Abstract
Permeability prediction has been an important problem since the time of Darcy. Most approaches to solve this problem have used either idealized physical models or empirical relations. In recent years, machine learning (ML) has led to more accurate and robust, but less interpretable empirical models. Using 211 core samples collected from 12 wells in the Garn Sandstone from the North Sea, this study compared idealized physical models based on the Carman-Kozeny equation to interpretable ML models. We found that ML models trained on estimates of physical properties are more accurate than physical models. Also, the results show evidence of a threshold of about 10% volume fraction, above which pore-filling cement strongly affects permeability.
Original language | English (US) |
---|---|
Article number | 103244 |
Journal | Journal of Natural Gas Science and Engineering |
Volume | 77 |
DOIs | |
State | Published - May 2020 |
All Science Journal Classification (ASJC) codes
- Fuel Technology
- Geotechnical Engineering and Engineering Geology
- Energy Engineering and Power Technology