Integrating Electrofacies and Well Logging Data Into Regression and Machine Learning Approaches for Improved Permeability Estimation in a Carbonate Reservoir In a Giant Southern Iraqi Oil Field

2020 ◽  
Author(s):  
Watheq J Al-Mudhafar
Keyword(s):  
Machine Learning ◽  
Well Logging ◽  
Carbonate Reservoir ◽  
Oil Field ◽  
Learning Approaches ◽  
Permeability Estimation

Forecast of Prospective Oil Saturation Zones in the Devonian Carbonate Deposits of the Kharyaginsky Field Based on Geological and Geophysical Information Analysis by Using Machine Learning Methods

2021 ◽  
Author(s):  
Sergey Igorevich Gusev ◽  
Elena Sergeyevna Kolbikova ◽  
Olga Igorevna Malinovskaya ◽  
Azat Fanisovich Garaev ◽  
Robert Kamilevich Valiev
Keyword(s):  
Machine Learning ◽  
Carbonate Reservoir ◽  
Oil Field ◽  
Core Material ◽  
Joint Analysis ◽  
Information Analysis ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Geophysical Information ◽  
Carbonate Deposits

Abstract The Kharyaginskoye oil field is located on the territory of the Nenets Autonomous District and belongs to the Timan-Pechora Basin oil and gas province. The main object of development is a Devonian age carbonate reservoir. The productive zones of the studied object are mainly confined to thin bed low-porosity reservoirs with a complex structure of void space. The high heterogeneity of deposits laterally and the presence of different levels of oil-water contact (OWC) in the marginal isolated zones necessitate a more accurate assessment of the oil-saturated effective thicknesses. The increase in the reliability of the interpretation was achieved by the joint analysis of borehole and seismic studies using Machine Learning methods. At the stage of configuring the facies model based on well logs and core data, a Multi-Resolution Graph-based Clustering MRGC was used, which provides effective integration of geological and geophysical information. The multi-dimensional dot-pattern recognition method based on k-Nearest neighbors algorithm (k-NN), and by combining various criteria, it allows solving the problem of non-linearity of the relationships between logging responses and the corresponding lithology. The algorithm of the democratic association of neural networks DNNA was used to propagate electrofacies in the inter-well space. The method optimizes the use of seismic data before summation and after summation together with well data through a controlled process that provides a calibrated and scaled distribution of facies. The most probable facies distribution can be used directly as a property in reservoir modeling or as a constraint for modeling. It is known that there is no direct connection between a certain type of wave pattern and the lithological composition of rocks, therefore, the analysis of changing reflection characteristics is performed in conjunction with geophysical data, such as well logging. In addition, a priori geological information about the work area is involved. An important condition for the effective application of facies analysis is the presence of representative core material and the availability of high-quality well information. At the first stage of the work, the lithotyping of carbonate deposits was performed according to the macro description of the core, based on the classification of limestones according to R. H. Dunham. Then, using the multidimensional statistical recognition algorithm MRGC, the relationships between the selected lithotypes and logging responses were obtained. As a result of the tuning, a cluster model was obtained that allows us to distinguish electrofacies characterized by an increased filtration and capacitance potential. At the second stage, the obtained electrofacies, considering the nature of saturation, were used to train cubes of seismic attributes and calculate the cubes of lithofacies and the probability of the existence of each lithofacies. The key point in the distribution was the use of electrofacies obtained in wells belonging to different facies zones. Thus, the joint analysis of all available borehole and seismic information by machine learning methods made it possible to make a forecast lithofacies considering the type of saturation based on geological and geophysical information analysis. The effectiveness of the presented technologies was demonstrated by analyzing the properties of low-permeable carbonate reservoirs, where classical attributes and inversion demonstrate limitations in describing a heterogeneous saturation model. The use of neural network approaches allows to configure complex nonlinear dependencies that are not available to classical methods. The use of a small volume of multi-scale geological and geophysical information using Machine Learning algorithms in the field of field-geophysical and seismic interpretation makes it possible to increase the reliability of interpretation and clarify the location of prospective zones with improved reservoir properties on the studied area, as well as to minimize geological risks during subsequent well placement.

Lithofacies Classification of Carbonate Reservoirs Using Advanced Machine Learning: A Case Study from a Southern Iraqi Oil Field

2021 ◽  
Author(s):  
Mohammed A. Abbas ◽  
Watheq J. Al-Mudhafar
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Reservoir Characterization ◽  
Carbonate Reservoir ◽  
Oil Field ◽  
Machine Learning Techniques ◽  
Classification Algorithms ◽  
Classification Rate ◽  
Porosity And Permeability ◽  
Lithofacies Classification

Abstract Estimating rock facies from petrophysical logs in non-cored wells in complex carbonates represents a crucial task for improving reservoir characterization and field development. Thus, it most essential to identify the lithofacies that discriminate the reservoir intervals based on their flow and storage capacity. In this paper, an innovative procedure is adopted for lithofacies classification using data-driven machine learning in a well from the Mishrif carbonate reservoir in the giant Majnoon oil field, Southern Iraq. The Random Forest method was adopted for lithofacies classification using well logging data in a cored well to predict their distribution in other non-cored wells. Furthermore, three advanced statistical algorithms: Logistic Boosting Regression, Bagging Multivariate Adaptive Regression Spline, and Generalized Boosting Modeling were implemented and compared to the Random Forest approach to attain the most realistic lithofacies prediction. The dataset includes the measured discrete lithofacies distribution and the original log curves of caliper, gamma ray, neutron porosity, bulk density, sonic, deep and shallow resistivity, all available over the entire reservoir interval. Prior to applying the four classification algorithms, a random subsampling cross-validation was conducted on the dataset to produce training and testing subsets for modeling and prediction, respectively. After predicting the discrete lithofacies distribution, the Confusion Table and the Correct Classification Rate Index (CCI) were employed as further criteria to analyze and compare the effectiveness of the four classification algorithms. The results of this study revealed that Random Forest was more accurate in lithofacies classification than other techniques. It led to excellent matching between the observed and predicted discrete lithofacies through attaining 100% of CCI based on the training subset and 96.67 % of the CCI for the validating subset. Further validation of the resulting facies model was conducted by comparing each of the predicted discrete lithofacies with the available ranges of porosity and permeability obtained from the NMR log. We observed that rudist-dominated lithofacies correlates to rock with higher porosity and permeability. In contrast, the argillaceous lithofacies correlates to rocks with lower porosity and permeability. Additionally, these high-and low-ranges of permeability were later compared with the oil rate obtained from the PLT log data. It was identified that the high-and low-ranges of permeability correlate well to the high- and low-oil rate logs, respectively. In conclusion, the high quality estimation of lithofacies in non-cored intervals and wells is a crucial reservoir characterization task in order to obtain meaningful permeability-porosity relationships and capture realistic reservoir heterogeneity. The application of machine learning techniques drives down costs, provides for time-savings, and allows for uncertainty mitigation in lithofacies classification and prediction. The entire workflow was done through R, an open-source statistical computing language. It can easily be applied to other reservoirs to attain for them a similar improved overall reservoir characterization.

scholarly journals K-Mean Clustering Analysis and Logistic Boosting Regression for Rock Facies Characterization and Classification in Zubair Reservoir in Luhais Oil Field, Southern Iraq

2021 ◽  
Vol 54 (2B) ◽  
pp. 65-75
Author(s):  
Mohammed Albuslimi
Keyword(s):  
Water Saturation ◽  
Confusion Matrix ◽  
Well Logging ◽  
Oil Field ◽  
Core Analysis ◽  
Learning Approaches ◽  
Classification Rate ◽  
Lithofacies Classification ◽  
Core Description ◽  
Southern Iraq

Identifying rock facies from petrophysical logs is a crucial step in the evaluation and characterization of hydrocarbon reservoirs. The rock facies can be obtained either from core analysis (lithofacies) or from well logging data (electrofacies). In this research, two advanced machine learning approaches were adopted for electrofacies identification and for lithofacies classification, both given the well-logging interpretations from a well in the upper shale member in Luhais Oil Field, southern Iraq. Specifically, the K-mean partitioning analysis and Logistic Boosting (Logit Boost) were conducted for electrofacies characterization and lithofacies classification, respectively. The dataset includes the routine core analysis of core porosity, core permeability, and measured discrete lithofacies along with the well-logging interpretations include (shale volume, water saturation and effective porosity) given the entire reservoir interval. The K-Mean clustering technique demonstrated good matching between the vertical sequence of identified electrofacies and the observed lithofacies from core description as attained 89.92% total correct percent from the confusion matrix table. The Logit Boost showed excellent matching between the recognized lithofacies from the core description and the predicted lithofacies through attained 98.26% total correct classification rate index from the confusion matrix table. The high accuracy of the Logit Boost algorithm comes from taking into account the non-linearity between the lithofacies and petrophysical properties in the classification process. The high degree of lithofacies classification by Logit Boost in this research can be considered in a similar procedure at all sandstone reservoirs to improve the reservoir characterization. The complete facies identification and classification were implemented with the programming language R, the powerful open-source statistical computing language.

Multiple vehicles detection and tracking for intelligent transport systems using machine learning approaches

2019 ◽  
Vol 70 (3) ◽  
pp. 214-224
Author(s):  
Bui Ngoc Dung ◽  
Manh Dzung Lai ◽  
Tran Vu Hieu ◽  
Nguyen Binh T. H.
Keyword(s):  
Machine Learning ◽  
Gaussian Mixture ◽  
Research Field ◽  
Transport Systems ◽  
Learning Approaches ◽  
Subtraction Method ◽  
Intelligent Transport Systems ◽  
Intelligent Transport ◽  
Detection And Tracking ◽  
Multiple Vehicles

Video surveillance is emerging research field of intelligent transport systems. This paper presents some techniques which use machine learning and computer vision in vehicles detection and tracking. Firstly the machine learning approaches using Haar-like features and Ada-Boost algorithm for vehicle detection are presented. Secondly approaches to detect vehicles using the background subtraction method based on Gaussian Mixture Model and to track vehicles using optical flow and multiple Kalman filters were given. The method takes advantages of distinguish and tracking multiple vehicles individually. The experimental results demonstrate high accurately of the method.

Sign in / Sign up

Export Citation Format

Share Document