The main goal of this paper is to identify lithologies from well-logs data using the continuous wavelet transform CWT combined with the self organizing map (SOM), we based at the fractional Brownian motion character of well-logs data we estimate the Holder exponent at each depth. The set of Holder exponents calculated for all well-logs data represents the input of the neural machine. Our system gives at each entry a specified lithology. We applied this technique at synthetics and real well-logs data, obtained results showed that the proposed technique is a powerful tool for reservoir characterization, witch is a crucial problem in geophysics. Because it attribute at each set of roughness coefficients (witch are directly related to the rocks types ) a particular lithology. Keywords: Lithologies , well-logs data , the CWT , the Self Organizing Map SOM , Holder exponent , roughness coefficients.


Article metrics loading...

Loading full text...

Full text loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error