Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Aceh International Journal of Science and Technology

Overpressure-generating mechanisms in the Blok F3, North Sea, Netherland Khusmia Karin; . Sudarmaji
Aceh International Journal of Science and Technology Vol 10, No 2 (2021): August 2021
Publisher : Graduate Program of Syiah Kuala University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2469.743 KB) | DOI: 10.13170/aijst.10.2.21193

Abstract

Block F3 North Sea is a block with pore pressure values that vary over time due to complex geological conditions such as burial and various sedimentation zones. Pore pressure is one of the important aspects that need to be analyzed as a basis for the identification of zones and overpressure mechanisms. Overpressure is a greater pore pressure condition than normal pressure and may cause drilling problems, such as kicks, blowouts, etc. This study calculated pore pressure values using the eaton method approach with well data and seismic data. Both data are integrated for generating pore pressure values in 1D and 3D. 1D Modelling uses Interactive Petrophysics 3.5, while 3D modeling uses Petrel software. In 3D modeling, the variables used are interval velocity and inversion velocity obtained by acoustic impedance inversion. The sub-variables used are the inversion density and the regression density obtained from well density acoustic impedance inversion. The existence of a 1D overpressure zone at a depth of 1,100 – 1,800 m with an overpressure value of 3,836 – 18,975 kPa. In addition, the overpressure value based on the 3D model is 8,000 – 18,000 kPa. The overpressure zone is validated using an acoustic impedance inversion model with a high value of 5,200 – 5,380 (m/s)*(gr/cc). Overpressure in Block F3 is predicted to occur from disequilibrium compaction..
The Implementation of Machine Learning in Lithofacies Classification using Multi Well Logs Data Sudarmaji Saroji; Ekrar Winata; Putra Pratama Wahyu Hidayat; Suryo Prakoso; Firman Herdiansyah
Aceh International Journal of Science and Technology Vol 10, No 1 (2021): April 2021
Publisher : Graduate Program of Syiah Kuala University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1057.537 KB) | DOI: 10.13170/aijst.10.1.18749

Abstract

Lithofacies classification is a process to identify rock lithology by indirect measurements. Usually, the classification is processed manually by an experienced geoscientist. This research presents an automated lithofacies classification using a machine learning method to increase computational power in shortening the lithofacies classification process's time consumption. The support vector machine (SVM) algorithm has been applied successfully to the Damar field, Indonesia. The machine learning input is various well-log data sets, e.g., gamma-ray, density, resistivity, neutron porosity, and effective porosity. Machine learning can classify seven lithofacies and depositional environments, including channel, bar sand, beach sand, carbonate, volcanic, and shale. The classification accuracy in the verification phase with trained lithofacies class data reached more than 90%, while the accuracy in the validation phase with beyond trained data reached 65%. The classified lithofacies then can be used as the input for describing lateral and vertical rock distribution patterns.