Development of Neural Network Model to Estimate the Permeability Coefficient of Soils
Author:
- 29 June 2011
- journal article
- research article
- Published by Taylor & Francis in Marine Georesources & Geotechnology
- Vol. 29 (4) , 267-278
Abstract
The permeability coefficient is a one of the important soil parameters that is essential to geotechnical designs. As the determination of the permeability coefficient from field tests is relatively time-consuming, empirical formulas based on soil parameters can be useful. Over the decades, a number of empirical formulas have been proposed to relate the compressibility to other soil parameters, such as the natural water content, grain size, specific gravity, and others. In this study, an artificial neural network (ANN) model is proposed to estimate the permeability coefficient with various permeability test sets. The permeability coefficient was modeled as a function of six variables including the natural water content, specific gravity, and grain sizes. 379 in-situ permeability tests performed at 21 construction sites in Korea were used for the training and testing of the ANN model. It was found that the permeability coefficient could be reasonably estimated using developed neural network model.Keywords
This publication has 15 references indexed in Scilit:
- ANN-based model for predicting the bearing capacity of strip footing on multi-layered cohesive soilComputers and Geotechnics, 2009
- Predicting the saturated hydraulic conductivity of sand and gravel using effective diameter and void ratioCanadian Geotechnical Journal, 2004
- Goodbye, Hazen; Hello, Kozeny-CarmanJournal of Geotechnical and Geoenvironmental Engineering, 2003
- Neural Networks for Profiling Stress History of Clays from PCPT DataJournal of Geotechnical and Geoenvironmental Engineering, 2002
- Identification of Solid Materials by Correlation Analysis Using a Microscopic Laser-Induced Plasma SpectrometerAnalytical Chemistry, 1999
- Prediction of pile bearing capacity using artificial neural networksComputers and Geotechnics, 1996
- Estimation of lateral wall movements in braced excavations using neural networksCanadian Geotechnical Journal, 1995
- Influence of fines on the collapse of loose sandsCanadian Geotechnical Journal, 1994
- Training feedforward networks with the Marquardt algorithmIEEE Transactions on Neural Networks, 1994
- Permeability of compacted granular materialsCanadian Geotechnical Journal, 1984