Volume 18, Issue 3 (Autumn 2024)                   2024, 18(3): 341-364 | Back to browse issues page

XML Persian Abstract Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Mollaei F, Mohebian R, Moradzadeh A. Proposing a Deep Learning Algorithm for Estimating the Brittleness Index Using Conventional Log Data in the Asmari Formation of a Southwestern Iranian Oil Field. Journal of Engineering Geology 2024; 18 (3) :341-364
URL: http://jeg.khu.ac.ir/article-1-3127-en.html
Proposing a Deep Learning Algorithm for Estimating the Brittleness Index Using Conventional Log Data in the Asmari Formation of a Southwestern Iranian Oil Field
Farhad Mollaei1 , Reza Mohebian 2, Ali Moradzadeh1
1- Tehran Univercity
2- Tehran Univercity , mohebian@ut.ac.ir
Abstract:   (1589 Views)
The brittlenessindex is one of the most important parameters in geomechanical analysis and modeling. Many methods have been proposed to estimate the brittleness index. One of the recently used methods is the  intelligent method. In this paper, firstly the aim is to introduce a new algorithm using deep learning algorithms to predict the brittleness index in one of the wells of the hydrocarbon field in southwest Iran. In this article, first, the effective features for the input of the algorithms were determined using Pearson's correlation coefficient, and then using (recurrent neural network + multi-layer perceptron neural network) (LSTM + MLP) and (convolutional neural network + recurrent neural network) (CNN+ LSTM) brittleness index was estimated and the mean error value (MSE) and coefficient of determination (R2) were calculated for the training and test data. For both training and test data, both algorithms have a coefficient of determination close to 1 and a very low error. Also, in order to ensure the results of the algorithms, a part of the data was set aside as blind data, and the error and coefficient of determination were calculated for this data, and the error was MSE CNN+LSTM =26.0425,  MSE LSTM+MLP =32.0751  and the coefficient of determination was R2 CNN+LSTM  =0.8064,  R2 LSTM+MLP  =0.7615 . The results show the effectiveness of the introduced deep learning algorithms as a new method in predicting the brittleness index, and comparing the two algorithms presented, the CNN+LSTM algorithm has higher accuracy and less error.
Keywords: brittleness index, petrophysical data, deep learning, evaluation model
Full-Text [PDF 2800 kb]   (27 Downloads)    
Type of Study: Original Research | Subject: En. Geophisic
Received: 2024/08/10 | Accepted: 2024/11/5 | Published: 2024/12/15
Add your comments about this article : Your username or Email:
CAPTCHA
Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2024 CC BY-NC 4.0 | Journal of Engineering Geology

Designed & Developed by : Yektaweb