Mr. Farhad Mollaei, Dr. Reza Mohebian, Dr. Ali Moradzadeh,
Volume 18, Issue 3 (12-2024)
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.
