The applicability of neural networks in the determination of soil profiles

Naci Caglar, Hasan Arman

Research output: Contribution to journalArticlepeer-review

24 Citations (Scopus)

Abstract

The drilling of a number of boreholes to determine the soil profile of a given area is time consuming and costly. This paper describes estimated soil profiles obtained using a model based on artificial neural networks (ANN). ANN is a powerful data-modelling tool capable of capturing and representing complex relationships between input and output. It deals with many multi-variate problems for which an exact analytical model does not exist or is very difficult and time consuming to develop. The main settlement in the Adapazari region was selected to demonstrate the capability of such model. The results obtained using ANN are promising when compared with the soil profile obtained from boreholes.

Original languageEnglish
Pages (from-to)295-301
Number of pages7
JournalBulletin of Engineering Geology and the Environment
Volume66
Issue number3
DOIs
Publication statusPublished - Aug 2007
Externally publishedYes

Keywords

  • Artificial neural network
  • Back-propagation
  • Borehole data
  • Soil profiling

ASJC Scopus subject areas

  • Geotechnical Engineering and Engineering Geology
  • Geology

Fingerprint

Dive into the research topics of 'The applicability of neural networks in the determination of soil profiles'. Together they form a unique fingerprint.

Cite this