Urban Geo-Informatics (Invited ATC10 Lectures)
doi:10.3850/978-981-07-0188-8_P166
Spatial Interpolation of Soil Properties in North Area of Osaka Bay through Artificial Neural Network
Kazuhiro Oda
Department of Civil Engineering, Osaka University,
2-1 Yamada-oka Suita, Osaka, Japan
ABSTRACT
The spatial interpolation of geotechnical information is one of the most representative applications of geo-informatics database. It is necessary to estimate the soil properties at arbitrary position in underground from soil investigations. In this study, an artificial neural network was applied to estimate the soil properties, such as natural water content, liquid limit, unconfined compression strength and one-dimensional compression curve. The architecture of artificial neural network was discussed from the viewpoints of accuracy of estimation to soil properties. Also, the spatial interpolation of soil properties was carried out through the artificial neural network chosen as the optimum one. Consequently, the availability of artificial neural network to the special interpolation of soil properties is confirmed.
Back to TOC
FULL TEXT(PDF)
|