Publications

Determination of mud weight and drilling location are the important things to prevent drilling hazards. Pore pressure is one of the parameters that can be used to determine the mud weight and location of the drilling well. By combining the Eaton method with Neural Network, pore pressure is predicted to be more accurate. The calculation of the Eaton method is using sonic and density log to estimate the value of pore pressure, with RFT data as a calibrator and the neural network as a prediction and modeling method was using four seismic attributes as inputs to estimate the pore pressure model in another well. The inputs that we used are average frequency, seismic amplitude, acoustic impedance, and simultaneous impedance. Those four data inputs were well correlated with the pore pressure values. Moreover, we compared the result of the two cases using three out of four data inputs. The purpose of this research is to estimate the value of the pore pressure in other wells using one calibration well. After we estimate the pore pressure value, we can determinate the mud weight and determine the next location of the well to be drilled to prevent drilling hazards. The result of this research shows that Eaton can be used to estimate pore pressure and neural network shows good accuracy up to 70% compared with the actual estimation using the Eaton method in the target well. Furthermore, the result of prediction using frequency is better than using amplitude.