Full Length Research Paper

A new approach for classification of clayey soil: A case study for Adapazari region, Turkey

Fatih Goktepe¹, Hasan Arman^1,2* and Murat Pala³

¹Department of Civil Engineering, Sakarya University, 54187 Sakarya, Turkey.

²Department of Geology, United Arab Emirates University, P. O. Box 17551, Al-Ain, U.A.E.

³Department of Technical Programs, Gaziantep University, 79000 Kilis, Turkey.

*Corresponding author. E-mail: Harman@uaeu.ac.ae, hasan.arman@gmail.com. Tel: +971-3-713 4210. Fax: +971-3-767 1291.

Accepted 30 June, 2010

Abstract

Adapazari city is founded on very deep alluvial deposits which mainly consist of gravel, sand, silt, silty and clayey sands and clay. In this study, neural networks (NN) are used in the classification of clay samples existence in north of Adapazari. NN is a powerful data modeling tool capable of capturing and representing complex relationships between input and output. It has been used as alternative method in engineering analyses and estimations. In order to define general soil condition of Adapazari region, the NN model was trained and tested using liquid limit and plasticity index of clay samples obtained from drillings and laboratory works. By this developed of new NN model, the formula for Adapazari clays was found out and presented.

Key words: Adapazari clay’s, soil classification, plasticity card, neural networks, explicit formulation.