Total organic carbon (TOC) quantification using artificial neural networks: Improved prediction by leveraging XRF data

Chan, Septriandi A.; Hassan, Amjed; Usman, Muhammad; Humphrey, John; Alzayer, Yaser; Duque, Fabian

doi:10.1016/j.petrol.2021.109302

Cited by 12 publications

(16 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, unconventional hydrocarbon production from shale source rocks has gained a vast interest in the oil and gas industry. Such interest is attributed to the depletion of conventional resources and the advancements in directional drilling and hydraulic fracturing. − The total organic carbon (TOC) content is one of the very important petrophysical properties that indicate the quality of source rocks. TOC represents the amount of organic matter deposited in the rock and is one of the most critical parameters to investigate prior to drilling for its significance in hydrocarbon quantification and quality measurement of the resource. ,− Organic matter depositions are controlled by the primary production, destruction, and dilution of organic matter where it maximizes when the first is fairly greater than the latter two factors .…”

Section: Introductionmentioning

confidence: 99%

“…However, they incur prohibitively high costs and cannot be used conventionally, hence requiring new robust and more convenient methods for TOC quantification . Artificial intelligence (AI) has been considerably used in the last few years in oil and gas research, and much work has been made on the prediction of TOC based on core and well log data. ,− In most cases, AI methods are not globally applicable due to the heterogeneity of shales, which indicates the cruciality of studying the nature of the targeted fields and picking proper logs for the model. , Huang et al demonstrated one of the early applications of AI in predicting TOC using only three conventional (gamma ray, resistivity, and sonic) logs as an input and a pseudo-TOC log calculated from an empirical correlation following the Passey et al approaches . Subsequently, conventional logs have been fed as inputs, that is, gamma ray log, density log, acoustic log, deep and medium resistivity logs, and porosity log in addition to uranium (U), thorium (Th), and potassium (K) contents. − X-ray fluorescence elements’ data (such as copper and nickel) and thermal neutron porosity as well as conventional log combinations displayed correlation with the TOC in the investigated environment − and were proofing evidence of AI reliability in predicting TOC.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Total Organic Carbon in Organic-Rich Shale Rocks Using Thermal Neutron Parameters

et al. 2023

View full text Add to dashboard Cite

Total organic carbon (TOC) content is one of the crucial parameters that determine the value of the source rock. The TOC content gives important indications about the source rocks and hydrocarbon volume. Various techniques have been utilized for TOC quantification, either by geochemical analysis of source rocks in laboratories or using well logs to develop mathematical correlations and advanced machine learning models. Laboratory methods require intense sampling intervals to have an accurate understanding of the reservoir, and depending on the thickness of the interested formation, it can be time-consuming and costly. Empirical correlations based on well logs (e.g., density, sonic, gamma ray, and resistivity) showed fast predictions and very reasonable accuracies. However, other important parameters such as thermal neutron logs have not been studied yet as a potential input for providing reliable TOC predictions. Also, different studies estimate the TOC based on the well-logging data for various formations; however, limited studies were reported to predict the TOC for the Horn River Formation. Therefore, the objective of this study is to estimate the TOC variations based on the thermal neutron logs using one of the largest source rocks in Canada: The Horn River Formation. More than 150 data sets were collected and used in this work. The parameters of the artificial neural network (ANN) model were fine-tuned in order to improve the model’s prediction performance. Furthermore, an empirical correlation was developed utilizing the optimized ANN model to allow fast and direct application for the developed model. The developed correlation can predict the TOC with an average absolute error of 0.52 wt %. The proposed TOC model was able to outperform the previous models, and the coefficient of determination was increased from 0.28 to 0.73. Overall, the proposed TOC model can provide high accuracy for TOC ranges from 0.3 to 6.44 wt %. The developed model can provide a real-time quantification for the organic matter maturity, helping to allocate the zones of mature organic matter within the drilled formations.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prediction of Total Organic Carbon in Organic-Rich Shale Rocks Using Thermal Neutron Parameters

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Laboratory core test and analysis technology is the most direct and accurate means to obtain the organic matter content of shale, in which total organic carbon content (TOC) is the most readily available and commonly used characterization index of organic matter content. Restricted by the lack of core data or incomplete coring in most wells, the interpretation of formation TOC with high resolution and high coverage logging data is an important means for rapid, accurate and continuous quantitative evaluation of organic matter content in shale formations (Yu et al, 2017;Wang et al, 2019;Liang et al, 2021;Chan et al, 2022;Meng et al, 2022;Zhao et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

“…Different from the model-driven method, the data-driven method can fully explore the statistical relationship between multi-logging response characteristics and TOC, which is more suitable for TOC interpretation of strongly heterogeneous shale (Huang and Williamson, 1996). Currently, a large number of data mining algorithms have been applied to TOC logging interpretation, including multiple linear regression, Gaussian mixture, optimization algorithm, SVM, BP neural network, deep neural network, etc., (Mendelzon and Roksoz, 1985;Huang and Williamson, 1996;Wang et al, 2014;Tan et al, 2015;Yu et al, 2017;Zhu et al, 2020;Zheng et al, 2021;Chan et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

“…In all data-driven TOC interpretation methods, the goal is to minimize the difference between the predicted value and the true value of the expected value (such as MSE and RMSE, etc.) (Huang and Williamson, 1996;Wang et al, 2014;Tan et al, 2015;Yu et al, 2017;Zhu et al, 2020;Zheng et al, 2021;Chan et al, 2022), which is the most direct indicator of learning algorithms in model training and performance verification. However, TOC test samples are often sampled by equidistant or random methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

TOC interpretation of lithofacies-based categorical regression model: A case study of the Yanchang formation shale in the Ordos basin, NW China

Yin

Gao²,

Cheng³

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

In this paper, taking the shale of Chang 7-Chang 9 oil formation in Yanchang Formation in the southeastern Ordos Basin as an example, through the study of shale heterogeneity characteristics, starting from the preprocessing of supervision data set, a logging interpretation method of total organic carbon content (TOC) on the lithofacies-based Categorical regression model (LBCRM) is proposed. It is show that: 1) Based on core observation, and Differences of sedimentation and structure, five lithofacies developed in the Yanchang Formation: shale shale facies, siltstone/ultrafine sandstone facies, tuff facies, argillaceous shale facies with silty lamina and argillaceous shale facies with tuff lamina. 2) The strong heterogeneity of shale makes it difficult to accurately explain the TOC distribution of shale intervals in the application of model-based interpretation methods. The LBCRM interpretation method based on the understanding of shale heterogeneity can effectively reduce the influence of formation factors other than TOC on the prediction accuracy by studying the characteristics of shale heterogeneity and constructing a TOC interpretation model for each lithofacies category. At the same time, the degree of unbalanced distribution of data is reduced, so that the data mining algorithm achieves better prediction effect. 3) The interpretability of lithofacies logging ensures the wellsite application based on the classification and regression model of lithofacies. Compared with the traditional homogeneous regression model, the prediction performance has been greatly improved, TOC segment prediction is more accurate. 4) The LBCRM method based on shale heterogeneity can better understand the reasons for the deviation of the traditional model-based interpretation method. After being combined with the latter, it can make logging data provide more useful information.

show abstract

Geochemical evaluation and source rock zonation by multi-layer perceptron neural network technique: a case study for Pabdeh and Gurpi Formations-North Dezful Embayment (SW Iran)

Jamshidipour,

Khanehbad,

Mirshahani

et al. 2023

J Petrol Explor Prod Technol

View full text Add to dashboard Cite

In this study, using a multi-layer perceptron neural network (MLPNN) model, total organic carbon (TOC) and hydrogen index (HI) values for Pabdeh and Gurpi Formations in the oil fields of Naft Sefid (NS-13), Kupal (KL-36, KL-38, and KL-48) and Palangan (PL-2) were calculated in the North Dezful Embayment located in the southwest of Iran. To build the MLPNN model, the geochemical data calculated by the Rock–Eval pyrolysis method (TOC and HI) and the conventional petrophysical well log data, including sonic transit time log (DT), formation density log (RHOB), total resistivity log (RT), spectral gamma-ray log, computed gamma-ray log and neutron porosity log from the NS-13 well were used. The log data were the input layer, and the geochemical data were the output layer of the model. Twenty-four datasets were used for MLPNN training, and seven datasets were used for MLPNN testing. Two hidden layers were considered in this technique. Each hidden layer has an activation function (tanh) and a solver parameter (lbfgs). The accuracy of measurement of TOC and HI indices of Pabdeh and Gurpi Formations in terms of R2 was 0.93 and 0.90, respectively. This model has higher accuracy than the ΔlogR technique (R2: 0.28). Considering the relationships between the input data and other wireline logs is an advantage of this technique. These two formations have five source rock zones. Pabdeh Formation has three zones. The middle zone of the Pabdeh Formation (Pz. II) has the highest TOC (2.6 wt%) and source rock potential. Pabdeh Formation has kerogen type II. Gurpi Formation has a weaker source rock potential than Pabdeh Formation due to its low TOC content (< 1%). Both source rock zones of this formation have low TOC, but in some layers of the lower zone of the Gurpi Formation (Gz. II), high values for TOC were predicted. Gurpi Formation has Kerogen types II and III.

show abstract

Total organic carbon (TOC) quantification using artificial neural networks: Improved prediction by leveraging XRF data

Cited by 12 publications

References 41 publications

Prediction of Total Organic Carbon in Organic-Rich Shale Rocks Using Thermal Neutron Parameters

Prediction of Total Organic Carbon in Organic-Rich Shale Rocks Using Thermal Neutron Parameters

TOC interpretation of lithofacies-based categorical regression model: A case study of the Yanchang formation shale in the Ordos basin, NW China

Geochemical evaluation and source rock zonation by multi-layer perceptron neural network technique: a case study for Pabdeh and Gurpi Formations-North Dezful Embayment (SW Iran)

Contact Info

Product

Resources

About