Author : Mostafa Behdin, Nasser Keshavarz Farajkhah and Asghar Naderi

This paper aimed to determine the optimum drilling area for petroleum exploration based on adaptive neuro fuzzy inference system has been performed. Drilling in petroleum exploration is costly and time consuming and has many problems. Therefore, the determination of drilling points in detailed exploration of petroleum reserves, which takes into account all the complex conditions governing the formation of petroleum reserves and the integration of factors such as source rocks, reservoir rocks, and petroleum traps are of great importance. Therefore, any mistake in determining the location of the excavation is very costly and time-consuming. Therefore, the present study aimed at identifying an optimal drilling area in petroleum exploration using an adaptive neural fuzzy inference system that seeks to reduce the time and cost of exploration. In this regard, the maps were developed using GIS functions. To model maps, this study used adaptive neuro-fuzzy inference system (ANFIS) methods to construct a reliable tool to predict the reservoir properties namely: oil rate, gas rate, cumulative oil, cumulative gas and gas oil ratio that lies within the reservoir and design properties for this study. The proposed approach was tested on an Iranian oil field to determine the potential areas more accurately using well log data. The predicted reservoir properties match the ones generated with an average error as follow; oil rate 13.25%, gas rate 4.32, cumulative oil 11.47%, cumulative gas 8.01%, gas oil ratio 5.41%. Experimental results show that our proposed method can be used to predict any other reservoir parameters using well logs data. So the ANFIS method with R and RSME (0.7651, 0.0298) can predicts optimum drilling area for petroleum exploration accurately.

Keywords: Optimum drilling area, petroleum exploration, adaptive neuro fuzzy inference system

Article published in International Journal of Current Engineering and Technology, Vol.7, No.6 (Nov/Dec 2017)