A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Fracture Pressure Prediction in Carbonate Reservoir Using Artificial Neural Networks
https://orcid.org/https://orcid.org/0000-0001-7053-0099
https://orcid.org/https://orcid.org/0000-0001-7191-5222
https://orcid.org/https://orcid.org/0009-0007-7809-2653
https://orcid.org/https://orcid.org/0000-0001-9271-9423
https://orcid.org/https://orcid.org/0000-0003-3814-3296
Accurately estimating fracture pressure is a critical factor in the success of the oil field industry. Fracture pressure is used in various applications, including increasing production and injection processes, making it essential to determine precisely. This study aims to predict the fracture pressure for Iraqi oil field using artificial intelligence techniques, such studies are crucial in optimizing oil field production and minimizing risks. Artificial intelligence (AI) methodologies employed a dataset comprising approximately 13 000 data points for different logs parameters. The input layer is employing the input parameter (neutron, density, gamma ray, rock strength (UCS), true vertical depth (TVD), Young’s modulus (E), and Poisson ratio (v). The obtained results should be remarkable R2 of 0.86. The optimal approach entails utilizing readily available log data, including sonic logs compression and shear (DTC, DTS) commendable R-squared value of 0.84. Artificial neural networks (ANN) have the upper hand over empirical models, as they require important data, only surface drilling parameters, which are easily accessible and use it from any well. In addition, a new fracture pressure correlation depended on artificial neural networks (ANN) has been created, which can accurately predict fracture pressure. The findings of the study can provide valuable insights for the oil and gas industry in predicting fracture pressure accurately and efficiently.
Fracture Pressure Prediction in Carbonate Reservoir Using Artificial Neural Networks
https://orcid.org/https://orcid.org/0000-0001-7053-0099
https://orcid.org/https://orcid.org/0000-0001-7191-5222
https://orcid.org/https://orcid.org/0009-0007-7809-2653
https://orcid.org/https://orcid.org/0000-0001-9271-9423
https://orcid.org/https://orcid.org/0000-0003-3814-3296
Accurately estimating fracture pressure is a critical factor in the success of the oil field industry. Fracture pressure is used in various applications, including increasing production and injection processes, making it essential to determine precisely. This study aims to predict the fracture pressure for Iraqi oil field using artificial intelligence techniques, such studies are crucial in optimizing oil field production and minimizing risks. Artificial intelligence (AI) methodologies employed a dataset comprising approximately 13 000 data points for different logs parameters. The input layer is employing the input parameter (neutron, density, gamma ray, rock strength (UCS), true vertical depth (TVD), Young’s modulus (E), and Poisson ratio (v). The obtained results should be remarkable R2 of 0.86. The optimal approach entails utilizing readily available log data, including sonic logs compression and shear (DTC, DTS) commendable R-squared value of 0.84. Artificial neural networks (ANN) have the upper hand over empirical models, as they require important data, only surface drilling parameters, which are easily accessible and use it from any well. In addition, a new fracture pressure correlation depended on artificial neural networks (ANN) has been created, which can accurately predict fracture pressure. The findings of the study can provide valuable insights for the oil and gas industry in predicting fracture pressure accurately and efficiently.
Fracture Pressure Prediction in Carbonate Reservoir Using Artificial Neural Networks
https://orcid.org/https://orcid.org/0000-0001-7053-0099
https://orcid.org/https://orcid.org/0000-0001-7191-5222
https://orcid.org/https://orcid.org/0009-0007-7809-2653
https://orcid.org/https://orcid.org/0000-0001-9271-9423
https://orcid.org/https://orcid.org/0000-0003-3814-3296
Accurately estimating fracture pressure is a critical factor in the success of the oil field industry. Fracture pressure is used in various applications, including increasing production and injection processes, making it essential to determine precisely. This study aims to predict the fracture pressure for Iraqi oil field using artificial intelligence techniques, such studies are crucial in optimizing oil field production and minimizing risks. Artificial intelligence (AI) methodologies employed a dataset comprising approximately 13 000 data points for different logs parameters. The input layer is employing the input parameter (neutron, density, gamma ray, rock strength (UCS), true vertical depth (TVD), Young’s modulus (E), and Poisson ratio (v). The obtained results should be remarkable R2 of 0.86. The optimal approach entails utilizing readily available log data, including sonic logs compression and shear (DTC, DTS) commendable R-squared value of 0.84. Artificial neural networks (ANN) have the upper hand over empirical models, as they require important data, only surface drilling parameters, which are easily accessible and use it from any well. In addition, a new fracture pressure correlation depended on artificial neural networks (ANN) has been created, which can accurately predict fracture pressure. The findings of the study can provide valuable insights for the oil and gas industry in predicting fracture pressure accurately and efficiently.
Fracture Pressure Prediction in Carbonate Reservoir Using Artificial Neural Networks
Pet. Chem.
Faraj, Ali Khaleel (author) / Salih, Ameen K. (author) / Ahmed, Mohammed A. (author) / Hadi, Farqad A. (author) / Al-Hasnawi, Ali Nahi Abed (author) / Zaidan, Ali Faraj (author)
Petroleum Chemistry ; 64 ; 796-803
2024-07-01
8 pages
Article (Journal)
Electronic Resource
English
Prediction of fracture toughness using artificial neural networks (ANNs)
| British Library Online Contents | 1997
Prediction of fracture parameters of concrete by Artificial Neural Networks
| British Library Online Contents | 2004
| IOP Institute of Physics | 2013
Permeability Prediction Using Different Methods in Carbonate Reservoir
| Springer Verlag | 2024