Vertical variations of rock thermal conductivity from well-logging data using machine-learning methods

2020 ◽  
Author(s):  
A. Shakirov ◽  
Y. Meshalkin ◽  
D. Koroteev ◽  
Y. Popov
Keyword(s):  
Machine Learning ◽  
Thermal Conductivity ◽  
Well Logging ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Vertical Variations ◽  
Rock Thermal Conductivity

Robust well-log based determination of rock thermal conductivity through machine learning

2020 ◽  
Vol 222 (2) ◽  
pp. 978-988
Author(s):  
Yury Meshalkin ◽  
Anuar Shakirov ◽  
Evgeniy Popov ◽  
Dmitry Koroteev ◽  
Irina Gurbatova
Keyword(s):  
Machine Learning ◽  
Thermal Conductivity ◽  
Random Forest ◽  
Well Logging ◽  
Machine Learning Algorithms ◽  
System Modelling ◽  
Well Log ◽  
Random Forest Algorithm ◽  
Rock Thermal Conductivity

SUMMARY Rock thermal conductivity is an essential input parameter for enhanced oil recovery methods design and optimization and for basin and petroleum system modelling. Absence of any effective technique for direct in situ measurements of rock thermal conductivity makes the development of well-log based methods for rock thermal conductivity determination highly desirable. A major part of the existing problem solutions is regression model-based approaches. Literature review revealed that there are only several studies performed to assess the applicability of neural network-based algorithms to predict rock thermal conductivity from well-logging data. In this research, we aim to define the most effective machine-learning algorithms for well-log based determination of rock thermal conductivity. Well-logging data acquired at a heavy oil reservoir together with results of thermal logging on cores extracted from two wells were the basis for our research. Eight different regression models were developed and tested to predict vertical variations of rock conductivity from well-logging data. Additionally, rock thermal conductivity was determined based on Lichtenecker–Asaad model. Comparison study of regression-based and theoretical-based approaches was performed. Among considered machine learning techniques Random Forest algorithm was found to be the most accurate at well-log based determination of rock thermal conductivity. From a comparison of the thermal conductivity—depth profile predicted from well-logging data with the experimental data, and it can be concluded that thermal conductivity can be determined with a total relative error of 12.54 per cent. The obtained results prove that rock thermal conductivity can be inferred from well-logging data for wells that are drilled in a similar geological setting based on the Random Forest algorithm with an accuracy sufficient for industrial needs.

scholarly journals Forecast of water-cut at wells under design by machine learning methods

2019 ◽  
pp. 510-520
Author(s):  
M R Enikeev ◽  
M F Fazlytdinov ◽  
L V Enikeeva ◽  
I M Gubaidullin
Keyword(s):  
Machine Learning ◽  
Oil Industry ◽  
Well Logging ◽  
Oil Fields ◽  
Local Analysis ◽  
Learning Methods ◽  
Initial Water ◽  
Machine Learning Methods ◽  
Deterministic Methods ◽  
Water Cut

A large amount of data is generated during the operation of oil fields. Such data can be both data already interpreted by a specialist, or "raw” data obtained directly from the devices, both structured and not structured, or locally structured (that is, allowing for local analysis, but in such form not allowing analyzing in conjunction with other types of data). To obtain from such a set of more informative data that will allow making decisions in the course of field operation, it is necessary to involve specialists from different areas of the oil industry. Therefore, it is possible and necessary to use non-deterministic methods for analyzing the data obtained. The article discusses the use of machine learning methods in the task of determining the initial water-cut based on well logging data.

Sign in / Sign up

Export Citation Format

Share Document