Total Organic Carbon Content Prediction Research Articles

New Method for Logging Evaluation of Total Organic Carbon Content in Shale Reservoirs Based on Time-Domain Convolutional Neural Network

Total organic carbon (TOC) content is a key indicator for determining the hydrocarbon content of shale. The current model for calculating the TOC content of shale is relatively simplistic, the modeling process is cumbersome, and the parameters involved are influenced by subjective factors, which have certain shortcomings. To address this problem, a time-domain convolutional neural network (TCN) model for predicting total organic carbon content based on logging sequence information was established by starting from logging sequence information, conducting logging parameter sensitivity analysis experiments, prioritizing logging-sensitive parameters as model feature vectors, and constructing a TCN network. Meanwhile, to overcome the problem of an insufficient sample size, a five-fold cross-validation method was used to train the TCN model and obtain the weight matrix with the minimum error, and then a shale reservoir TOC content prediction model based on the TCN model was established. The model was applied to evaluate the TOC logging of the Lianggaoshan Formation in the Sichuan Basin, China, and the predicted results were compared with the traditional ΔlogR model. The results indicate that the TCN model predicts the TOC content more accurately than the traditional model, as demonstrated by laboratory tests. This leads to a better application effect. Additionally, the model fully explores the relationship between the logging curve and the total organic carbon content, resulting in improved accuracy of the shale TOC logging evaluation.

Novel method for total organic carbon content prediction based on non-equigap multivariable grey model

Predicting total organic carbon content plays a crucial role in shale gas reservoir evaluation. To address multi-variable, imperfect logging data and non-equigap characteristics, this study developed a multi-variable grey derivative model for predicting the total organic carbon content trend. To begin with, the non-equigap factor is introduced and the parameter identification of the new model is established on the basis of least square method. Then, to reduce fluctuations in the original data, the weighted geometric average weakening operator is introduced. In addition, considering the system stability, the derivation method is used to calculate the time response formula of the model. Furthermore, two validation cases are provided to verify the validity of this novel model. Finally, the model is applied to the Fuling shale gas field in China for practical forecasting. Compared to other models, such as the grey model, statistical model, and artificial intelligence model, the proposed model achieved higher prediction accuracy in the three cases. Specifically, this model obtained 95.62%, 95.88% and 94.55% prediction accuracy for total organic carbon content. Results that the new model effectively addresses the limitations of previous studies that focus on single-parameter or equal spacing issues.

A deep encoder-decoder neural network model for total organic carbon content prediction from well logs

• This work proposed a deep encoder-decoder neural network (DEDNN) for predicting TOC contents. • The DEDNN model shows more accurate and sensitive than ΔLogR method and CNN method. • The DEDNN model can highlight the contribution of individual logging curve to the TOC prediction. Total organic carbon (TOC) content is an important geochemical parameter for evaluating the hydrocarbon generation potential of unconventional oil and gas resources. The TOC content of source rocks significantly affects the responses of well logs so, in principle, well logs can be used for source rock appraisal. However, the complex relationships between TOC content and well logs involve nonlinear mapping with many parameters. It is sometimes difficult to obtain continuous and accurate TOC content values using conventional methods such as the ΔLogR method. In this study, we propose a TOC prediction model using a deep encoder-decoder neural network (DEDNN) based on mining and mapping of multiscale features of logging curves. The prediction performance of the model is validated by a series of tests using data from four exploration wells in the Longmaxi black shale in the Dingshan area of the Sichuan Basin. The TOC content prediction results confirm that the proposed DEDNN is more accurate than either the ΔLogR method or CNN, which is a state-of-the-art convolutional neural network. Furthermore, a saliency map derived from the DEDNN results shows the relative importance of different well logs to TOC contents.

A Bayesian multivariate model using Hamiltonian Monte Carlo inference to estimate total organic carbon content in shale

The prediction of total organic carbon (TOC) content using geophysical logs is one of the key steps in shale reservoir characterization. Various empirical relations have previously been used for the estimation of TOC content from well-logs; however, uncertainty quantification in the model estimation is often ignored while performing TOC estimation in a deterministic framework. We introduce the problem of TOC estimation in a Bayesian setting with the goal of enhancing the TOC content prediction together with the quantification of the uncertainty in the model prediction. To signify the uncertainty, we draw random samples of model parameters from the posterior distribution by realizing multidimensional stochastic processes within the Hamiltonian Monte Carlo algorithm. The posterior model for the variables that influence TOC estimation is conditioned on the available well-log observations and is further defined by a priori and likelihood distributions. We demonstrate examples of applications of this approach to estimate the TOC content on two real field data sets from the well-known Devonian Duvernay shale of Western Canada and the Silurian shale of the Ahnet Basin. The accuracy in the estimation is arbitrated by comparing the prediction results with those obtained using the two most widely used empirical models. Corroborating the results by the laboratory-measured TOC contents demonstrate that the Bayesian approach offers a more reliable and better confidence in predictions when compared with the empirical models, as it provides additional information on the prediction uncertainty. Finally, the implications of the present approach are derived in terms of depositional environments to characterize the high TOC content zone in the studied organic shale formations.

Total organic carbon content logging prediction based on machine learning: A brief review

The total organic carbon content usually determines the hydrocarbon generation potential of a formation. A higher total organic carbon content often corresponds to a greater possibility of generating large amounts of oil or gas. Hence, accurately calculating the total organic carbon content in a formation is very important. Present research is focused on precisely calculating the total organic carbon content based on machine learning. At present, many machine learning methods, including backpropagation neural networks, support vector regression, random forests, extreme learning machines, and deep learning, are employed to evaluate the total organic carbon content. However, the principles and perspectives of various machine learning algorithms are quite different. This paper reviews the application of various machine learning algorithms to deal with total organic carbon content evaluation problems. Of various machine learning algorithms used for TOC content predication, two algorithms, the backpropagation neural network and support vector regression are the most commonly used, and the backpropagation neural network is sometimes combined with many other algorithms to achieve better results. Additionally, combining multiple algorithms or using deep learning to increase the number of network layers can further improve the total organic carbon content prediction. The prediction by backpropagation neural network may be better than that by support vector regression; nevertheless, using any type of machine learning algorithm improves the total organic carbon content prediction in a given research block. According to some published literature, the determination coefficient (R2) can be increased by up to 0.46 after using machine learning. Deep learning algorithms may be the next breakthrough direction that can significantly improve the prediction of the total organic carbon content. Evaluating the total organic carbon content based on machine learning is of great significance.

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

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 highlightsIn 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.

Total Organic Carbon Content Prediction in Lacustrine Shale Using Extreme Gradient Boosting Machine Learning Based on Bayesian Optimization

The total organic carbon (TOC) content is a critical parameter for estimating shale oil resources. However, common TOC prediction methods rely on empirical formulas, and their applicability varies widely from region to region. In this study, a novel data-driven Bayesian optimization extreme gradient boosting (XGBoost) model was proposed to predict the TOC content using wireline log data. The lacustrine shale in the Damintun Sag, Bohai Bay Basin, China, was used as a case study. Firstly, correlation analysis was used to analyze the relationship between the well logs and the core-measured TOC data. Based on the degree of correlation, six logging curves reflecting TOC content were selected to construct training dataset for machine learning. Then, the performance of the XGBoost model was tested using K -fold cross-validation, and the hyperparameters of the model were determined using a Bayesian optimization method to improve the search efficiency and reduce the uncertainty caused by the rule of thumb. Next, through the analysis of prediction errors, the coefficient of determination ( R 2 ) of the TOC content predicted by the XGBoost model and the core-measured TOC content reached 0.9135. The root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) were 0.63, 0.77, and 12.55%, respectively. In addition, five commonly used methods, namely, Δ log R method, random forest, support vector machine, K -nearest neighbors, and multiple linear regression, were used to predict the TOC content to confirm that the XGBoost model has higher prediction accuracy and better robustness. Finally, the proposed approach was applied to predict the TOC curves of 20 exploration wells in the Damintun Sag. We obtained quantitative contour maps of the TOC content of this block for the first time. The results of this study facilitate the rapid detection of the sweet spots of the lacustrine shale oil.

Machine Learning Method for TOC Prediction: Taking Wufeng and Longmaxi Shales in the Sichuan Basin, Southwest China as an Example

The total organic carbon content (TOC) is a core indicator for shale gas reservoir evaluations. Machine learning-based models can quickly and accurately predict TOC, which is of great significance for the production of shale gas. Based on conventional logs, the measured TOC values, and other data of 9 typical wells in the Jiaoshiba area of the Sichuan Basin, this paper performed a Bayesian linear regression and applied a random forest machine learning model to predict TOC values of the shale from the Wufeng Formation and the lower part of the Longmaxi Formation. The results showed that the TOC value prediction accuracy was improved by more than 50% by using the well-trained machine learning models compared with the traditionalΔLogRmethod in an overmature and tight shale. Using the halving random search cross-validation method to optimize hyperparameters can greatly improve the speed of building the model. Furthermore, excluding the factors that affect the log value other than the TOC and taking the corrected data as input data for training could improve the prediction accuracy of the random forest model by approximately 5%. Data can be easily updated with machine learning models, which is of primary importance for improving the efficiency of shale gas exploration and development.

Total organic carbon content prediction of source rocks with conventional well log data based on regression committee machine

Total organic carbon content prediction of source rocks with conventional well log data based on regression committee machine

Selective methods of TOC content estimation for organic-rich interbedded mudstone source rocks

The total organic carbon content (TOC) is one of the key parameters for evaluating the hydrocarbon generation potential of source rocks. Petroleum geochemists and geologists usually use conventional logging curves to predict TOC content in order to reduce the errors caused by limited TOC content data. The ΔlogR method is the most widely used TOC prediction method. However, it is not applicable to organic-rich mudstone interlayers, due to the rapidly changing lithology and the difficulty in determining a baseline. Some improved ΔlogR methods and artificial neural network techniques have also been proposed by previous authors. In this paper, a 3D surface fitting technique based on biharmonic interpolation is proposed to optimize an improved ΔlogR method. A total of 76 samples were divided into pure mudstone and mudstone interlayers. The correlation coefficient (R) and the root mean square error (RMSE) between the measured TOC and the predicted TOC obtained using the improved ΔlogR method, the artificial neural network method, and the 3D surface fitting method were calculated. These methods were applied to assess the source rocks of the Eocene Liushagang Formation in the Fushan Depression, South China Sea. The results show that the 3D surface fitting method can effectively distinguish source rocks from non-source rocks and has a higher accuracy, which makes it the most suitable method for assessing the TOC content of organic-rich source rocks with alternating mudstone layers.

TOC determination of Zhangjiatan shale of Yanchang formation, Ordos Basin, China, using support vector regression and well logs

Total organic carbon content (TOC) is an important parameter for shale gas resource evaluation. Among the existing TOC prediction methods, ΔlgR method is the most widely used. There are two main problems in this method: 1) assuming a linear relationship between ΔlgR and TOC; 2) manually determining the baseline and introducing human error. Due to the frequent alternating changes in the sedimentary environments of continental shale, the heterogeneity of it is strong. In this case, the relationship between well logs and TOC is complex and nonlinear, which leads to incorrect results for predicted TOC using ΔlgR method. The objective of this paper is to develop a new empirical method to determine the TOC of continental shale using support vector regression (SVR) based on grid search cross-validation. The optimized SVR method can fit the nonlinear relationships between log data and TOC well, and it is suitable for TOC estimation in strong heterogeneity case such as continental shale. Three hundred sixty-four measured TOC samples of Zhangjiatan shale and the corresponding GR, DEN, AC, U logs data were used to construct the SVR model. Compared with the ΔlgR method, the accuracy of the SVR model to calculate TOC is obviously higher.

Dynamic committee machine with fuzzy-c-means clustering for total organic carbon content prediction from wireline logs

The total organic carbon (TOC) content is of great significance to reflect the hydrocarbon-generation potential in shale reservoirs. The well logs were always used to predict the TOC content, but some linear regression methods do not match well with complex data. The neural network method can improve prediction accuracy, but it always generates unstable prediction models. A static committee machine can reduce errors and uncertainties by combining multiple learners, but the weight of integrating learners is difficult to determine. Therefore, a dynamic committee machine with fuzzy-c-means clustering (DCMF) was proposed to predict the TOC content. Experts in the DCMF include Elman neural network, extreme learning machine, and generalized regression neural network. The fuzzy-c-means clustering algorithm was used as the gate network to perform subtasks decomposition and weights calculation based on input data. The subtasks were used to train more adaptive TOC content prediction models, and the weights were transferred to the combiner to integrate all experts’ outputs into final results. The DCMF was applied in two wells located in the Jiumenchong formation in the Qiannan depression, China. The TOC prediction results using the DCMF method are more accurate than the linear regression method, three individual intelligent algorithms, and the static committee machine. The DCMF also provides a new method for weight calculation by mining potential information of input data.

TOC content prediction based on a combined Gaussian process regression model

Continuous total organic carbon (TOC) content estimation plays a crucial role in source rock reservoir evaluation. However, conventional prediction methods (e.g., empirical formulas or the δlogR method) have low prediction accuracy. Although machine learning algorithms possess a better prediction accuracy, they have also reached a bottleneck in this regard. Recently, ensemble learning and combined model prediction have achieved excellent results in many fields. In this study, a combined model was used for building a more accurate prediction model. Based on the theory that different formations correspond to different logging responses, we hypothesized that a Gaussian mixture model (GMM) classification of the logging data would be able to represent different geological conditions. Hence, we constructed independent Gaussian process regression (GPR) model based on the classified data; in particular, the posterior probability given by the GMM was used as a weight coefficient to combine the prediction results of all the independent GPR models. In addition, a confidence interval was obtained through the GPR to quantify the uncertainty of the prediction results. Finally, an error analysis showed that the combined-GPR model performed better than the δlogR method and other machine learning algorithms. In conclusion, the combined prediction model proposed in this study is reliable and effective, and it provides a new solution for quantitative prediction problems in corresponding fields.

Feature Selection-Based Artificial Intelligence Techniques for Estimating Total Organic Carbon from Well Logs

For shale oil and gas exploration total organic carbon (TOC) is the significant factors where TOC estimation considered as a challenges for geological engineers because direct laboratory coring analysis is costly and time consuming. Passey method and Artificial Intelligence (AI) technique have used on well logs extensively to determine TOC content. But, the prediction of Passey method is low and AI technique such as ANN, Support Vector Machine (SVM) trapped in local optima, overfitting and heavy computation work or error if the technique isn’t reasonable. In this paper, for the first time in TOC prediction we propose three feature selection-based algorithm which are Decision Tree (DT), Gradient Boosting Regressor (GBR) and Random Forest (RF) respectively. This feature selection-based algorithm select the best attributes among the input parameters for TOC content prediction. Then those best attributes works as an input for AI models for training and testing the AI models which illustrates that making a correlation between well logs and TOC content for the prediction. Specifically, 2069 core shale sample and well logging sample data of the Texas University Lands of Kansas Geologic Society were divided into 1448 training sample and 621 validating sample to evaluate the proposed AI models. This proposed AI model and feature selection-based algorithm jointly allows TOC content to be accurately and continuously predicted based on conventional well logs.

A new and reliable dual model- and data-driven TOC prediction concept: A TOC logging evaluation method using multiple overlapping methods integrated with semi-supervised deep learning

The total organic carbon content (TOC) is the most important parameter when determining the source rock quality. At present, there are two main types of TOC well logging calculation methods: model-driven and data-driven methods. However, research on the these two types of methods has slowed over the past ten years, and the ongoing research is very limited; thus, it is difficult to improve the TOC calculation accuracy. This paper analyses the advantages and disadvantages of current methods and proposes a new model- and data-driven TOC prediction concept to improve the TOC prediction accuracy. The proposed concept takes the curve obtained with the overlap method as an input instead of using a conventional log curve; we believe that deep learning is best suited to accomplish this task. We propose a new integrated semi-supervised deep learning network—the integrated deep semi-supervised ladder network (IDLN) algorithm—for small-sample well logging interpretation problems based on the proposed approach. A two-step method consisting of intelligent curve overlapping and automatic TOC prediction is employed to better interpret logging data and core data; this method can predict the TOC without manually overlapping curves. Testing the data from 12 wells in 3 blocks revealed that the proposed concept and IDLN algorithm greatly improve the TOC prediction accuracy, and the mean square error was reduced by more than 50%. The new method is also more reasonable for locating non-reservoir segments. Moreover, this novel approach can further enhance the TOC prediction accuracy and may even constitute a new research direction for improving the existing logging interpretation theory. These novel principles can ultimately help evaluate source rock reservoirs.

Total organic carbon content prediction based on support-vector-regression machine with particle swarm optimization

Total organic carbon (TOC) is a significant factor to evaluate the hydrocarbon potential of the unconventional reservoir, while it is difficult to obtain the continuous and accurate prediction result of TOC by traditional methods due to the non-linear relationship between TOC content and wireline log data. However, support vector regress machine is an efficient supervised learning artificial intelligence algorithm, and performs well to deal with non-linear relationship dataset. Therefore, in order to explore a more efficient way for TOC content prediction, the support vector regress machine was tried to predict TOC content through wireline log data. To further verify this, some data tests have been conducted on an offshore exploration prior well data in the northern of Beibu Gulf Basin. After analyzing various kernel functions and optimization methods by cross-validation and error analysis, it can be indicated that the Gaussian kernel function and the particle swarm optimization (PSO) algorithm which used the linear decreasing inertia coefficient and mutated particles are suitable for SVR model and model parameter selection, respectively. Finally, the prediction result of SVR with the best model and model parameters is compared with the results of an improved ΔlogR method and multilayer perceptron method. The comparison results show that SVR has a higher correlation coefficient than other methods. In conclusion, the prediction result of SVR can be thought of as an efficient and reliable method for TOC content prediction. Through the continuous prediction of organic carbon content, the qualitative and quantitative evaluation of high-quality source rocks in this area can be realized, which is of great practical significance for determining the exploration field and the search for favorable target reservoirs.

Mathematical modeling for total organic carbon content prediction with logging parameters by neural networks: A case study of shale gas well in South China

The lower Cambrian Niutitang Formation in northwestern Hunan, South China, has already reached its high or over matured stage and is formed with hydrothermal activity and deposition. Thus, it is extremely difficult to predict the total organic carbon (TOC) content accurately by common methods with well-logging data. To solve this problem, we use artificial neural networks for predicting the TOC of the black shales in our study case. We got the input vectors through principal component analysis and based on the relationships and the logging response mechanism between TOC and logging data. In the back-propagation algorithm, some important parameters including the sample databases, the number of hidden layer nodes, transfer function, and weight value adjustment were all optimized correctly in the networks. Then, we built the mathematical model through a large number of learning sample datum and the error function between the actual and expected outputs, and we found that the results are good according to many performance indicators. In testing samples, mean absolute and relative errors are all reduced probably due to the datum ranges and features being focused, but the accuracy also drops when the numbers of participating samples are reduced. Through redefining the [Formula: see text] sample database, we gained more accurate values for the high-TOC source rock. Finally, we think that the results suggest that the method is suitable for shale gas resource exploration under similar geologic conditions and data characteristics.

A novel approach to total organic carbon content prediction in shale gas reservoirs with well logs data, Tonghua Basin, China

As a geochemical parameter for characterizing source rock in shale gas reservoirs, estimation of total organic carbon (TOC) is a main task of geophysical and geochemical studies. TOC can be used to evaluate the hydrocarbon generation potential of source rocks. Artificial intelligence (AI) methods have been proposed recently to obtain TOC from well logs. This avoids expensive and time-consuming core analysis of geochemical experiments. However, the optimal combination (selected) of logs should be determined to get the highest accuracy TOC. We used a well-trained least square support vector machine model to select appropriate well log inputs for intelligent model based on mean impact values. We used a conventional 9 logs obtained from a shale gas well in Tonghua Basin, China, to test our method. The results were compared with 215 TOC values from core analysis. In addition, we tested three AI of models, including artificial neural network based on backpropagation algorithm (ANN-BP), least square support vector machine (LSSVM), and particle swarm optimization-least square support vector machine (PSO-LSSVM). For these three models, both selected logs and all logs are used for comparison. The TOC results, obtained from different calculations, showed that selected logs significantly improved the TOC accuracy in each AI model. By comparing different AI model, we found that PSO-LSSVM model outperforms the other two models. The TOC obtained from the PSO-LSSVM can benchmark with core analysis results.

Prediction of total organic carbon content in shale reservoir based on a new integrated hybrid neural network and conventional well logging curves

There is increasing interest in shale gas reservoirs due to their abundant reserves. As a key evaluation criterion, the total organic carbon content (TOC) of the reservoirs can reflect its hydrocarbon generation potential. The existing TOC calculation model is not very accurate and there is still the possibility for improvement. In this paper, an integrated hybrid neural network (IHNN) model is proposed for predicting the TOC. This is based on the fact that the TOC information on the low TOC reservoir, where the TOC is easy to evaluate, comes from a prediction problem, which is the inherent problem of the existing algorithm. By comparing the prediction models established in 132 rock samples in the shale gas reservoir within the Jiaoshiba area, it can be seen that the accuracy of the proposed IHNN model is much higher than that of the other prediction models. The mean square error of the samples, which were not joined to the established models, was reduced from 0.586 to 0.442. The results show that TOC prediction is easier after logging prediction has been improved. Furthermore, this paper puts forward the next research direction of the prediction model. The IHNN algorithm can help evaluate the TOC of a shale gas reservoir.

Geophysical Prediction Technology Based on Organic Carbon Content in Source Rocks of the Huizhou Sag, the South China Sea

Abstract Due to the high exploration cost, limited number of wells for source rocks drilling and scarce test samples for the Total Organic Carbon Content (TOC) in the Huizhou sag, the TOC prediction of source rocks in this area and the assessment of resource potentials of the basin are faced with great challenges. In the study of TOC prediction, predecessors usually adopted the logging assessment method, since the data is only confined to a “point” and the regional prediction of the source bed in the seismic profile largely depends on the recognition of seismic facies, making it difficult to quantify TOC. In this study, we combined source rock geological characteristics, logging and seismic response and built the mathematical relation between quasi TOC curve and seismic data based on the TOC logging date of a single well and its internal seismic attribute. The result suggested that it was not purely a linear relationship that was adhered to by predecessors, but was shown as a complicated non-linear relationship. Therefore, the neural network algorithm and SVMs were introduced to obtain the optimum relationship between the quasi TOC curve and the seismic attribute. Then the goal of TOC prediction can be realized with the method of seismic inversion.