A REVIEW ON PREDICTION OVER PRESSURED ZONE IN HYDROCARBON WELL USING SEISMIC TRAVEL TIME THROUGH ARTIFICIAL INTELLIGENCE TECHNIQUE FOR PRE-DRILLING PLANNING

摘要

Various basins in the world comprises of areas with abnormal pore-fluid pressures (higher or lower than normal hydrostatic pressure). Undesirably, predicting pore pressure parameters (depth, extension, magnitude, etc.) in such areas are challenging tasks. The compression seismic travel time converted into sonic logs (DT) is often used as a predictor because it responds to changes in porosity or compaction produced by abnormal pore-fluid pressures. The objective of the paper is to propose a model using an artificial neural network (ANN) to synthetically create wirelinelogs (sonic logs (DT), Density logs and Resistivity Logs (RIED)) by identifying the mathematical dependency between Seismic Travel time and wireline logs of neighboring wells. A neighboring well will be used as a training well to enable the system to learn the relationship among the predictors. Once the system has trained and learnt the relationship, the model will be used to predict the next well's pore pressure position and magnitude, using only seismic travel time logs.