Prediction of vitrinite reflectance values using machine learning techniques: a new approach

Sadeghtabaghi, Zahra; Talebkeikhah, Mohsen; Rabbani, Ahmad Reza

doi:10.1007/s13202-020-01043-8

Cited by 11 publications

(6 citation statements)

References 66 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the varying physical and chemical properties of different macerals, researchers are increasingly focusing on developing new theories and methods to separate macerals for various applications. As a result, the pyrolysis properties and macromolecular structures of various macerals have become research topics of great interest in the fields of coal geology, coal chemical industry, and coal-derived gas industry. − …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effects of Functional Groups in Coal with Different Vitrinite/Inertinite Ratios on Pyrolysis Products

et al. 2023

View full text Add to dashboard Cite

Maceral composition is one of the key factors affecting the liquefaction and gasification of coal, which has attracted extensive attention of researchers working on coal chemical industry. To elucidate the impact of vitrinite and inertinite in coal on pyrolysis products, vitrinite and inertinite were extracted from a single coal sample and mixed to create six samples with varying vitrinite/inertinite ratios. The samples were subjected to thermogravimetry coupled online with mass spectrometry (TG–MS) experiments, and the Fourier transform infrared spectrometry (FITR) experiment was used to determine the macromolecular structures before and after the TG–MS experiments. The results show that the maximum mass loss rate is proportional to the vitrinite content and inversely proportional to the inertinite content, and increased vitrinite content accelerates the pyrolysis process and shifts the pyrolysis peak to low temperatures. Based on FTIR experiments, the sample’s CH2/CH3 content, representing the length of aliphatic side chains, decreases significantly after pyrolysis, and the greater the loss of CH2/CH3, the greater the intensity of organic molecule production, indicating that aliphatic side chains are likely to yield organic molecule products. The aromatic degree (I) of samples rises sharply and steadily with increasing inertinite content. After high-temperature pyrolysis, the polycondensation degree of aromatic rings (DOC) and relative abundance of aromatic and aliphatic hydrogen (Har/Hal) within the sample increased significantly, indicating the thermal degradation rate of aromatic hydrogen content is much lower than that of aliphatic hydrogen. When the pyrolysis temperature is lower than 400 °C, the higher the inertinite content, the easier it is to produce CO2, whereas an increase in vitrinite leads to an increase in CO production. At this stage, the “–C–O–” functional group is pyrolyzed to produce CO and CO2. When the temperature exceeds 400 °C, the CO2 output intensity of vitrinite-rich samples is much higher than that of inertinite-rich samples, while the CO output intensity of vitrinite-rich samples is lower, and the higher the vitrinite content, the higher the peak temperature of CO gas production of samples, indicating that when the temperature exceeds 400 °C, the increase of vitrinite inhibits CO production and promotes CO2 production. At this stage, the reduction of each sample’s “–C–O–” functional group after pyrolysis is positively correlated with the maximum CO gas production intensity, and the reduction of each sample’s “–CO” functional group after pyrolysis is positively correlated with the maximum CO2 gas production intensity. As a result, the “–C–O–” functional group is more likely to produce CO, whereas the “–CO” functional group is more likely to be pyrolyzed to CO2. Hydrogen is primarily produced during the polycondensation and aromatization processes, and its production is proportional to the dynamic DOC values after pyrolysis. The higher the I value after pyrolysis, the lower the maximu...

show abstract

Section: Introductionmentioning

confidence: 99%

“…As a result, the pyrolysis properties and macromolecular structures of various macerals have become research topics of great interest in the fields of coal geology, coal chemical industry, and coal-derived gas industry. 6 − 8 …”

Section: Introductionmentioning

confidence: 99%

Effects of Functional Groups in Coal with Different Vitrinite/Inertinite Ratios on Pyrolysis Products

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence and machine learning are considered techniques being used widely for parameter prediction, especially in different branches of petroleum engineering. For instance, these artificial intelligence methods have been used for making synthetic well logs [4], determination of infill well location [5], reservoir characterization [6], drilling fluid [7], oil gas ratio [8], prediction of permeability [9], lost circulation [10], prediction of scale thickness [11], and vitrinite reflectance prediction [12]. Various approaches can predict this parameter by making models, and many published studies investigated the subject of permeability modeling.…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Machine Learning Approaches for Prediction of Permeability using Well Log Data in the Hydrocarbon Reservoirs

Talebkeikhah

Sadeghtabaghi

Shabani

2021

J. Hum. Earth Future

Self Cite

View full text Add to dashboard Cite

Permeability is a vital parameter in reservoir engineering that affects production directly. Since this parameter's significance is obvious, finding a way for accurate determination of permeability is essential as well. In this paper, the permeability of two notable carbonate reservoirs (Ilam and Sarvak) in the southwest of Iran was predicted by several different methods, and the level of accuracy in all models was compared. For this purpose, Multi-Layer Perceptron Neural Network (MLP), Radial Basis Function Neural Network (RBF), Support Vector Regression (SVR), decision tree (DT), and random forest (RF) methods were chosen. The full set of real well-logging data was investigated by random forest, and five of them were selected as the potent variables. Depth, Computed gamma-ray log (CGR), Spectral gamma-ray log (SGR), Neutron porosity log (NPHI), and density log (RHOB) were considered efficacious variables and used as input data, while permeability was considered output. It should be noted that permeability values are derived from core analysis. Statistical parameters like the coefficient of determination ( ), root mean square error (RMSE) and standard deviation (SD) were determined for the train, test, and total sets. Based on statistical and graphical results, the SVM and DT models perform more accurately than others. RMSE, SD and R2values of SVM and DT models are 0.38, 1.63, 0.97 and 0.44, 2.89, and 0.96 respectively. The results of the best-proposed models of this paper were then compared with the outcome of the empirical equation for permeability prediction. The comparison indicates that artificial intelligence methods perform more accurately than traditional methods for permeability estimation, such as proposed equations. Doi: 10.28991/HEF-2021-02-02-01 Full Text: PDF

show abstract

“…Estimation and correct determination of vitrinite reflectance (R o ) and the content of total organic carbon (TOC) are the main steps in describing source rock in both conventional and unconventional hydrocarbon deposits. Determination of these parameters using laboratory measurements has been widely used in the petroleum industry [1]. Unfortunately, this approach allows measurement and determination of parameters only from geological samples that provide point information.…”

Section: Introductionmentioning

confidence: 99%

“…Currently, shale gas deposits in Poland are under intense consideration because of gas saturation and perspectives in exploitation [12][13][14][15][16][17][18][19]. Hence, estimation of basic parameters, such as R o or TOC content in the shale gas formations based on well logs and laboratory data become a key task for researchers [1,11,[20][21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

Vitrinite Equivalent Reflectance Estimation from Improved Maturity Indicator and Well Logs Based on Statistical Methods

Waszkiewicz

Krakowska-Madejska

2021

Energies

View full text Add to dashboard Cite

Estimation and correct determination of vitrinite equivalent reflectance in rock is crucial for the assessment of the source rock in both conventional and unconventional hydrocarbon deposits. These parameters can be determined in laboratories on rock samples. Laboratory measurements provide only point information. However, the use of well logs could overcome discontinuities in the data and provide parameters throughout a study interval. Attention has been paid to the estimation of TOC based on well logs. Vitrinite equivalent reflectance estimation is less well discussed and most papers reported cases with high TOC content in analyzed deposits. In this paper, the estimation of improved Ro is presented using a calculated maturity indicator with well logs. As the organic matter content is not high, additional steps were required for the calculation. To improve the quality of the fit and to find similar intervals, the data were grouped using cluster and neural network analysis. The next step was to use the resistivity log to improve the obtained maturity indicator. Due to the changing properties of kerogen with the type and degree of thermal maturity, this approach turned out to be reliable. The use of resistivity significantly increased the correlation coefficient and reduced errors. The method was tested on two wells with different type and maturity of kerogen. The obtained results are satisfactory, which makes it possible to use the method even in formations with a low organic matter content.

show abstract

Prediction of vitrinite reflectance values using machine learning techniques: a new approach

Cited by 11 publications

References 66 publications

Effects of Functional Groups in Coal with Different Vitrinite/Inertinite Ratios on Pyrolysis Products

Effects of Functional Groups in Coal with Different Vitrinite/Inertinite Ratios on Pyrolysis Products

A Comparison of Machine Learning Approaches for Prediction of Permeability using Well Log Data in the Hydrocarbon Reservoirs

Vitrinite Equivalent Reflectance Estimation from Improved Maturity Indicator and Well Logs Based on Statistical Methods

Contact Info

Product

Resources

About