Identification of well logs with significant impact on prediction of oil and gas reservoirs permeability using statistical analysis of RSE values

Majdi, Abbas; Beiki, Morteza; Pirayehgar, A.; Hosseinyar, Gholamreza

doi:10.1016/j.petrol.2010.10.001

Cited by 11 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On one hand, the composition of wellhead gas includes above seven components of alkanes and a little of other alkanes with more -CH 2 -molecular group, such as iso-hexane and n-hexane. On the other hand, for gas well logging, GC has been widely used for a long time, and was even the only instrument [14,20]. And its gas well log can be taken as the reference for testing the instrument based on FTIR.…”

Section: Testing Results and Analysismentioning

confidence: 99%

On-line multi-component alkane mixture quantitative analysis using Fourier transform infrared spectrometer

Tang

Zhu

et al. 2015

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

Keywords:FTIR Multi-component alkane mixture On-line quantitative analysis Feature extraction and selection Calibration transfer Fourier transform infrared spectrometer (FTIR) has been widely used to analyze multi-component gas mixture for more than ten years because of its potential benefits. However, it is a challenge to analyze multicomponent alkane mixture on-line with FTIR because their absorption spectra overlap with each other extensively. In this paper, the methods of feature extraction and selection based on Tikhonov regularization (TR), and the modeling methods based on neural network (NN) are discussed in the practical conditions of alkane mixture analysis with FTIR. Then, the proposed methods compared with gas chromatograph (GC), normally regarded as the standard way for quantitative gas analysis, are used for gas well logging to analyze the mixture of methane, ethane, propane, iso-butane and n-butane on-line. By comparing the well logging curves obtained from FTIR with the ones from GC, it is shown that the logging curves analyzed with proposed method are good matches with the ones obtained from GC, which means that our analysis results are accurate. At the end of this paper, a calibration transfer is used to calibrate additional 18 instruments with a few sets of samples. And the work introduced in this paper demonstrates that FTIR can also be used in analyzing multi-component gas with close molecular structure accurately and the analyzer can be produced in mass.

show abstract

Section: Testing Results and Analysismentioning

confidence: 99%

On-line multi-component alkane mixture quantitative analysis using Fourier transform infrared spectrometer

Tang

Zhu

et al. 2015

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

show abstract

“…Data preprocessing [3,6,7]: In order to establish the lithology faces-identification model based on the neural network method, the four cored wells in Block K have been used, which include log curves, carbonate rocks types, more than 45m cored-well intervals in all. To get reasonable carbonate rock type parameters and because of the different series of logging data, the environmental correction of well-log curves, the work of depth matching between well logging and curves normalization have to be done firstly.…”

Section: Model Buildingmentioning

confidence: 99%

Artificial Neural Networks Identification of Lithology-Types in Complex Carbonate from Well Logs, Block K, in Uzbekistan

Lin

Sheng

et al. 2013

AMR

View full text Add to dashboard Cite

In oil and gas exploration of Block K in Amu Darya basin Uzbekistan, the reservoir lithologies are mainly in different carbonate rocks, the more types of rocks, the more various reservoir space is, as a result, it brings some difficulties to the reservoir quantitative evaluation. Therefore, according to this situation that the difficulty in identification of complex carbonate lithologies is, in this study block, artificial neural network analysis method is used in this paper. The method combines mud logging, cutting, core data, well logging, studies logging response characteristics of the different types of carbonate rocks, establishes lithology identification index. In this study, the method is used in identifying the types of carbonate rocks, the identified result compared to actual rocks displays about 70.51~87.23%, and it plays the positive role for reservoir quantitative evaluation.

show abstract

“…Linear multiple regression and neural networks are popular among 2 statistical techniques for reservoir modeling from well logs and seismic attributes (Nikravesh and Aminzadeh, 2001;Bosch et al, 2005). Lately, several computation intensive artificial intelligence (AI) methods such as artificial neural network (ANN), neuro-fuzzy, self-organizing map (SOM), committee machine and learning vector quantization (LVQ) have attained recognition as the potential tools to solve nonlinear and complex problems in the domain of reservoir characterization (Fung et al, 1997;Nikravesh et al, 1998;Nikravesh and Aminzadeh, 2001;Nikravesh and Hassibi, 2003;Hamada and Elshafei, 2010;Bosch et al, 2010, Karimpouli et al, 2010Majdi et al, 2010;Asadisaghandi and Tahmasebi, 2011;Tahmasebi and Hezarkhani, 2012). Permeability, porosity, fluid saturation and, sand and shale fractions are some of the fundamental reservoir characteristics spatially distributed non-uniformly.…”

Section: Introductionmentioning

confidence: 99%

Well tops guided prediction of reservoir properties using modular neural network concept: A case study from western onshore, India

Chaki

Verma

Routray

et al. 2014

Journal of Petroleum Science and Engineering

View full text Add to dashboard Cite

This paper proposes a complete framework consisting pre-processing, modeling, and postprocessing stages to carry out well tops guided prediction of a reservoir property (sand fraction) from three seismic attributes (seismic impedance, instantaneous amplitude, and instantaneous frequency) using the concept of modular artificial neural network (MANN). The dataset used in this study comprising three seismic attributes and well log data from eight wells, is acquired from a western onshore hydrocarbon field of India. Firstly, the acquired dataset is integrated and normalized. Then, well log analysis and segmentation of the total depth range into three different units (zones) separated by well tops are carried out. Secondly, three different networks are trained corresponding to three different zones using combined dataset of seven wells and then trained networks are validated using the remaining test well. The target property of the test well is predicted using three different tuned networks corresponding to three zones; and then the estimated values obtained from three different networks are concatenated to represent the 1 predicted log along the complete depth range of the testing well. The application of multiple simpler networks instead of a single one improves the prediction accuracy in terms of performance evaluators-correlation coefficient, root mean square error, absolute error mean and program execution time. Then, volumetric prediction of reservoir properties is carried out using calibrated network parameters. This stage is followed by post-processing to improve visualization. Thus, a complete framework, which includes pre-processing, model building and validation, volumetric prediction, and post-processing, is designed for successful mapping between seismic attributes and a reservoir characteristic. The proposed framework outperformed a single artificial neural network in terms of reduced prediction error, program execution time and improved correlation coefficient as a result of application of the MANN concept.

show abstract

Identification of well logs with significant impact on prediction of oil and gas reservoirs permeability using statistical analysis of RSE values

Cited by 11 publications

References 14 publications

On-line multi-component alkane mixture quantitative analysis using Fourier transform infrared spectrometer

On-line multi-component alkane mixture quantitative analysis using Fourier transform infrared spectrometer

Artificial Neural Networks Identification of Lithology-Types in Complex Carbonate from Well Logs, Block K, in Uzbekistan

Well tops guided prediction of reservoir properties using modular neural network concept: A case study from western onshore, India

Contact Info

Product

Resources

About