scholarly journals Comparison of Rock Type Determination Based on Permeability Estimation and FZI Value in Upper Cibulakan Shaly Sand Formation, ASR Field

2020 ◽  
Vol 2 (3) ◽  
Author(s):  
Anditya Sapta Rahesthi ◽  
Ratnayu Sitaresmi ◽  
Sigit Rahmawan
Keyword(s):  
Rock Type ◽  
Well Log ◽  
Rock Permeability ◽  
Log Data ◽  
Core Data ◽  
Permeability Prediction ◽  
Rock Types ◽  
Fluid Production ◽  
Shaly Sand ◽  
High Uncertainty

<em>Rock permeability is an important rock characteristic because it can help determine the rate of fluid production. Permeability can only be determined by direct measurement of core samples in the laboratory. Even though coring gives good results, the disadvantage is that it takes a lot of time and costs so it is not possible to do coring at all intervals. So that the well log is required to predict the level of permeability indirectly. However, the calculation of permeability prediction using well log data has a high uncertainty value, so rock typing is required so that the calculation of permeability prediction becomes more detailed. This research was conducted in an effort to determine the Hydraulic Flow Unit (HFU) of the reservoir in the well that has core data using the Flow Zone Indicator (FZI) parameter and FZI value propagation on wells that do not have core data so that the type of rock and permeability value are obtained from every well interval. From the results of the study, the reservoirs on the ASR field can be grouped into six rock types. The six rock types each have permeability as a function of validated porosity by applying it at all intervals. After FZI is calculated from log data and validated with core data, it can be seen that the results of the method produce a fairly good correlation (R<sup>2</sup> = 0.92). Furthermore, from the permeability equation values for each different rock type, the predicted permeability results are also quite good (R<sup>2 </sup>= 0.81).</em>

scholarly journals Reservoir Parameters Estimation with Some Log Curves of Qiongdongnan Basin Based on LS-SVM Method

2021 ◽  
Vol 2092 (1) ◽  
pp. 012024
Author(s):  
Tangwei Liu ◽  
Hehua Xu ◽  
Xiaobin Shi ◽  
Xuelin Qiu ◽  
Zhen Sun
Keyword(s):  
Prediction Models ◽  
Parameters Estimation ◽  
Qiongdongnan Basin ◽  
Support Vector ◽  
Well Log ◽  
Statistical Regression ◽  
Log Data ◽  
Core Data ◽  
Permeability Prediction ◽  
Porosity And Permeability

Abstract Reservoir porosity and permeability are considered as very important parameters in characterizing oil and gas reservoirs. Traditional methods for porosity and permeability prediction are well log and core data analysis to get some regression empirical formulas. However, because of strong non-linear relationship between well log data and core data such as porosity and permeability, usual statistical regression methods are not completely able to provide meaningful estimate results. It is very difficult to measure fine scale porosity and permeability parameters of the reservoir. In this paper, the least square support vector machine (LS-SVM) method is applied to the parameters estimation with well log and core data of Qiongdongnan basin reservoirs. With the log and core exploration data of Qiongdongnan basin, the approach and prediction models of porosity and permeability are constructed and applied. There are several type of log data for the determination of porosity and permeability. These parameters are related with the selected log data. However, a precise analysis and determine of parameters require a combinatorial selection method for different type data. Some curves such as RHOB,CALI,POTA,THOR,GR are selected from all obtained logging curves of a Qiongdongnan basin well to predict porosity. At last we give some permeability prediction results based on LS-SVM method. High precision practice results illustrate the efficiency of LS-SVM method for practical reservoir parameter estimation problems.

Rock Type Classification Models Interpretability Using Shapley Values

2021 ◽  
Author(s):  
Anton Georgievich Voskresenskiy ◽  
Nikita Vladimirovich Bukhanov ◽  
Maria Alexandrovna Kuntsevich ◽  
Oksana Anatolievna Popova ◽  
Alexey Sergeevich Goncharov
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Causal Inference ◽  
Rock Type ◽  
Well Logs ◽  
Well Log ◽  
Classification Models ◽  
Rock Types ◽  
Shapley Values ◽  
Type Classification

Abstract We propose a methodology to improve rock type classification using machine learning (ML) techniques and to reveal causal inferences between reservoir quality and well log measurements. Rock type classification is an essential step in accurate reservoir modeling and forecasting. Machine learning approaches allow to automate rock type classification based on different well logs and core data. In order to choose the best model which does not progradate uncertainty further into the workflow it is important to interpret machine learning results. Feature importance and feature selection methods are usually employed for that. We propose an extension to existing approaches - model agnostic sensitivity algorithm based on Shapley values. The paper describes a full workflow to rock type prediction using well log data: from data preparation, model building, feature selection to causal inference analysis. We made ML models that classify rock types using well logs (sonic, gamma, density, photoelectric and resistivity) from 21 wells as predictors and conduct a causal inference analysis between reservoir quality and well logs responses using Shapley values (a concept from a game theory). As a result of feature selection, we obtained predictors which are statistically significant and at the same time relevant in causal relation context. Macro F1-score of the best obtained models for both cases is 0.79 and 0.85 respectively. It was found that the ML models can infer domain knowledge, which allows us to confirm the adequacy of the built ML model for rock types prediction. Our insight was to recognize the need to properly account for the underlying causal structure between the features and rock types in order to derive meaningful and relevant predictors that carry a significant amount of information contributing to the final outcome. Also, we demonstrate the robustness of revealed patterns by applying the Shapley values methodology to a number of ML models and show consistency in order of the most important predictors. Our analysis shows that machine learning classifiers gaining high accuracy tend to mimic physical principles behind different logging tools, in particular: the longer the travel time of an acoustic wave the higher probability that media is represented by reservoir rock and vice versa. On the contrary lower values of natural radioactivity and density of rock highlight the presence of a reservoir. The article presents causal inference analysis of ML classification models using Shapley values on 2 real-world reservoirs. The rock class labels from core data are used to train a supervised machine learning algorithm to predict classes from well log response. The aim of supervised learning is to label a small portion of a dataset and allow the algorithm to automate the rest. Such data-driven analysis may optimize well logging, coring, and core analysis programs. This algorithm can be extended to any other reservoir to improve rock type prediction. The novelty of the paper is that such analysis reveals the nature of decisions made by the ML model and allows to apply truly robust and reliable petrophysics-consistent ML models for rock type classification.

Rock typing and facies identification using fractal theory and conventional petrophysical logs

2018 ◽  
Vol 58 (1) ◽  
pp. 102
Author(s):  
Roozbeh Koochak ◽  
Manouchehr Haghighi ◽  
Mohammad Sayyafzadeh ◽  
Mark Bunch
Keyword(s):  
Fractal Dimension ◽  
Multiple Scales ◽  
Fractal Theory ◽  
Depositional Environments ◽  
Log Data ◽  
Rock Types ◽  
Rock Typing ◽  
Resistivity Logs ◽  
Shaly Sand ◽  
Rock Texture

Rock typing or subdivision of a reservoir either vertically or laterally is an important task in reservoir characterisation and production prediction. Different depositional environments and diagenetic effects create rocks with different grain size distribution and grain sorting. Rock typing and zonation is usually made by analysing log data and core data (mercury injection capillary pressure and permeability measurement). In this paper, we introduce a new technique (approach) for rock typing using fractal theory in which resistivity logs are the only required data. Since resistivity logs are sensitive to rock texture, in this study, deep conventional resistivity logs are used from eight different wells. Fractal theory is applied to our log data to seek any meaningful relationship between the variability of resistivity logs and complexity of rock fabric. Fractal theory has been previously used in many stochastic processes which have common features on multiple scales. The fractal property of a system is usually characterised by a fractal dimension. Therefore, the fractal dimension of all the resistivity logs is obtained. The results of our case studies in the Cooper Basin of Australia show that the fractal dimension of resistivity logs increases from 1.14 to 1.29 for clean to shaly sand respectively, indicating that the fractal dimension increases with complexity of rock texture. The fractal dimension of resistivity logs is indicative of the complexity of pore fabric, and therefore can be used to define rock types.

Enhanced group method of data handling (GMDH) for permeability prediction based on the modified Levenberg Marquardt technique from well log data

Energy ◽  
2022 ◽  
Vol 239 ◽  
pp. 121915
Author(s):  
Alvin K. Mulashani ◽  
Chuanbo Shen ◽  
Baraka M. Nkurlu ◽  
Christopher N. Mkono ◽  
Martin Kawamala
Keyword(s):  
Group Method ◽  
Well Log ◽  
Data Handling ◽  
Log Data ◽  
Permeability Prediction ◽  
Levenberg Marquardt

scholarly journals Centimeter-Scale Lithology and Facies Prediction in Cored Wells Using Machine Learning

2021 ◽  
Vol 9 ◽  
Author(s):  
Thomas Martin ◽  
Ross Meyer ◽  
Zane Jobe
Keyword(s):  
Machine Learning ◽  
Open Source ◽  
Image Data ◽  
Machine Learning Algorithms ◽  
Core Material ◽  
Depth Interval ◽  
Well Log ◽  
Log Data ◽  
Core Data ◽  
Labeling Scheme

Machine-learning algorithms have been used by geoscientists to infer geologic and physical properties from hydrocarbon exploration and development wells for more than 40 years. These techniques historically utilize digital well-log information, which, like any remotely sensed measurement, have resolution limitations. Core is the only subsurface data that is true to geologic scale and heterogeneity. However, core description and analysis are time-intensive, and therefore most core data are not utilized to their full potential. Quadrant 204 on the United Kingdom Continental Shelf has publicly available open-source core and well log data. This study utilizes this dataset and machine-learning models to predict lithology and facies at the centimeter scale. We selected 12 wells from the Q204 region with well-log and core data from the Schiehallion, Foinaven, Loyal, and Alligin hydrocarbon fields. We interpreted training data from 659 m of core at the sub-centimeter scale, utilizing a lithology-based labeling scheme (five classes) and a depositional-process-based facies labeling scheme (six classes). Utilizing a “color-channel-log” (CCL) that summarizes the core image at each depth interval, our best performing trained model predicts the correct lithology with 69% accuracy (i.e., the predicted lithology output from the model is the same as the interpreted lithology) and predicts individual lithology classes of sandstone and mudstone with over 80% accuracy. The CCL data require less compute power than core image data and generate more accurate results. While the process-based facies labels better characterize turbidites and hybrid-event-bed stratigraphy, the machine-learning based predictions were not as accurate as compared to lithology. In all cases, the standard well-log data cannot accurately predict lithology or facies at the centimeter level. The machine-learning workflow developed for this study can unlock warehouses full of high-resolution data in a multitude of geological settings. The workflow can be applied to other geographic areas and deposit types where large quantities of photographed core material are available. This research establishes an open-source, python-based machine-learning workflow to analyze open-source core image data in a scalable, reproducible way. We anticipate that this study will serve as a baseline for future research and analysis of borehole and core data.

Sign in / Sign up

Export Citation Format

Share Document