6TH International Congress on Technology - Engineering - Kuala Lumpur3 - Malaysia (2018-07-19)

Fracture Network Based On Principal Component Analysis And Neural Network– A Case Study In The Malay Basin

Finding oil in the fractured basement rock in South East Asia has been a goal for several decades, but remains a challenge in terms of exploration/production areas in the Malay Basin due to geological complexity, including rock properties and tectonics in understanding fracture characterisation. In principle the fracture scale was divided into megascopic, macroscopic, mesoscopic and microscopic. However, it is still difficult to understand the fracture in terms of scale as they are in the form of the fracture system. Thus, the purpose of this study is to delineate fracture network based on the geometrical attributes in order to have better fracture understanding. The analysis starts with the analysis of the top of the basement as the key surface incorporated with the combination of geometrical seismic attributes analysis – maximum curvature, minimum curvature, variance and ant tracking to identify fracture density of the fracture network. Five main steps were conducted starting with the data conditioning followed by seismic interpretation of the key surface. The final steps from step 3 were conducted by using geometrical seismic attributes, step 4 and step 5 by using principal component analysis and neural network – supervised analysis. Principal component analysis (PCA) of these four seismic attributes is able to delineate the contribution of each attributes with the PC0: 1.3450 (33.63%), PC1:1.0556 (26.39%), PC2:0.9270 (23.17%) and PC3:0.6724 (16.81%). The results of these analysis followed by results from neural network – supervised analysis based on the contribution of each PC in four main results (i) PC0 (ii) PC0 and PC1 (iii) PC0, PC1 and PC2 (iv) PC0, PC1, PC 2 and PC3. In this study, fracture networks were able to be delineated geological features that might be overlooked was able to be captured and can guide the fracture network inside the fractured basement
ANNUR ASMA SAYIDAH SHAMSUDDIN, DEVA PRASAD GHOSH