Development of an Intelligent System to Synthesize Petrophysical Well Logs

Porosity is one of the fundamental petrophysical properties that should be evaluated for hydrocarbonbearing reservoirs. It is a vital factor in precise understanding of reservoir quality in a hydrocarbonfield. Log data are exceedingly crucial information in petroleum industries, for many of hydrocarbonparameters are obtained by virtue of petrophysical data. There are three main petrophysical loggingtools for the determination of porosity, namely neutron, density, and sonic well logs. Porosity can bedetermined by the use of each of these tools; however, a precise analysis requires a complete set ofthese tools. Log sets are commonly either incomplete or unreliable for many reasons (i.e. incompletelogging, measurement errors, and loss of data owing to unsuitable data storage). To overcome thisdrawback, in this study several intelligent systems such as fuzzy logic (FL), neural network (NN), andsupport vector machine are used to predict synthesized petrophysical logs including neutron, density,and sonic. To accomplish this, the petrophysical well logs data were collected from a real reservoir inone of Iran southwest oil fields. The corresponding correlation was obtained through the comparisonof synthesized log values with real log values. The results showed that all intelligent systems werecapable of synthesizing petrophysical well logs, but SVM had better accuracy and could be used asthe most reliable method compared to the other techniques.

Keywords:

Fuzzy logic , Artificial Neural Network , Support Vector Machine , Porosity log , Mean Square Error