Artificial intelligence techniques and their application in oil and gas industry
- PDF / 764,625 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 1 Downloads / 245 Views
Artificial intelligence techniques and their application in oil and gas industry Sachin Choubey1 · G. P. Karmakar2
© Springer Nature B.V. 2020
Abstract Data are being continuously generated from various operational steps in the oil and gas industry. The recordings of these data and their proper utilization have become a major concern for the oil and gas industry. Decision making based on predictive as well as inferential data analytics helps in making accurate decisions within a short period of time. In spite of many challenges, the use of data analytics for decision making is increasing on a large-scale in the oil and gas industry. An appreciable amount of development has been done in the above area of research. Many complex problems may now be easily solved using Artificial Intelligence (AI) and Machine Learning (ML) techniques. Historical, as well as real-time data, can be assimilated to achieve higher production by gathering data from the gas/oil wells. Various analytical modeling techniques are now widely being used by the oil and gas sector to make a decision based on data analytics. This paper reviews the recent developments via applications of AI and ML techniques for efficient exploitation of the data obtained, starting from the exploration for crude oil to the distribution of its end products. A brief account of the acceptance and future of these techniques in the oil and gas industry is also discussed. Present work may provide a technical framework for choosing relevant technologies for effectively gaining the information from the large volume of data generated by the oil and gas industry. Keywords Artificial intelligence · Machine learning · Big data analytics · Oil and gas industry Abbreviations ARE Absolute Relative Error ANN Artificial Neural Network BDMT Big Data Methods and Tools BHP Bottom Hole Pressure BNN Bayesian Belief Network * Sachin Choubey [email protected] G. P. Karmakar [email protected] 1
Information Technology and Systems, Indian Institute of Management, Kashipur 244713, India
2
Department of Mining Engineering, Indian Institute of Technology, Kharagpur 721302, India
13
Vol.:(0123456789)
S. Choubey, G. P. Karmakar
DT Decision Tree E&P Exploration and Production EOR Enhanced Oil Recovery ESP Electrical Submersible Pump FL Fuzzy Logic GA Genetic Algorithm GBM Gradient Boosting Machine LR Linear Regression NDT Neural Decision Tree MPD Measured Pressure Drilling MSE Mean Squared Error PCA Principal Component Analysis PNN Probabilistic Neural Network PVT Pressure Volume Temperature RF Random Forest SVM Support Vector Machine SVR Support Vector Regression
1 Introduction Newer fields for petroleum exploration are even deeper and remotely located. As reported by Lantham (2019), the demand for oil and gas products is growing every year. And thus, the organizations need to optimize production, reduce costs, and impact of oil and gas production on the environment. These objectives cannot be fulfilled by conventional methods of petroleum ex
Data Loading...
