Full text loading...
-
Micro-Fault System Detection by Machine Learning
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, 81st EAGE Conference and Exhibition 2019, Jun 2019, Volume 2019, p.1 - 5
Abstract
We propose a new micro-fault system predicting approach based on support vector machine and well-seismic tie. First, we estimate sensitive micro-fault factor which can reflect the fracture property near wells combining anisotropy theory and rock physics. Then, seismic attributes were extracted from post-stack seismic data. Correlation cluster method was utilized to select attributes related to micro-fault system. Finally, support vector machine was applied to establish non-linear relationship between sensitive micro-fault factor and attributes sets. Sensitive micro-fault factor was estimated by the new mapping function and realised the aim of micro-fault system discrimination. Real data example revealed that the detected results consist with structural map and well log data. We confirm that the new approach is feasible and efficient for complex reservoir detection.