Total Organic Carbon Prediction Research Articles

Enhancing machine learning models for total organic carbon prediction by integrating geospatial parameters in river watersheds

This study utilizes machine learning (ML) algorithms to develop a robust total organic carbon (TOC) prediction model for river waters in the Geumho River sub-basins, South Korea, considering both non-rain and rain events. The model incorporates geospatial parameters such as land use, slope, flow rate, and basic water quality metrics including biochemical oxygen demand (BOD), chemical oxygen demand (COD), total nitrogen (TN), total phosphorus (TP), and suspended solids (SS). A key aspect of this research is examining how land use information enhances the model's predictive accuracy. We compared two ML algorithms—extreme gradient boosting (XGBoost) and deep neural networks (DNN)—with a traditional multiple linear regression (MLR) approach. XGBoost outperformed the others, achieving an R2 value between 0.61 and 0.68 in the test dataset and demonstrating significant improvement during rain events with an R2 of 0.77 when including land use data. In contrast, this enhancement was not observed with the MLR model. Feature importance analysis using Shapley values highlighted COD as the primary predictor for non-rain events, while during rain events, COD, TP, TN, SS and agricultural land collectively influenced TOC levels. This study significantly advances understanding of TOC variability across different land use scenarios in river systems and underscores the importance of integrating geospatial and water quality parameters to enhance TOC prediction, particularly during rain events. This methodology provides a valuable framework for developing river management strategies and monitoring long-term TOC trends, especially in scenarios with gaps in essential monitoring data.

Geophysical prediction of organic matter abundance in source rocks based on geochemical analysis: A case study of southwestern Bozhong Sag, Bohai Sea, China

The Bozhong Sag is the largest petroliferous sag in the Bohai Bay Basin, and the source rocks of Paleogene Dongying and Shahejie Formations were buried deeply. Most of the drillings were located at the structural high, and there were few wells that met good quality source rocks, so it is difficult to evaluate the source rocks in the study area precisely by geochemical analysis only. Based on the Rock-Eval pyrolysis, total organic carbon (TOC) testing, the organic matter (OM) abundance of Paleogene source rocks in the southwestern Bozhong Sag were evaluated, including the lower of second member of Dongying Formation (E3d2L), the third member of Dongying Formation (E3d3), the first and second members of Shahejie Formation (E2s1+2), the third member of Shahejie Formation (E2s3). The results indicate that the E2s1+2 and E2s3 have better hydrocarbon generative potentials with the highest OM abundance, the E3d3 are of the second good quality, and the E3d2L have poor to fair hydrocarbon generative potential. Furthermore, the well logs were applied to predict TOC and residual hydrocarbon generation potential (S2) based on the sedimentary facies classification, using ΔlogR, generalized ΔlogR, logging multiple linear regression and BP neural network methods. The various methods were compared, and the BP neural network method have relatively better prediction accuracy. Based on the pre-stack simultaneous inversion (P-wave impedance, P-wave velocity and density inversion results) and the post-stack seismic attributes, the three-dimensional (3D) seismic prediction of TOC and S2 was carried out. The results show that the seismic near well prediction results of TOC and S2 based on seismic multi-attributes analysis correspond well with the results of well logging methods, and the plane prediction results are identical with the sedimentary facies map in the study area. The TOC and S2 values of E2s1+2 and E2s3 are higher than those in E3d3 and E3d2L, basically consistent with the geochemical analysis results. This method makes up the deficiency of geochemical methods, establishing the connection between geophysical information and geochemical data, and it is helpful to the 3D quantitative prediction and the evaluation of high-quality source rocks in the areas where the drillings are limited.

Source Rock Evaluation of Hydrocarbons in Deep-Water Offshore Areas Based on a BP Neural Network

Due to the lack of drilling data and poor quality of seismic data in deep-water offshore areas, conventional methods cannot effectively predict the total organic carbon (TOC) content. In this paper, the BP neural network method is used to predict the TOC of the strata overlying the target layer, which adds to the TOC information in the study area. Then, the highest TOC value of the strata overlying the target layer is used to select the most sensitive seismic attributes. Finally, the sensitive seismic attributes are used to evaluate the source rocks with no or few wells. A set of TOC prediction technology flows is established for TOC combined with seismic attributes under the condition of no wells and few wells in deep-water areas. The application example shows the reliability of TOC prediction by this technical process, and the study has a certain reference significance for the evaluation of hydrocarbon source rocks in offshore deep water.

A data-driven method for total organic carbon prediction based on random forests

The total organic carbon (TOC) is an important parameter for shale gas reservoir exploration. Currently, predicting TOC using seismic elastic properties is challenging and of great uncertainty. The inverse relationship, which acts as a bridge between TOC and elastic properties, is required to be established correctly. Machine learning especially for Random Forests (RF) provides a new potential. The RF-based supervised method is limited in the prediction of TOC because it requires large amounts of feature variables and is very onerous and experience-dependent to derive effective feature variables from real seismic data. To address this issue, we propose to use the extended elastic impedance to automatically generate 222 extended elastic properties as the feature variables for RF predictor training. In addition, the synthetic minority oversampling technique is used to overcome the problem of RF training with imbalanced samples. With the help of variable importance measures, the feature variables that are important for TOC prediction can be preferentially selected and the redundancy of the input data can be reduced. The RF predictor is finally trained well for TOC prediction. The method is applied to a real dataset acquired over a shale gas study area located in southwest China. Examples illustrate the role of extended variables on improving TOC prediction and increasing the generalization of RF in prediction of other petrophysical properties.

Integrated well-log data and seismic inversion results for prediction of hydrocarbon source rock distribution in W segment, Pearl River Mouth Basin, China

Hydrocarbon source rocks possess a high concentration of organic matter and can generate significant quantities of hydrocarbons, which are integral components within hydrocarbon systems. It is critical for well deployment and hydrocarbon production enhancement to accurately anticipate the geographical dispersion of hydrocarbon source rocks in hydrocarbon-bearing basins. Total Organic Carbon (TOC) serves as a pivotal metric for assessing hydrocarbon source rocks, enabling the estimation of their spatial distribution through TOC prediction. In this study, we present a Machine Learning-based process for predicting the distribution of hydrocarbon source rocks, utilizing well-log data and seismic inversion results. Based on the TOC value of the well curve, the hydrocarbon source rock quality is divided into four categories: normal, medium, good, and excellent. We identify the sensitive parameters governing hydrocarbon source rock quality through cross-plot and correlation analysis. Machine Learning will predict the spatial distribution of hydrocarbon source rock by establishing a relationship between hydrocarbon source rock quality and sensitive parameters. The prediction results are evaluated by comparing the performance of Random Forest, Gradient Boosting Decision Tree (GBDT), eXtreme Gradient Boosting tree (XGBoost), and Histogram-Based Gradient Boosting Decision Tree (HGBDT) using confusion matrix and ROC curve. The findings consistently demonstrate that HGBDT exhibits superior prediction capability, accurately anticipating the spatial distribution of hydrocarbon source rocks. The prediction outcomes align well with the depositional properties of the research area and demonstrate excellent agreement with the well data.

An approach for total organic carbon prediction using convolutional neural networks optimized by differential evolution

An approach for total organic carbon prediction using convolutional neural networks optimized by differential evolution

Super learner approach to predict total organic carbon using stacking machine learning models based on well logs

Determining the total organic carbon (TOC) content is essential information for risk assessment in oil exploration, as it is a parameter used for the characterization of hydrocarbon-generating rocks, considering that intervals rich in organic matter are the basic requirements for oil and gas accumulation. However, the determination of TOC can be costly, demanding destructive tests in samples from the source rock, expensive laboratory machinery, and specialized personnel. In this context, one notes the necessity of the computational methods to bypass those problems and that machine learning models emerge as an option. One approach to integrating machine learning methods improves performance and, consequently, the prediction quality is stacking models. This paper presents a super learner strategy, based on stacking approaches, as a surrogate model for TOC modeling. The super-learner has three levels in this structure containing different types of learners (machine learning methods), where two stack models from the first two levels. The following machine learning models were used in the building of super learner the K-Neighbors Nearest (KNN), Linear Regression (LR), Multi-layer Perceptron Neural Network (MLP), Random Forest (RF), Ridge Regression (RR), and Support Vector Regression (SVR). The proposed model was compared with standalone machine learning models and other canonical stacking models. The resulting super learner stacking model attained the best average performance for the TOC modeling (R = 0.897, R2 = 0.80, RMSE = 1.16, MAE = 0.93, and MAPE = 28.30%). The proposed approach produces an alternative data-driven efficient model for TOC prediction, resulting in reliable automated technology to assist oil and gas well management and decision-making.

Predicting total organic carbon from few well logs aided by well-log attributes

Derivative/volatility well-log attributes from very few commonly recorded well logs can assist in the prediction of total organic carbon (TOC) in shales and tight formations. This is of value where only limited suites of well logs are recorded, and few laboratory measurements of TOC are conducted on rock samples. Data from two Lower-Barnett-Shale (LBS) wells (USA), including well logs and core analysis is considered. It demonstrates how well-log attributes can be exploited with machine learning (ML) to generate accurate TOC predictions. Six attributes are calculated for gamma-ray (GR), bulk-density (PB) and compressional-sonic (DT) logs. Used in combination with just one of those recorded logs, those attributes deliver more accurate TOC predictions with ML models than using all three recorded logs. When used in combination with two or three of the recorded logs, the attributes generate TOC prediction accuracy comparable with ML models using five recorded well logs. Multi-K-fold-cross-validation analysis reveals that the K-nearest-neighbour algorithm yields the most accurate TOC predictions for the LBS dataset. The extreme-gradient-boosting (XGB) algorithm also performs well. XGB is able to provide information about the relative importance of each well-log attribute used as an input variable. This facilitates feature selection making it possible to reduce the number of attributes required to generate accurate TOC predictions from just two or three recorded well logs.

TOC prediction and grading evaluation based on variable coefficient △logR method and its application for unconventional exploration targets in Songliao Basin

The prediction of total organic carbon (TOC) content and grading evaluation of shale formation are very much significant and essential for reservoir description of rolling exploration and development in the new shale exploration area (Shuangcheng) in Songliao basin, China. In order to improve exploration efficiency and obtain continuous TOC content curve of wells, the variable coefficient △logR technique was developed for TOC estimating which is based on the two of acoustic time difference and deep lateral resistivity logging curve and the variable scale coefficient (K) between them as well as another scale coefficient (A) between TOC and △logR. A prediction model of TOC was established for the well which TOC is measured by evaluation of side wall cores, then apply it to other wells to verify the reliability of the model. The application result of eleven exploration Wells in Shuangcheng area show that the TOC of shale is linearly correlated with △logR, and the maximum prediction accuracy k value varies with wells, so it is necessary to determine the undetermined coefficient k according to a single well, but the A value having no big change from one well to another in similar sedimentary facies and thermal evolution degree of shale. The average relative error of TOC between prediction model and core measurement is 10.6% which verifies the accuracy of this method. On this basis of TOC prediction, we establish shale grading evaluation criteria for the study area. In the establishment process, not only the relationship between TOC and S1, but also vitrinite reflectance (Ro) are considered. The shale in Shuangcheng area can be divided into three types (Class I: TOC > 3.5% and Ro > 0.9%; Class II: TOC 2%–3.5% and Ro > 0.9; Class III: TOC < 2% or Ro < 0.9%), and achieved shale classification on the well profile with TOC and Ro which are easy to predict and reliable. According to the relationship between the thickness of shale of disparate classes and the total thickness of shale in different zones, the thickness of shale of disparate classes in each well is predicted.

Rock physics and seismic reflectivity parameterization and amplitude variation with offsets inversion in terms of total organic carbon indicator

Total organic carbon (TOC) prediction with elastic parameter inversions has been widely used in the identification and evaluation of source rocks. However, the elastic parameters used to predict TOC are not only determined by TOC but also depend on the other physical properties of source rocks. Besides, the TOC prediction with the elastic parameters inversion is an indirect method based on the statistical relationship obtained from well logs and experiment data. Therefore, we propose a rock physics model and define a TOC indicator mainly affected by TOC to predict TOC directly. The proposed rock physics model makes the equivalent elastic moduli of source rocks parameterized by the TOC indicator. Combining the equivalent elastic moduli of source rocks and Gray’s approximation leads to a novel linearized approximation of the P-wave reflection coefficient incorporating the TOC indicator. Model examples illustrate that the novel reflectivity approximation well agrees with the exact Zoeppritz equation until incident angles reach 40°. Convoluting the novel P-wave reflection approximation with seismic wavelets as the forward solver, an AVO inversion method based on the Bayesian theory is proposed to invert the TOC indicator with seismic data. The synthetic examples and field tests validate the feasibility and stability of the proposed AVO inversion approach. Using the inversion results of the TOC indicator, TOC is directly and accurately estimated in the target area.

Prediction of total organic carbon and E. coli in rivers within the Milwaukee River basin using machine learning methods

Ensemble-hybrid ML models can explain and predict the variability in water quality parameters and living microorganism behavior in natural streams with satisfactory prediction accuracies based on specific physicochemical parameters.

Total organic carbon estimation in seagrass beds in Tauranga Harbour, New Zealand using multi-sensors imagery and grey wolf optimization

Estimation of carbon stock in seagrass meadows is in challenges of paucity of assessment and low accuracy of the estimates. In this study, we used a fusion of the synthetic aperture radar (SAR) Sentinel-1 (S-1), the multi-spectral Sentinel-2 (S-2), and coupled this with advanced machine learning (ML) models and meta-heuristic optimization to improve the estimation of total organic carbon (TOC) stock in the Zostera muelleri meadows in Tauranga Harbour, New Zealand. Five scenarios containing combinations of data, ML models (Random Forest, Extreme Gradient Boost, Rotation Forest, CatBoost) and optimization were developed and evaluated for TOC retrieval. Results indicate a fusion of S1, S2 images, a novel ML model CatBoost and the grey wolf optimization algorithm (the CB-GWO model) yielded the best prediction of seagrass TOC (R 2, RMSE were 0.738 and 10.64 Mg C ha−1). Our results provide novel ideas of deriving a low-cost, scalable and reliable estimates of seagrass TOC globally.

TOC prediction using a gradient boosting decision tree method: A case study of shale reservoirs in Qinshui Basin

Shale oil and shale gas are important unconventional resources. As the total organic carbon (TOC) of shales is related to the generation potentiality of hydrocarbons, accurate TOC prediction models can improve development efficiency and reduce cost. However, there has been little work on intelligent prediction of TOC. This study focused on hydrocarbon-rich shale from the Linfen area of Qinshui Basin in China. Multiple regression analysis (MRA), ΔlgR, back propagation (BP) neural network, gradient boosting decision tree (GBDT) were selected to predict the TOC of the studied shale reservoirs using density (DEN), uranium (U), acoustic (AC), and resistivity (RT) logs. The predicted TOC was compared with the geochemical-measured TOC. To fairly evaluate these models, the correlation of determination (R2), root-mean-square-error (RMSE) and three-scale analytic hierarchy process (TAHP) were introduced. The results show that MRA, ΔlgR, and BP methods gave low R2, high RMSE values, and low total weight, indicating these methods poorly predicted TOC. These models significantly underestimate the TOC, resulting in evident deviations between the predicted TOC and their real values. In contrast, GBDT provided accurate TOC prediction, with values of R2, RMSE, and total weight of 0.9254, 0.032 and 0.42. The GBDT model can greatly outperform other models by extracting complex relationships between well log data and TOC values. Sensitivity analysis of the GBDT model revealed that the U parameter exhibited the greatest impact on TOC prediction. The results of this work show that the GBDT model is well suited for TOC prediction of unconventional resources.

Prediction of TOC in Lishui–Jiaojiang Sag Using Geochemical Analysis, Well Logs, and Machine Learning

Total organic carbon (TOC) is important geochemical data for evaluating the hydrocarbon generation potential of source rocks. TOC is commonly measured experimentally using cutting and core samples. The coring process and experimentation are always expensive and time-consuming. In this study, we evaluated the use of three machine learning (ML) models and two multiple regression models to predict TOC based on well logs. The well logs involved gamma rays (GR), deep resistivity (RT), density (DEN), acoustic waves (AC), and neutrons (CN). The ML models were developed based on random forest (RF), extreme learning machine (ELM), and back propagation neural network (BPNN). The source rock of Paleocene Yueguifeng Formation in Lishui–Jiaojiang Sag was taken as a case study. The number of TOC measurements used for training and testing were 50 and 27. All well logs and selected well logs (including AC, CN, and DEN) were used as inputs, respectively, for comparison. The performance of each model has been evaluated using different factors, including R2, MAE, MSE, and RMSE. The results suggest that using all well logs as input improved the TOC prediction accuracy, and the error was reduced by more than 30%. The accuracy comparison of ML and multiple regression models indicated the BPNN was the best, followed by RF and then multiple regression. The worst performance was observed in the ELM models. Considering the running time, the BPNN model has higher prediction accuracy but longer running time in small-sample regression prediction. The RF model can run faster while ensuring a certain prediction accuracy. This study confirmed the ability of ML models for estimating TOC using well logs data in the study area.

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.

Unsupervised contrastive learning for few-shot TOC prediction and application

Total organic carbon (TOC) content is significant for “sweet spots” prediction and resource calculation. Traditional physical methods and machine learning methods, however, only use labeled samples (core TOC samples and well logging data) to predict TOC, resulting in a performance bottleneck. Meanwhile, many oilfields have considerable unlabeled data (well logging data). Therefore, this paper proposed a pretrain-and-finetune few-shot learning framework, called Contrastive Learning-Convolutional Neural Network (CL-CNN), to predict TOC using unlabeled data. CL has been a research hotspot in unsupervised learning in recent years, with the principle of reducing the distance between similar samples and increasing the distance between different samples in the feature space. CNN is distinguished by its strong generalization ability and high prediction accuracy, as well as its local connectivity and weight sharing. The CL-CNN model first uses CL to pretrain the initial parameters of the CNN model on a large number of unlabeled datasets and then finetunes the resultant CNN model using the labeled data. The framework combines the advantages of CL and CNN to further improve the prediction accuracy and generalization ability. The proposed method was applied to predict the TOC of shale gas in the Sichuan Basin, China, using 121 core samples and 1224 well logging data from the JY 10 well (121 logging data for supervised learning and 1103 logging data for unsupervised learning). Besides, JY 10–10 well data were used to validate the CL-CNN model. Experimental results demonstrated that the CL-CNN model outperformed many machine learning methods, including the support vector machine (SVM), Gaussian process regression (GPR), random forest (RF), and CNN models, indicating the feasibility and effectiveness of the proposed method. Because of this, the CL-CNN model can also be used as a general prediction tool for reservoir parameters such as porosity and permeability.

An ensemble deep neural network approach for predicting TOC concentration in lakes along the middle-lower reaches of Yangtze River

In recent years, lakes pollution has become increasingly serious, so water quality monitoring is becoming increasingly important. The concentration of total organic carbon (TOC) in lakes is an important indicator for monitoring the emission of organic pollutants. Therefore, it is of great significance to determine the TOC concentration in lakes. In this paper, the water quality dataset of the middle and lower reaches of the Yangtze River is obtained, and then the temperature, transparency, pH value, dissolved oxygen, conductivity, chlorophyll and ammonia nitrogen content are taken as the impact factors, and the stacking of different epochs’ deep neural networks (SDE-DNN) model is constructed to predict the TOC concentration in water. Five deep neural networks and linear regression are integrated into a strong prediction model by the stacking ensemble method. The experimental results show the prediction performance, the Nash-Sutcliffe efficiency coefficient (NSE) is 0.5312, the mean absolute error (MAE) is 0.2108 mg/L, the symmetric mean absolute percentage error (SMAPE) is 43.92%, and the root mean squared error (RMSE) is 0.3064 mg/L. The model has good prediction performance for the TOC concentration in water. Compared with the common machine learning models, traditional ensemble learning models and existing TOC prediction methods, the prediction error of this model is lower, and it is more suitable for predicting the TOC concentration. The model can use a wireless sensor network to obtain water quality data, thus predicting the TOC concentration of lakes in real time, reducing the cost of manual testing, and improving the detection efficiency.

Evaluation of Source Rock Potentiality and Prediction of Total Organic Carbon Using Well Log Data and Integrated Methods of Multivariate Analysis, Machine Learning, and Geochemical Analysis

Evaluation of Source Rock Potentiality and Prediction of Total Organic Carbon Using Well Log Data and Integrated Methods of Multivariate Analysis, Machine Learning, and Geochemical Analysis

Ensemble Learning for Predicting TOC from Well-Logs of the Unconventional Goldwyer Shale

Precise estimation of total organic carbon (TOC) is extremely important for the successful characterization of an unconventional shale reservoir. Indirect traditional continuous TOC prediction methods from well-logs fail to provide accurate TOC in complex and heterogeneous shale reservoirs. A workflow is proposed to predict a continuous TOC profile from well-logs through various ensemble learning regression models in the Goldwyer shale formation of the Canning Basin, WA. A total of 283 TOC data points from ten wells is available from the Rock-Eval analysis of the core specimen where each sample point contains three to five petrophysical logs. The core TOC varies largely, ranging from 0.16 wt % to 4.47 wt % with an average of 1.20 wt %. In addition to the conventional MLR method, four supervised machine learning methods, i.e., ANN, RF, SVM, and GB are trained, validated, and tested for continuous TOC prediction using the ensemble learning approach. To ensure robust TOC prediction, an aggregated model predictor is designed by combining the four ensemble-based models. The model achieved estimation accuracy with R2 value of 87%. Careful data preparation and feature selection, reconstruction of corrupted or missing logs, and the ensemble learning implementation and optimization have improved TOC prediction accuracy significantly compared to a single model approach.