Petrophysical Workflows vs Machine Learning – A Comparative Case Study in the Dakota Group, Williston Basin
- Saptaswa Basu (ConocoPhillips Company Ltd) | Kyrre Johansen (ConocoPhillips Company Ltd) | Sergey Skvortsov (ConocoPhillips Company Ltd)
- Document ID
- Society of Petrophysicists and Well-Log Analysts
- SPWLA 61st Annual Logging Symposium - Online, 24 June - 29 July, Virtual Online Webinar
- Publication Date
- Document Type
- Conference Paper
- 2020. held jointly by the Society of Petrophysicists and Well Log Analysts (SPWLA) and the submitting authors
- 80 in the last 30 days
- 80 since 2007
- Show more detail
This work compares traditional petrophysical workflows to machine learning methods to compute porosity and permeability in the Inyan Kara Formation of the Dakota Group in the Williston Basin. Quality of dataset (variability, size and robustness), basic theoretical approach, method, results, applicability in the geological area and predictive power are the fundamental basis of this comparison.
Produced water disposal into a shallow Dakota Group presents challenges to nearby development drilling, potentially generating high-pressure zones in the overburden. Accurate pressure prediction for the Dakota is very valuable for drilling design and development timing decisions. Along with disposal volumes, porosity is the critical variable which determines the formation pressure. The Dakota does not contain hydrocarbons resulting in limited porosity log data. However, there are abundant resistivity and gamma ray logs through this interval. Therefore, a data analytics model is used to compute porosity based on location and available resistivity and gamma ray logs. Also, a modified Archie’s equation is used to compute porosity from resistivity and gamma ray data. Data analytics-based porosity and resistivity-based porosity are compared with available neutron-density log derived porosities.
The team working this project comprised a Petrophysicist, Reservoir Engineer and Geologist who compiled, analyzed and built a geo- and reservoir model based on this work to predict formation pressure in the Dakota Sands.
The Williston Basin, North Dakota, has become one of the largest oil producers in the United States. Large volumes of water are being produced along with oil, most of which is disposed in Inyan Kara formation of the Dakota Group. The Dakota Group is situated between the surface and the zones targeted for oil and gas development drilling. Water disposal into this shallower formation presents risks to nearby development drilling, potentially causing high pressure zones in the overburden. Accurate pore pressure predictions for the Dakota Group is very valuable for drilling design decisions. Along with disposal volumes, porosity is the critical variable which determines the formation pressure.
|File Size||2 MB||Number of Pages||12|