Estimation of Static Young’s Modulus for Sandstone Formation Using Artificial Neural Networks
In this study, we used artificial neural networks (ANN) to estimate static Young’s modulus (E<sub>static</sub>) for sandstone formation from conventional well logs. ANN design parameters were optimized using the self-adaptive differential evolution optimization algorithm. The A...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/12/11/2125 |
| _version_ | 1797999603142885376 |
|---|---|
| author | Ahmed Abdulhamid Mahmoud Salaheldin Elkatatny Abdulwahab Ali Tamer Moussa |
| author_facet | Ahmed Abdulhamid Mahmoud Salaheldin Elkatatny Abdulwahab Ali Tamer Moussa |
| author_sort | Ahmed Abdulhamid Mahmoud |
| collection | DOAJ |
| description | In this study, we used artificial neural networks (ANN) to estimate static Young’s modulus (E<sub>static</sub>) for sandstone formation from conventional well logs. ANN design parameters were optimized using the self-adaptive differential evolution optimization algorithm. The ANN model was trained to predict E<sub>static</sub> from conventional well logs of the bulk density, compressional time, and shear time. The ANN model was trained on 409 data points from one well. The extracted weights and biases of the optimized ANN model was used to develop an empirical relationship for E<sub>static</sub> estimation based on well logs. This empirical correlation was tested on 183 unseen data points from the same training well and validated using data from three different wells. The optimized ANN model estimated E<sub>static</sub> for the training dataset with a very low average absolute percentage error (AAPE) of 0.98%, a very high correlation coefficient (R) of 0.999 and a coefficient of determination (R<sup>2</sup>) of 0.9978. The developed ANN-based correlation estimated E<sub>static</sub> for the testing dataset with a very high accuracy as indicated by the low AAPE of 1.46% and a very high R and R<sup>2</sup> of 0.998 and 0.9951, respectively. In addition, the visual comparison of the core-tested and predicted E<sub>static</sub> of the validation dataset confirmed the high accuracy of the developed ANN-based empirical correlation. The ANN-based correlation overperformed four of the previously developed E<sub>static</sub> correlations in estimating E<sub>static</sub> for the validation data, E<sub>static</sub> for the validation data was predicted with an AAPE of 3.8% by using the ANN-based correlation compared to AAPE’s of more than 36.0% for the previously developed correlations. |
| first_indexed | 2024-04-11T11:07:20Z |
| format | Article |
| id | doaj.art-4bba5abe4b5348ba95d432bf8d044565 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T11:07:20Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-4bba5abe4b5348ba95d432bf8d0445652022-12-22T04:28:16ZengMDPI AGEnergies1996-10732019-06-011211212510.3390/en12112125en12112125Estimation of Static Young’s Modulus for Sandstone Formation Using Artificial Neural NetworksAhmed Abdulhamid Mahmoud0Salaheldin Elkatatny1Abdulwahab Ali2Tamer Moussa3College of Petroleum Engineering and Geosciences, King Fahd University of Petroleum & Minerals, Dhahran 31261, Saudi ArabiaCollege of Petroleum Engineering and Geosciences, King Fahd University of Petroleum & Minerals, Dhahran 31261, Saudi ArabiaCenter of Integrative Petroleum Research, King Fahd University of Petroleum & Minerals, Dhahran 31261, Saudi ArabiaCollege of Petroleum Engineering and Geosciences, King Fahd University of Petroleum & Minerals, Dhahran 31261, Saudi ArabiaIn this study, we used artificial neural networks (ANN) to estimate static Young’s modulus (E<sub>static</sub>) for sandstone formation from conventional well logs. ANN design parameters were optimized using the self-adaptive differential evolution optimization algorithm. The ANN model was trained to predict E<sub>static</sub> from conventional well logs of the bulk density, compressional time, and shear time. The ANN model was trained on 409 data points from one well. The extracted weights and biases of the optimized ANN model was used to develop an empirical relationship for E<sub>static</sub> estimation based on well logs. This empirical correlation was tested on 183 unseen data points from the same training well and validated using data from three different wells. The optimized ANN model estimated E<sub>static</sub> for the training dataset with a very low average absolute percentage error (AAPE) of 0.98%, a very high correlation coefficient (R) of 0.999 and a coefficient of determination (R<sup>2</sup>) of 0.9978. The developed ANN-based correlation estimated E<sub>static</sub> for the testing dataset with a very high accuracy as indicated by the low AAPE of 1.46% and a very high R and R<sup>2</sup> of 0.998 and 0.9951, respectively. In addition, the visual comparison of the core-tested and predicted E<sub>static</sub> of the validation dataset confirmed the high accuracy of the developed ANN-based empirical correlation. The ANN-based correlation overperformed four of the previously developed E<sub>static</sub> correlations in estimating E<sub>static</sub> for the validation data, E<sub>static</sub> for the validation data was predicted with an AAPE of 3.8% by using the ANN-based correlation compared to AAPE’s of more than 36.0% for the previously developed correlations.https://www.mdpi.com/1996-1073/12/11/2125static young’s modulusartificial neural networksself-adaptive differential evolution algorithmsandstone reservoirs |
| spellingShingle | Ahmed Abdulhamid Mahmoud Salaheldin Elkatatny Abdulwahab Ali Tamer Moussa Estimation of Static Young’s Modulus for Sandstone Formation Using Artificial Neural Networks Energies static young’s modulus artificial neural networks self-adaptive differential evolution algorithm sandstone reservoirs |
| title | Estimation of Static Young’s Modulus for Sandstone Formation Using Artificial Neural Networks |
| title_full | Estimation of Static Young’s Modulus for Sandstone Formation Using Artificial Neural Networks |
| title_fullStr | Estimation of Static Young’s Modulus for Sandstone Formation Using Artificial Neural Networks |
| title_full_unstemmed | Estimation of Static Young’s Modulus for Sandstone Formation Using Artificial Neural Networks |
| title_short | Estimation of Static Young’s Modulus for Sandstone Formation Using Artificial Neural Networks |
| title_sort | estimation of static young s modulus for sandstone formation using artificial neural networks |
| topic | static young’s modulus artificial neural networks self-adaptive differential evolution algorithm sandstone reservoirs |
| url | https://www.mdpi.com/1996-1073/12/11/2125 |
| work_keys_str_mv | AT ahmedabdulhamidmahmoud estimationofstaticyoungsmodulusforsandstoneformationusingartificialneuralnetworks AT salaheldinelkatatny estimationofstaticyoungsmodulusforsandstoneformationusingartificialneuralnetworks AT abdulwahabali estimationofstaticyoungsmodulusforsandstoneformationusingartificialneuralnetworks AT tamermoussa estimationofstaticyoungsmodulusforsandstoneformationusingartificialneuralnetworks |