Analyzing organic richness of source rocks from well log data by using SVM and ANN classifiers: A case study from the Kazhdumi formation, the Persian Gulf basin, offshore Iran

Bolandi, Vahid; Kadkhodaie, Ali; Farzi, Reza

doi:10.1016/j.petrol.2017.01.003

Cited by 82 publications

(19 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Passey method has more widely selected parameters than Schmoker method (Bolandi et al 2017, Kim et al 2017, Zhao et al 2016) Firstly, we defined the baseline of resistivity and sonic logs, then we got DLogR from equation (4). Here, LOM (level of organic maturity) in equation 5is a parameter about maturity which can be obtained from the TOC-DlogR plot.…”

Section: Passey Methodsmentioning

confidence: 99%

A new method for TOC estimation in tight shale gas reservoirs

Rezaee

Wang

et al. 2017

International Journal of Coal Geology

View full text Add to dashboard Cite

Total organic carbon (TOC) estimation is significantly crucial for shale reservoir characterization. Traditional TOC estimation methods (such as Passey and Schmoker method) do not provide accurate TOC predictions in shale gas reservoirs especially for the self-generated and self-stored reservoirs. This study proposes, for the first time, a new TOC prediction method based on Gaussian Process Regression (GPR) bridging geostatistics and machine learning technique. The method utilizes a non-parametric regression approach in shale TOC predictions, and not only provides the expert solutions in high-dimension processing, small samples and non-linear problems, but also has a better adaptation and generalization ability compared with other machine learning methods. The approach accounts for all the well logging attributes and chooses the relevant logs to build TOC estimation model, and 7 different kernel functions and 5 attributes groups are analyzed to get the optimized hyperparameters in practice. Application of the developed model to two shale gas reservoirs showed that the model predicted TOC matched well with that from the laboratory measurements. The proposed model based on GPR method provides an accurate way for the TOC prediction in the tight shale gas reservoirs.

show abstract

Section: Passey Methodsmentioning

confidence: 99%

A new method for TOC estimation in tight shale gas reservoirs

Rezaee

Wang

et al. 2017

International Journal of Coal Geology

View full text Add to dashboard Cite

show abstract

“…This method seeks the optimal classification plane among the samples in the high dimensional feature space, which enables the classification surface to both guarantee the classification accuracy and maximize the interval between two classes of data. Finally, decision functions are constructed to determine the microfacies type of unknown prediction samples as well as the output type labels of the prediction samples, thus achieving depositional microfacies identification [37,38]. The Figure 2 presents the main flow chart of the methodology.…”

Section: Depositional Facies Subfacies Microfaciesmentioning

confidence: 99%

Support Vector Machine Algorithm for Automatically Identifying Depositional Microfacies Using Well Logs

et al. 2019

View full text Add to dashboard Cite

Depositional microfacies identification plays a key role in the exploration and development of oil and gas reservoirs. Conventionally, depositional microfacies are manually identified by geologists based on the observation of core samples. This conventional method for identifying depositional microfacies is time-consuming, and only the depositional microfacies in a few wells can be identified due to the limited core samples in these wells. In this study, the support vector machine (SVM) algorithm is proposed to identify depositional microfacies automatically using well logs. The application of SVM includes the following steps: First, the depositional microfacies are determined manually in several wells with core samples. Then, the training sets used in the SVM algorithm are extracted from the well logs. Finally, a quantitative discrimination model based on the SVM algorithm is established to realize the classification of depositional microfacies. Field application shows that this innovative and constructive solution can be effectively used in uncored wells to identify depositional microfacies with a rate of accuracy approaching 84%. It overcomes the limitation of the conventional manual method which greatly contributes to the cost-saving of core analysis and improves the sustainable profitability of oil and gas exploration.

show abstract

“…The issue of source rocks that produced the oil and gas has received considerable critical attention [1][2][3][4][5][6]. What known about the source rocks, total organic carbon (TOC) has been the most crucial concept in the study of the source rocks [7]. Otherwise, actual work is required to determine the TOC amount in the evaluation process of source rocks [5].…”

Section: Introductionmentioning

confidence: 99%

Geochemical Analysis for Determining Total Organic Carbon Content Based on ∆LogR Technique in the South Pars Field

et al. 2019

View full text Add to dashboard Cite

There is a recognized need for the determination of total organic carbon (TOC) as an essential factor in the evaluation of source rocks. In this study, the ∆LogR technique was coupled with logging curves of sonic, resistivity, spectral gamma-ray (SGR), and computed gamma-ray (CGR) to determine an accurate content of TOC in the Gadvan Formation. Multiple linear regression analysis was also applied to the ∆LogR technique. To this aim, 14 samples of the Gadvan Formation were taken from Wells B and C in the South Pars field and analyzed using Rock-Eval pyrolysis. Results from the ∆LogR technique and multiple linear regression analysis, well logs, and Rock-Eval were compared to calculate the accurate content of TOC in the Gadvan Formation. Geochemical data confirmed that the Gadvan Formation was a relatively poor source rock in the South Pars field, as average TOC and Tmax values of the samples were 0.79 and less than 430 °C, respectively. Also, the content of potassium (K < 0.1%) confirmed the origin of the source rock as a pure carbonate, whereas the low content of thorium (Th < 5 ppm) was indicative of the percentage of clays. There was a moderate content of uranium (U < 10 ppm), suggesting that the Gadvan Formation was not deposited in an excellent reducing environment to conserve the organic matter. Moreover, the results from the integration of the multiple linear regression model with SGR and CGR showed that the value of R2 was higher than the results obtained without SGR and CGR. Findings from this study could help the exploration and production team to determine the accurate content of TOC using the ∆LogR technique in association with logging curves.

show abstract

Analyzing organic richness of source rocks from well log data by using SVM and ANN classifiers: A case study from the Kazhdumi formation, the Persian Gulf basin, offshore Iran

Cited by 82 publications

References 30 publications

A new method for TOC estimation in tight shale gas reservoirs

A new method for TOC estimation in tight shale gas reservoirs

Support Vector Machine Algorithm for Automatically Identifying Depositional Microfacies Using Well Logs

Geochemical Analysis for Determining Total Organic Carbon Content Based on ∆LogR Technique in the South Pars Field

Contact Info

Product

Resources

About