Page 144 - Intelligent Digital Oil And Gas Fields

Components of Artificial Intelligence and Data Analytics 107

Data mining 65
Neural networks 58
Workflow automation 47
Fuzzy logic 45
Expert systems 42
Automatic process control 40
Genetic algorithms 36
Rule-based on reasoning 34
Proxy models 31
Virtual models 31
Machine learning 21
Intelligent agents 19
None 10
Others 4
Fig. 4.1 Professional awareness of AIPA technologies in oil and gas industry. Numbers
are given in percent (%). (Modified from Bravo, C., Saputelli, L., Rivas, F., P erez, A.G.,
Nikolaou, M., Zangl, G., et al., 2014. State of the Art of Artificial Intelligence and Predictive
Analytics in the E&P Industry: A Technology Survey. SPE 150314-PA, https://doi.org/10.2118/
150314-PA.)

On the other hand, statistical and machine learning (ML) techniques
[which is one of the fastest growing technical fields and in the core of AI
and evidence-based decision-making data science in health care, manu-
facturing, education, financial modeling, policing, marketing, and even
social networking (Jordan and Mitchell, 2015)] remain relatively under-
utilized in E&P. The results of the survey suggest that the reasons for this
underutilization may be attributed mostly to the relative obscureness and
advanced technical concepts of ML, with the limited sources of informa-
tion available for engineers and geoscientists; however, the situation is
improving.
Lochmann and Brown (2016) further argue that the concepts of
“intelligent energy,” which largely encompass the methods and techniques
of AIPA, have reached a strategic inflection point (SIP) in the oil and gas
industry as “numerous case studies have documented new ways of working
and more-than 10-folds improvement to individual productivity, demon-
strating that new, more-effective ways of operating oil and gas assets are
possible and practical.”