Prediction of Reservoir Properties by Monte Carlo Simulation and Artificial Neural Network in the Exploration Stage
Monte Carlo Simulation and Artificial Neural Network are applied to two areas for predicting the distribution of reservoirs. One is the Pantai Pakam Timur field, located in Northern Sumatra, Indonesia, where the data from only two wells were available and the other is Iwafune Oki field, located in the Sea of Japan, Eastern Japan, where wells were concentrated in the central part of the field. Although 2-D and 3-D seismic exploration was executed in the two areas, respectively, the distributions of reservoir thickness and quality remain unclear. It is of great help to predict the distribution of reservoirs in the regions because the prediction can help to improve the accuracy for exploration and to save the cost in the following exploration stage. However, the method of geostatistics is hardly applied to the regions where there are a few wells drilled. There is a new suitable technique, named as Geology Driven Integration Tool (GDI), to estimate reservoir properties under the condition of such a few wells. In GDI, many pseudo-wells are created by Monte Carlo Simulation, based on the factual well data and regional geological constraints to compensate the condition of a few wells. Furthermore, synthetic seismograms are generated from them. The suitable seismic attributes and the given reservoir properties are selected and input to the Artificial Neural Network (ANN) to detect the weighting factors, which relate the selected seismic attributes to the given reservoir properties. Finally, the trained ANN is applied to entire seismic record to estimate the distribution of reservoir properties in a region. The southern part of Pantai Pakam Timur field and the northern part of Iwafune Oki field are proposed as prospect areas according to the estimated results, besides the areas already developed. The net thickness of gas zone is estimated to increase to 27 meters with higher porosity of 27% in the southern part of Pantai Pakam Timur field. Reservoir of 15–25 meter thickness with the porosity of 20–25% is expected to distribute in the northern part of Iwafune Oki field.
KeywordsMonte Carlo Simulation Artificial Neural Network Seismic Response Seismic Record Synthetic Seismogram
Unable to display preview. Download preview PDF.
- 2.H. Miyazaki, T. Kude, F. Akiba, H. Fukasawa and K. Asano, 1987, Geology of Iwafune-oki Field — A Preliminary Study of the Distribution of the Sandstone Reservoirs, JAPT, vol.52, no.2, p.35–49. (in Japanese)Google Scholar
- 3.Pertamina Operasi EP Rantau, 1996, Provisional Report Seismic Study and Reservoir Distribution of Pantai Pakam Timur Area.Google Scholar
- 4.Rumelhart, D.E., Hinton, G.E. and Williams, R.J., 1986, Learning internal representations by error propagation, Parallel Distributed Processing, Editors:Rumelhart, D.E., McClelland, T.T. and the PDP Research group, Cambridge, Massachusetts, MIT Press, p.318–362.Google Scholar
- 5.Shultz, P.S., Ronen, S., Hattori, M. and Corbett, C., 1994a, Seismic-guided estimation of log properties Part 1: A data-driven interpretation methodology, The Leading Edge, May 1994, p.305–315.Google Scholar
- 6.Ronen, S., Shultz, P.S., Hattori, M. and Corbett, C., 1994, Seismic-guided estimation of log properties Part 2: Using artificial neural networks for nonlinear attribute calibration, The Leading Edge, June 1994, p.674–678.Google Scholar
- 7.Shultz, P.S., Ronen, S., Hattori, M., Mantran, P. and Corbett, C., 1994b, Seismicguided estimation of log properties Part 3: A controlled study, The Leading Edge, July 1994, p.770–776.Google Scholar
- 8.Stephen, J.J., 1990, Neural Network Design and the Complexity of Learning, MIT Press, Cambridge, Massachusetts, 150pp.Google Scholar