scholarly journals Evaluation of the Total Organic Carbon (TOC) Using Different Artificial Intelligence Techniques

2019 ◽  
Vol 11 (20) ◽  
pp. 5643 ◽  
Author(s):  
Ahmed Abdulhamid Mahmoud ◽  
Salaheldin Elkatatny ◽  
Abdulwahab Z. Ali ◽  
Mohamed Abouelresh ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Artificial Intelligence ◽  
Organic Carbon ◽  
Total Organic Carbon ◽  
Well Logs ◽  
Support Vector ◽  
Validation Data ◽  
Fuzzy Interference System ◽  
Interference System ◽  
Unseen Data ◽  
Devonian Shale

Total organic carbon (TOC) is an essential parameter used in unconventional shale resources evaluation. Current methods that are used for TOC estimation are based, either on conducting time-consuming laboratory experiments, or on using empirical correlations developed for specific formations. In this study, four artificial intelligence (AI) models were developed to estimate the TOC using conventional well logs of deep resistivity, gamma-ray, sonic transit time, and bulk density. These models were developed based on the Takagi-Sugeno-Kang fuzzy interference system (TSK-FIS), Mamdani fuzzy interference system (M-FIS), functional neural network (FNN), and support vector machine (SVM). Over 800 data points of the conventional well logs and core data collected from Barnett shale were used to train and test the AI models. The optimized AI models were validated using unseen data from Devonian shale. The developed AI models showed accurate predictability of TOC in both Barnett and Devonian shale. FNN model overperformed others in estimating TOC for the validation data with average absolute percentage error (AAPE) and correlation coefficient (R) of 12.02%, and 0.879, respectively, followed by M-FIS and SVM, while TSK-FIS model showed the lowest predictability of TOC, with AAPE of 15.62% and R of 0.832. All AI models overperformed Wang models, which have recently developed to evaluate the TOC for Devonian formation.

scholarly journals Application of Various Machine Learning Techniques in Predicting Total Organic Carbon from Well Logs

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Osama Siddig ◽  
Ahmed Farid Ibrahim ◽  
Salaheldin Elkatatny
Keyword(s):  
Machine Learning ◽  
Organic Carbon ◽  
Total Organic Carbon ◽  
The Other ◽  
Well Logs ◽  
Machine Learning Techniques ◽  
Percentage Error ◽  
Average Error ◽  
Support Vector ◽  
Empirical Correlations

Unconventional resources have recently gained a lot of attention, and as a consequence, there has been an increase in research interest in predicting total organic carbon (TOC) as a crucial quality indicator. TOC is commonly measured experimentally; however, due to sampling restrictions, obtaining continuous data on TOC is difficult. Therefore, different empirical correlations for TOC have been presented. However, there are concerns about the generalization and accuracy of these correlations. In this paper, different machine learning (ML) techniques were utilized to develop models that predict TOC from well logs, including formation resistivity (FR), spontaneous potential (SP), sonic transit time (Δt), bulk density (RHOB), neutron porosity (CNP), gamma ray (GR), and spectrum logs of thorium (Th), uranium (Ur), and potassium (K). Over 1250 data points from the Devonian Duvernay shale were utilized to create and validate the model. These datasets were obtained from three wells; the first was used to train the models, while the data sets from the other two wells were utilized to test and validate them. Support vector machine (SVM), random forest (RF), and decision tree (DT) were the ML approaches tested, and their predictions were contrasted with three empirical correlations. Various AI methods’ parameters were tested to assure the best possible accuracy in terms of correlation coefficient (R) and average absolute percentage error (AAPE) between the actual and predicted TOC. The three ML methods yielded good matches; however, the RF-based model has the best performance. The RF model was able to predict the TOC for the different datasets with R values range between 0.93 and 0.99 and AAPE values less than 14%. In terms of average error, the ML-based models outperformed the other three empirical correlations. This study shows the capability and robustness of ML models to predict the total organic carbon from readily available logging data without the need for core analysis or additional well interventions.

scholarly journals Utilization of adaptive neuro-fuzzy interference system and functional network in prediction of total organic carbon content

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Osama Siddig ◽  
Hany Gamal ◽  
Pantelis Soupios ◽  
Salaheldin Elkatatny
Keyword(s):  
Organic Carbon ◽  
Total Organic Carbon ◽  
Carbon Content ◽  
Total Organic Carbon Content ◽  
Functional Network ◽  
Organic Carbon Content ◽  
Empirical Correlations ◽  
Fuzzy Interference System ◽  
Interference System ◽  
Neuro Fuzzy

Abstract This paper presents the application of two artificial intelligence (AI) approaches in the prediction of total organic carbon content (TOC) in Devonian Duvernay shale. To develop and test the models, around 1250 data points from three wells were used. Each point comprises TOC value with corresponding spectral and conventional well logs. The tested AI techniques are adaptive neuro-fuzzy interference system (ANFIS) and functional network (FN) which their predictions are compared to existing empirical correlations. Out of these two methods, ANFIS yielded the best outcomes with 0.98, 0.90, and 0.95 correlation coefficients (R) in training, testing, and validation respectively, and the average errors ranged between 7 and 18%. In contrast, the empirical correlations resulted in R values less than 0.85 and average errors greater than 20%. Out of eight inputs, gamma ray was found to have the most significant impact on TOC prediction. In comparison to the experimental procedures, AI-based models produces continuous TOC profiles with good prediction accuracy. The intelligent models are developed from preexisting data which saves time and costs. Article highlights In contrast to existing empirical correlation, the AI-based models yielded more accurate TOC predictions. Out of the two AI methods used in this article, ANFIS generated the best estimations in all datasets that have been tested. The reported outcomes show the reliability of the presented models to determine TOC for Devonian shale.

Estimating the Total Organic Carbon for Unconventional Shale Resources During the Drilling Process: A Machine Learning Approach

2021 ◽  
pp. 1-26
Author(s):  
Ahmed Mahmoud ◽  
Hany Gamal ◽  
Salaheldin Elkatatny ◽  
Ahmed Alsaihati
Keyword(s):  
Machine Learning ◽  
Organic Carbon ◽  
Total Organic Carbon ◽  
Gamma Ray ◽  
Fuzzy Inference ◽  
Support Vector ◽  
Drilling Process ◽  
Validation Data ◽  
Inference System ◽  
Data Points

Abstract Total organic carbon (TOC) is an essential parameter that indicates the quality of unconventional reservoirs. In this study, four machine learning (ML) algorithms of the adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR), functional neural networks (FNN), and random forests (RF) were optimized to evaluate the TOC. The novelty of this work is that the optimized models predict the TOC from the bulk gamma-ray (GR) and spectral GR logs of uranium, thorium, and potassium only. The ML algorithms were trained on 749 datasets from Well-1, tested on 226 datasets from Well-2, and validated on 73 data points from Well-3. The predictability of the optimized algorithms was also compared with the available equations. The results of this study indicated that the optimized ANFIS, SVR, and RF models overperformed the available empirical equations in predicting the TOC. For validation data of Well-3, the optimized ANFIS, SVR, and RF algorithms predicted the TOC with AAPE's of 10.6%, 12.0%, and 8.9%, respectively, compared with the AAPE of 21.1% when the FNN model was used. While for the same data, the TOC was assessed with AAPE's of 48.6%, 24.6%, 20.2%, and 17.8% when Schmoker model, ΔlogR method, Zhao et al. correlation, and Mahmoud et al. correlation was used, respectively. The optimized models could be applied to estimate the TOC during the drilling process if the drillstring is provided with GR and spectral GR logging tools.

Predicting Pyrite and Total Organic Carbon from Well Logs for Enhancing Shale Reservoir Interpretation

2012 ◽  
Author(s):  
James M. Witkowsky ◽  
James Elmer Galford ◽  
John Andrew Quirein ◽  
Jerome Allen Truax
Keyword(s):  
Organic Carbon ◽  
Total Organic Carbon ◽  
Well Logs ◽  
Shale Reservoir

Determination of the total organic carbon (TOC) based on conventional well logs using artificial neural network

2017 ◽  
Vol 179 ◽  
pp. 72-80 ◽  
Author(s):  
Ahmed Abdulhamid A. Mahmoud ◽  
Salaheldin Elkatatny ◽  
Mohamed Mahmoud ◽  
Mohamed Abouelresh ◽  
Abdulazeez Abdulraheem ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Organic Carbon ◽  
Total Organic Carbon ◽  
Well Logs ◽  
Artificial Neural

DETERMINATION FROM WELL LOGS OF THE TOTAL ORGANIC CARBON CONTENT IN POTENTIAL SOURCE ROCKS

1994 ◽  
Vol 34 (1) ◽  
pp. 307
Author(s):  
J.L. Lin ◽  
H.A. Salisch
Keyword(s):  
Organic Carbon ◽  
Total Organic Carbon ◽  
Source Rocks ◽  
Well Logs ◽  
Organic Carbon Content ◽  
Well Log ◽  
Single Model ◽  
Geochemical Properties ◽  
Comparison Of The Results ◽  
Immature Source Rock

This paper discusses, in some detail, the log responses to total organic carbon (TOC) in the Upper and Middle Velkerri Formation in an area of the McArthur Basin, Northern Territory, Australia. The Formation Density log was found to be superior to other standard well logs in assessing values of TOC in the area studied. A theoretical model was used to estimate TOC from the Formation Density log. The model was established and its applicability was verified by comparison with other models. Based on geochemical properties the Upper and Middle Velkerri Formation is classified into three categories: nonsource rocks, mature source rocks and immature source rock. They show significant differences in the well log responses, and different models had to be established for the three categories to determine the TOC content from well logs. Comparison of the results of using a different model for each category instead of a single model to cover the three categories shows that the former approach gives more meaningful answers.

Sign in / Sign up

Export Citation Format

Share Document