediction of shear strength parameters of soils using artificial neural networks and multivariate regression methods , 2012 .

[32]  S. Pamukcu,et al.  Characterization of Granular Material by Low Strain Dynamic Excitation and ANN , 1996 .

[33]  In Mo Lee,et al.  Prediction of pile bearing capacity using artificial neural networks , 1996 .

[34]  H. Rahardjo,et al.  Unsaturated shear strength of soil with bimodal soil-water characteristic curve , 2019, Géotechnique.

[35]  J. Parker,et al.  Analysis of the inverse problem for transient unsaturated flow , 1988 .

[36]  Yudong Cal,et al.  Soil classification by neural network , 1995 .

[37]  Holger R. Maier,et al.  ARTIFICIAL NEURAL NETWORK APPLICATIONS IN GEOTECHNICAL ENGINEERING , 2001 .

[38]  Aman Jantan,et al.  State-of-the-art in artificial neural network applications: A survey , 2018, Heliyon.

[39]  C. H. Juang,et al.  A fuzzy neural network approach to evaluation of slope failure potential , 1996 .

[40]  H. Rahardjo,et al.  Three-dimensional slope stability analysis incorporating unsaturated soil properties in Singapore , 2020 .

[41]  E. Leong,et al.  Effects of Rainfall Characteristics on the Stability of Tropical Residual Soil Slope , 2016 .

[42]  H. Rahardjo,et al.  Estimation of unimodal water characteristic curve for gap-graded soil , 2017 .