Subject:
Geology

 

Number Of Pages:
70     Single-spaced (31500 words)

 

Number Of Sources:
50

 

Type of Document:
Thesis

 

Academic Level:
Master

 

Citation Style:
Harvard

 

Attachment(s):
N/A

 

Solution Files(s):
N/A

 

Description:

 

The objective of this study is to employ the novel technique of Artificial Neural Networks(ANN) to estimate the grades of the manganese deposit at Egyaso Mine. ANN has a couple of advantages compared with geostatistical methods. Firstly, the artificial neural network method is independent of the statistical distribution of the data and there is no need for specific statistical variables. Neural networks also allow the target classes to be defined with much consideration to their distribution in the corresponding domain of each data source. In the ANN, spatial ore variability is captured through the nonlinear input–output mapping via a set of connection weights. Neural networks appear to work like a parametric nonlinear global fitting model. Hence, ANN is expected to provide improved performance in the presence of a nonlinear spatial trend in the data variability. Artificial neural networks have performed well in grade estimation due to its ability to synthesize complex and nonlinear problems. Neural networks have been widely used for estimating grades or metal contents as found in the works of Wu and Zhou (1993), Samanta, Ganguli and Bandopadhyay (2005).

Place New Order
It's Free, Fast & Safe

"Looking for a Similar Assignment? Order now and Get a Discount!