Enhanced Reservoir Geosteering and Geomapping from Refined Models of Ultra-Deep LWD Resistivity Inversions Using Machine-Learning Algorithms
- Hsu-Hsiang (Mark) Wu (Halliburton) | Li Pan (Halliburton) | Jin Ma (Halliburton) | Weixin Dong (Halliburton) | Yijing Fan (Halliburton) | Clint Lozinsky (Halliburton) | Michael Bittar (Halliburton)
- Document ID
- Society of Petrophysicists and Well-Log Analysts
- SPWLA 60th Annual Logging Symposium, 15-19 June, The Woodlands, Texas, USA
- Publication Date
- Document Type
- Conference Paper
- 2019. held jointly by the Society of Petrophysicists and Well Log Analysts (SPWLA) and the submitting authors
- 69 in the last 30 days
- 116 since 2007
- Show more detail
Ultradeep logging-while-drilling (LWD) resistivity tools have been widely used in the borehole resistivity applications. Previous field examples successfully demonstrated a detection range more than 200 ft away from a wellbore. As a result of the ultradeep detection capability, the complexity of the inversion process increases to accommodate a larger number of layered models, as compared to the conventional approaches. Cloud-based distributed solutions were implemented in the algorithms to efficiently provide in-time geological inverted models for real-time decisions. These available software platforms and successful field data from the ultradeep-reading tools initialized further studies and evaluations of the advanced, machine-learning algorithms applied into the existing inversion process.
Based on a large database of ultradeep resistivity measurements from past successful field jobs and prewell modeling, this paper presents several deep-learning algorithms to improve the existing inversion process for extracting more geological information (Payrazyan et al., 2017; Xu et al., 2019). The proposed methods identify similarities among numerous solutions attained by individual steps of the existing inversion process. Then, most likely distributions are detected within a detection range of the inversion to remove outlier signals and models, and to further produce more geologically reasonable representations. The proposed methods also enable automatic boundary-picking of layers with a major resistivity contrast between them. The determined connections learned from the previous sets of measurements are used to train any future processes based on a new set of measurements, enabling more efficient evaluations and calculations. Both modeling and field examples establish better geological interpolations acquired from the presented machinelearning algorithms than the original inversion approach. The use of the machine-learning concepts on the ultradeep resistivity measurements efficiently enhances the quality of the final geological interpretation over long detection distances into the formations. This enhancement benefits operations by optimizing reservoir development, maximizing assets, and reducing overall operational cost.
During oil and gas exploration, knowledge of the geology is always essential for maximizing the reservoir production. Successful reservoir development relies on optimal placement of many wellbores over long periods of time within an area. While drilling a new wellbore, other wellbores in the production stage may have existed for many years. Therefore, the content of the reservoirs could be changed and filled with injected water from these wells. Although similar geology may be expected in the area, different geosteering decisions in the new wellbores are needed by considering the actual contents of the reservoirs during different periods. Previously, these decisions were not available because of the limited detection range or low resolutions of conventional techniques. Thus, the introduction of ultradeep electromagnetic resistivity techniques became a turning point to provide insightful geological information. The technique can determine the actual formation contents from more than 100 to 200 ft from a well that is being drilled, making previously impossible real-time geosteering decisions possible. The technique determines shapes of the reservoirs, confirms the water contents within the reservoirs, and identifies possible locations of other reservoirs that were not detectable previously.
|File Size||1 MB||Number of Pages||8|