A dynamic adaptive radial basis function approach for total organic carbon content prediction in organic shale

Tan, Maojin; Liu, Qiong; Zhang, Songyang

doi:10.1190/geo2013-0154.1

Cited by 45 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indirect methods involve the utilization of petrophysical well logs and seismic data. A large number of models are reported in the literature for the prediction of geochemical parameters using composite well logs. ,− ,− …”

Section: Introductionmentioning

confidence: 99%

Data-Driven Approaches to Predict Thermal Maturity Indices of Organic Matter Using Artificial Neural Networks

et al. 2020

View full text Add to dashboard Cite

Prediction of thermal maturity index parameters in organic shales plays a critical role in defining the hydrocarbon prospect and proper economic evaluation of the field. Hydrocarbon potential in shales is evaluated using the percentage of organic indices such as total organic carbon (TOC), thermal maturity temperature, source potentials, and hydrogen and oxygen indices. Direct measurement of these parameters in the laboratory is the most accurate way to obtain a representative value, but, at the same time, it is very expensive. In the absence of such facilities, other approaches such as analytical solutions and empirical correlations are used to estimate the organic indices in shale. The objective of this study is to develop data-driven machine learning-based models to predict continuous profiles of geochemical logs of organic shale formation. The machine learning models are trained using the petrophysical wireline logs as input and the corresponding laboratory-measured core data as a target for Barnett shale formations. More than 400 log data and the corresponding core data were collected for this purpose. The petrophysical wireline logs are γ-ray, bulk density, neutron porosity, sonic transient time, spontaneous potential, and shallow resistivity logs. The corresponding core data includes the experimental results from the Rock-Eval pyrolysis and Leco TOC measurements. A backpropagation artificial neural network coupled with a particle swarm optimization algorithm was used in this work. In addition to the development of optimized PSO-ANN models, explicit empirical correlations are also extracted from the fine-tuned weights and biases of the optimized models. The proposed models work with a higher accuracy within the range of the data set on which the models are trained. The proposed models can give real-time quantification of the organic matter maturity that can be linked with the real-time drilling operations and help identify the hotspots of mature organic matter in the drilled section.

show abstract

Section: Introductionmentioning

confidence: 99%

Data-Driven Approaches to Predict Thermal Maturity Indices of Organic Matter Using Artificial Neural Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The values of DEN, R, Vp, and Vs are plotted against the organic related porosity, as shown in Figure e–h. Generally, petrophysical responses of the organic related pores are approximately the same as the organic carbon. ,,, Substances residing in organic related pores like the bitumen and kerogen are nonconductive with low weight, yielding high resistivity and low density in petrophysical experiments. Organic related pores are composited by soft matters showing the characteristics of high acoustic transit time.…”

Section: Results and Discussionmentioning

confidence: 99%

“…These reservoirs are featured by near-source accumulation, or self-generating and self-preserving. Organic matter plays an important role in these reservoir since the type and content of organic carbon controls the reservoir quality and hydrocarbon potential. − There are growing advancements to estimate the total organic carbon (TOC) using petrophysical and well logging data. − However, few reports are published on the characterization and quantitative evaluation of organic related pores using petrophysical methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Investigation of Organic Related Pores in Unconventional Reservoir and Its Quantitative Evaluation

Fan

Cao

et al. 2016

Energy Fuels

View full text Add to dashboard Cite

Pores in organic matters are important for unconventional reservoirs since a large amount of absorbed hydrocarbons reside in these spaces. An integrated method to quantify organic pores using low field nuclear magnetic resonance (NMR) is introduced in this paper. Relationships between the organic related porosity and geochemical parameters are also discussed. Resistivity, velocity, density, and natural gamma ray spectra are measured simultaneously to investigate petrophysical responses of organic pores, aiming to predict the organic related porosity using conventional petrophysical data. Results show that the NMR signal of samples under the dry state is a good indicator of organic pores and can be calibrated to the organic related porosity. The organic related porosity is positively correlated with total organic carbon content (TOC), absorbed free gaseous hydrocarbons (S0), absorbed free liquid hydrocarbons (S1), and residual petroleum potential (S2) but negatively correlated with residual carbons (RCs). The organic related porosity is positively correlated with thorium content (Th), natural gamma intensity (GR), and resistivity (R), whereas it is negatively correlated with density (DEN), compression wave velocity (Vp), and shear wave velocity (Vs). The model achieves favorable results, which can be generalized to predict the in situ organic related porosity.

show abstract

“…Due to the third artificial intelligence boom, machine learning has been widely used for lithology identification [23][24][25] and reservoir evaluation [26,27]. Machine learning methods for TOC content prediction include support vector machine (SVM) [28,29], Gaussian process regression (GPR) [30,31], extreme learning machine (ELM) [32,33], neural network [34,35], fuzzy clustering [36], and random forest (RF) [37]. Machine learning is data-driven, which improves the accuracy and efficiency of TOC prediction compared to conventional methods.…”

Section: Introductionmentioning

confidence: 99%

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

Liu¹,

Tian²,

Chen³

2021

Geofluids

View full text Add to dashboard Cite

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.

show abstract

A dynamic adaptive radial basis function approach for total organic carbon content prediction in organic shale

Cited by 45 publications

References 14 publications

Data-Driven Approaches to Predict Thermal Maturity Indices of Organic Matter Using Artificial Neural Networks

Data-Driven Approaches to Predict Thermal Maturity Indices of Organic Matter Using Artificial Neural Networks

Investigation of Organic Related Pores in Unconventional Reservoir and Its Quantitative Evaluation

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

Contact Info

Product

Resources

About