In the early days of intelligent fields, we tended to see the game as more data, more control, more models, and more integration. All these aspects, of course, are still key components to the system solutions that are now emerging. However, the most-competitive emerging systems blend artificial intelligence to bring better efficiency to the human work that results in good business decisions. As a result, we waste less time and fewer resources finding and manipulating data and focus more on complex engineering judgment and building richness into the bases of our decisions.
When Deep Blue beat Kasparov, it was a watershed event, but the timing of the event was the only surprise. That a computer could beat the best human chess player at some point was certain long before it happened.
As with most industries, the oil industry is ripe for automation of the type that is likely to trivialize much of what consumes our days as engineers today—which might seem threatening if you are a Kasparov. Unlike chess players, we have a much larger endgame, and our effective mastery of these technologies can help us sustain and deliver in an environment of intense competitive pressures. The body of knowledge and practice in this area is large and growing quickly, and some of the recommended articles in this section are examples of the current state of the art.
This Month's Technical Papers
Pseudodensity Log Generation by Use of Artificial Neural Networks
Cointerpretation of Distributed Acoustic and Temperature Sensing for Inflow Profiling
Efficient Optimization Strategies for Developing Intelligent-Well Business Cases
Recommended additional reading
OTC 26509 Limitations of Using Smart Wells To Achieve Waterflood Conformance in Stacked Heterogeneous Reservoirs: Case Study From Piltun Field by Harsimran Khural, Shell, et al.
SPE 180165 DAS/DTS/DSS/DPS/DxS—Do We Measure What Adds Value? by Kousha Gohari, Baker Hughes, et al.
SPE 181110 Optimal Field Development and Control Yield Accelerated, More-Reliable Production: A North Sea Case Study by M. Haghighat Sefat, Heriot-Watt University, et al.
SPE 181435 Machine-Learning Approach for Irregularity Detection in Dynamic Operating Conditions by Mohamed Sidahmed, BP, et al.
