Prediction of gas hydrate saturation using machine learning and optimal set of well-logs
- PDF / 2,733,857 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 66 Downloads / 233 Views
ORIGINAL PAPER
Prediction of gas hydrate saturation using machine learning and optimal set of well-logs Harpreet Singh 1
&
Yongkoo Seol 1 & Evgeniy M. Myshakin 1,2
Received: 31 January 2020 / Accepted: 14 September 2020 # Springer Nature Switzerland AG 2020
Abstract Resistivity and acoustic logs are widely used to estimate gas hydrate saturation in various sedimentary systems using one of the two popular methods ((1) acoustic velocity and (2) electrical resistivity), but the limitations of these two methods are often overlooked, which include (i) well-specific calibration of empirical exponents in the electrical resistivity method, (ii) assumption of known pore morphology for gas hydrates in the acoustic velocity method, and (iii) presence of unknown mineralogy and bulk modulus terms in the acoustic velocity method. NMR-density porosity-derived gas hydrate saturation based on the analysis of the transverse magnetization relaxation time (T2) is considered the most precise method, but acquisition of NMR-based logs is limited at relatively recent drilled sites; additionally, its use in conventional oil and gas reservoirs is not that common due to higher cost and operational deployment limitations associated with acquiring NMR well-logs. This study proposes a new method that predicts gas hydrate saturation (Sh) for any well using porosity, bulk density, and compressional wave (P wave) velocity welllogs with neural network (or stochastic gradient descent regression) without any well-specific calibration and/or other aforementioned shortcomings of the existing methods. The method is developed by examining the underlying dependency between Sh and different combinations of well-logs, chosen from 6 routine logs, with 12 different machine learning (ML) algorithms. The accuracy of the proposed method in predicting Sh is ~ 84%, which is better than the accuracy of seismic and electrical resistivity methods (≤ 75%) per the results reported by three different studies. The robustness of the method in the specific case of permafrost-associated gas hydrates is demonstrated with well-log data from two wells drilled on the Alaska North Slope. Keywords Machine learning . Gas hydrates . Well-logs . Neural network . Supervised learning
1 Introduction Well-logs are rock and fluid measurements obtained through tools that are run down through a deep wellbore during or after drilling to quantify reservoir properties and evaluate its potential. Some of the well-logs are routinely acquired for all the Electronic supplementary material The online version of this article (https://doi.org/10.1007/s10596-020-10004-3) contains supplementary material, which is available to authorized users. * Harpreet Singh [email protected] * Yongkoo Seol [email protected] 1
National Energy Technology Laboratory, Morgantown, WV, USA
2
Leidos Research Support Team, 626 Cochrans Mill Road, Pittsburgh, PA, USA
wells, whereas some advanced well-logs like nuclear magnetic resonance (NMR) are not part of the commonly acquired well-logs due to h
Data Loading...
