Pore pressure prediction using eaton and neural network method in carbonate field "x" based on seismic data

P. S. Hutomo, M. S. Rosid, M. W. Haidar

Research output: Contribution to journalConference articlepeer-review

8 Citations (Scopus)


Abnormal pore pressure can cause some problems during the drilling process such as a blowout or sticking pipe while drilling. Pore pressure prediction may prevent the drilling hazard, especially in carbonate field that known as a complex reservoir. It is useful for mud weight determination to prevent blowout and sticking pipe while drilling. This study focuses on predicting pore pressure values and maps it through 3D seismic data. The field is carbonate reservoir which known as a heterogeneous formation with shale above the reservoir. Due to the difference of lithologies, the two different empirical parameter is used in each lithology for Eaton equation. The pore pressure prediction then correlates with the seismic attribute using a neural network method. The input parameter of the Eaton is sonic and density log. Then, the result of Eaton's method is calibrated by leak-off test (LOT) and repeat formation test (RFT), hence the results are more accurate and verified. Then, the pore pressure is correlated to acoustic impedance, shear impedance, seismic frequency, and seismic amplitude to create a subsurface model by the neural network machine learning. The result shows that the pore pressure prediction of the model is verified by the measured pore pressure well-log data with good accuracy up to 90%. The combination method of Eaton and neural network was proven to be able to predict and map pore pressure distribution in a complex carbonate field.

Original languageEnglish
Article number032017
JournalIOP Conference Series: Materials Science and Engineering
Issue number3
Publication statusPublished - 1 Jul 2019
Event9th Annual Basic Science International Conference 2019, BaSIC 2019 - Malang, Indonesia
Duration: 20 Mar 201921 Mar 2019


Dive into the research topics of 'Pore pressure prediction using eaton and neural network method in carbonate field "x" based on seismic data'. Together they form a unique fingerprint.

Cite this