University of Khartoum

Prediction of Blue Nile Soil Profile in Khartoum State Using Artificial Neural Network

Prediction of Blue Nile Soil Profile in Khartoum State Using Artificial Neural Network

Show full item record

Title: Prediction of Blue Nile Soil Profile in Khartoum State Using Artificial Neural Network
Author: El Hassan, Mutwakil Ali M.
Abstract: This thesis deals with the potential application of neural network technology to build up and to investigate a powerful network capable to classify and predict some soil properties at the blue Nile area in Khartoum state based on previous investigated site conditions, Also the effect of Artificial neural network ANN geometry and some internal parameters (learning rate and momentum) on the performance of ANN models is studied. A large database (data of 55 sites) of actual available site investigation data is used to develop and verify the ANN model. About 38% of the total database (21 sites) is used as input data to construct seventeen ANN models using Neuroshell2 program. A data of new34 sites were predicted by the models. The results indicate the neural network is a useful technique and have an ability to make relationships between the input parameters (the three dimensional coordinates) and the output parameters (soil classification and its l properties) with an acceptable degree of accuracy.
Description: 1131page
URI: http://khartoumspace.uofk.edu/handle/123456789/10839
Date: 2015-05-14


Files in this item

Files Size Format View

This item appears in the following Collection(s)

Show full item record

Share

Search DSpace


Browse

My Account