Enhanced group method of data handling (GMDH) for permeability prediction based on the modified Levenberg Marquardt technique from well log data

Energy ◽  
2022 ◽  
Vol 239 ◽  
pp. 121915
Author(s):  
Alvin K. Mulashani ◽  
Chuanbo Shen ◽  
Baraka M. Nkurlu ◽  
Christopher N. Mkono ◽  
Martin Kawamala
Keyword(s):  
Group Method ◽  
Well Log ◽  
Data Handling ◽  
Log Data ◽  
Permeability Prediction ◽  
Levenberg Marquardt

scholarly journals Prediction of Permeability Using Group Method of Data Handling (GMDH) Neural Network from Well Log Data

Energies ◽  
2020 ◽  
Vol 13 (3) ◽  
pp. 551 ◽  
Author(s):  
Baraka Mathew Nkurlu ◽  
Chuanbo Shen ◽  
Solomon Asante-Okyere ◽  
Alvin K. Mulashani ◽  
Jacqueline Chungu ◽  
...  
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Group Method ◽  
Well Testing ◽  
Well Log ◽  
Data Handling ◽  
Permeability Model ◽  
Log Data ◽  
Artificial Neural Network Ann

Permeability is an important petrophysical parameter that controls the fluid flow within the reservoir. Estimating permeability presents several challenges due to the conventional approach of core analysis or well testing, which are expensive and time-consuming. On the contrary, artificial intelligence has been adopted in recent years in predicting reliable permeability data. Despite its shortcomings of overfitting and low convergence speed, artificial neural network (ANN) has been the widely used artificial intelligent method. Based on this, the present study conducted permeability prediction using the group method of data handling (GMDH) neural network from well log data of the West arm of the East African Rift Valley. Comparative analysis of GMDH permeability model and ANN methods of the back propagation neural network (BPNN) and radial basis function neural network (RBFNN) were further explored. The results of the study showed that the proposed GMDH model outperformed BPNN and RBFNN as it achieved R/root mean square error (RMSE) value of 0.989/0.0241 for training and 0.868/0.204 for predicting, respectively. Sensitivity analysis carried out revealed that shale volume, standard resolution formation density, and thermal neutron porosity were the most influential well log parameters when developing the GMDH permeability model.

scholarly journals Reservoir Parameters Estimation with Some Log Curves of Qiongdongnan Basin Based on LS-SVM Method

2021 ◽  
Vol 2092 (1) ◽  
pp. 012024
Author(s):  
Tangwei Liu ◽  
Hehua Xu ◽  
Xiaobin Shi ◽  
Xuelin Qiu ◽  
Zhen Sun
Keyword(s):  
Prediction Models ◽  
Parameters Estimation ◽  
Qiongdongnan Basin ◽  
Support Vector ◽  
Well Log ◽  
Statistical Regression ◽  
Log Data ◽  
Core Data ◽  
Permeability Prediction ◽  
Porosity And Permeability

Abstract Reservoir porosity and permeability are considered as very important parameters in characterizing oil and gas reservoirs. Traditional methods for porosity and permeability prediction are well log and core data analysis to get some regression empirical formulas. However, because of strong non-linear relationship between well log data and core data such as porosity and permeability, usual statistical regression methods are not completely able to provide meaningful estimate results. It is very difficult to measure fine scale porosity and permeability parameters of the reservoir. In this paper, the least square support vector machine (LS-SVM) method is applied to the parameters estimation with well log and core data of Qiongdongnan basin reservoirs. With the log and core exploration data of Qiongdongnan basin, the approach and prediction models of porosity and permeability are constructed and applied. There are several type of log data for the determination of porosity and permeability. These parameters are related with the selected log data. However, a precise analysis and determine of parameters require a combinatorial selection method for different type data. Some curves such as RHOB,CALI,POTA,THOR,GR are selected from all obtained logging curves of a Qiongdongnan basin well to predict porosity. At last we give some permeability prediction results based on LS-SVM method. High precision practice results illustrate the efficiency of LS-SVM method for practical reservoir parameter estimation problems.

scholarly journals Comparison of Rock Type Determination Based on Permeability Estimation and FZI Value in Upper Cibulakan Shaly Sand Formation, ASR Field

2020 ◽  
Vol 2 (3) ◽  
Author(s):  
Anditya Sapta Rahesthi ◽  
Ratnayu Sitaresmi ◽  
Sigit Rahmawan
Keyword(s):  
Rock Type ◽  
Well Log ◽  
Rock Permeability ◽  
Log Data ◽  
Core Data ◽  
Permeability Prediction ◽  
Rock Types ◽  
Fluid Production ◽  
Shaly Sand ◽  
High Uncertainty

<em>Rock permeability is an important rock characteristic because it can help determine the rate of fluid production. Permeability can only be determined by direct measurement of core samples in the laboratory. Even though coring gives good results, the disadvantage is that it takes a lot of time and costs so it is not possible to do coring at all intervals. So that the well log is required to predict the level of permeability indirectly. However, the calculation of permeability prediction using well log data has a high uncertainty value, so rock typing is required so that the calculation of permeability prediction becomes more detailed. This research was conducted in an effort to determine the Hydraulic Flow Unit (HFU) of the reservoir in the well that has core data using the Flow Zone Indicator (FZI) parameter and FZI value propagation on wells that do not have core data so that the type of rock and permeability value are obtained from every well interval. From the results of the study, the reservoirs on the ASR field can be grouped into six rock types. The six rock types each have permeability as a function of validated porosity by applying it at all intervals. After FZI is calculated from log data and validated with core data, it can be seen that the results of the method produce a fairly good correlation (R<sup>2</sup> = 0.92). Furthermore, from the permeability equation values for each different rock type, the predicted permeability results are also quite good (R<sup>2 </sup>= 0.81).</em>

scholarly journals Group Method of Data Handling (GMDH) Lithology Identification Based on Wavelet Analysis and Dimensionality Reduction as Well Log Data Pre-Processing Techniques

Energies ◽  
2019 ◽  
Vol 12 (8) ◽  
pp. 1509 ◽  
Author(s):  
Chuanbo Shen ◽  
Solomon Asante-Okyere ◽  
Yao Yevenyo Ziggah ◽  
Liang Wang ◽  
Xiangfeng Zhu
Keyword(s):  
Dimensionality Reduction ◽  
Yellow Sea ◽  
Classification Accuracy ◽  
Group Method ◽  
Well Log ◽  
Data Handling ◽  
South Yellow Sea ◽  
Southern Basin ◽  
The South Yellow Sea ◽  
Processing Techniques

Although the group method of data handling (GMDH) is a self-organizing metaheuristic neural network capable of developing a classification function using influential input variables, the results can be improved by using some pre-processing steps. In this paper, we propose a joint principal component analysis (PCA) and GMDH (PCA-GMDH) classifier method. We investigated well log data pre-processing techniques composed of dimensionality reduction (DR) and wavelet analysis (WA), using the southern basin of the South Yellow Sea as a case study, with the aim of improving the lithology classification accuracy of the GMDH. Our results showed that the dimensionality reduction method, which is composed of PCA and linear discriminant analysis (LDA), minimized the complexity of the classifier by reducing the number of well log suites to the relevant components and factors. On the other hand, the WA decomposed the well log signals into time-frequency wavelets for the GMDH algorithm. Of all the pre-processing methods, only the PCA was able to significantly increase the classification accuracy rate of the GMDH. Finally, the proposed joint PCA-GMDH classifier not only increased the accuracy but also was able to distinguish between all the classes of lithofacies present in the southern basin of the South Yellow Sea.

Sign in / Sign up

Export Citation Format

Share Document