Publications

Melibur field is a mature oil field in Indonesia, discovered in 1984. The field has been producing oil for 25 years. Peak production of 15 Mbopd was recorded in 1987. Cumulative oil recovery is 44 MMstb. Current production is 3 Mbopd with 90% water cut from 62 wells. Our production enhancement team faces challenge of high water-cuts and limited drill-site availability due to population encroachment. This paper describes a method to rank potential infill well locations using Artificial Neural Networks (ANN) with a 44-well data-set. 80% of wells were used for training and the rest was for testing. Two ANN models have been built. The first model predicted top sand depth, resistivity, gamma-ray and density-neutron from infill well location (chosen from structural position and good oil rates from offset wells). The second model predicted initial oil rate from outputs from the first model. Predicted initial oil rates from the ANN model were compared with those from the 3D reservoir simulation model. Similar oil rates have given high confidence in the predicted oil rate. Very different oil rates triggered us to revisit the simulation model, both the static model and the history-match. The ANN model predictions have increased confidence in our investment decision to drill infill wells. The wells will be drilled in 2013.