Paitoon (PT) Tontiwahwuthikul, Christin W.Chan, Fanhua (Bill) Zng,Zhiwu (Hnry) Liang, Trawat Sma, Chao Min

a Canadian Academy of Engineering (FCAE), Clean Energy Technologies Research Institute (CETRi), University of Regina, SK, Canada

b Canadian Academy of Engineering (FCAE), Canada Research Chair Tier I in Energy and Environmental Informatics (2006-2020), Energy Informatics Laboratory, University of Regina, SK, Canada

c Faculty of Graduate Studies and Research, University of Regina, SK, Canada

d Joint International Center for CO2 Capture & Storage (iCCS), Hunan University, Changsha, Hunan, 410082, China

e Sustainable Multiphase ARtificial-intelligence Technology (SMART) Laboratory, Department of Chemical Technology, Chulalongkorn University, Bangkok, Thailand

f Institute for Artificial Intelligence, Southwest Petroleum University, Chengdu, China

Over the past two decades, broad-based and intense efforts have been devoted to apply concepts and methodologies from information technology (IT) and artificial intelligence (AI) to informatics research related to energy and environmental systems.Both academic research and industrial practices have generated an impressive amount of literature, which spans virtually every aspect of synergistic work among these disciplines.Informatics and systems analysis techniques are now being widely used by the practicing engineers and scientists to solve a broad range of problems in the petroleum industry.Speaking at the World Economic Forum at Davos Switzerland in 2017, Ginni Rometty, IBM′ CEO at that time (now Executive Chairperson of IBM), described AI's role in the partnership between humans and machines as “augmented cognition.” In other words, AI not only supports but augments human cognition so that humans can be more efficient and “do a better job” [1,2].This should also be true and very beneficial for the petroleum industry.

Since 2014, the petroleum crude and products prices have fallen dramatically, and this development has forced most petroleum companies to take drastic actions such as layoffs, cutting investments and budgets, and others.As a result, the petroleum industry has been challenged to adapt and optimize its performance to remain profitable while maintaining a long-term investment and operation outlook.Currently, oil and gas companies find it very difficult to maintain the same level of investment in exploration and production as when crude prices were at their peak more 10 years ago.Operations in the oil and gas industry today require balancing a vast array of trade-offs in the drive for competitive advantage while maximizing return on investment.This situation has created an urgent need to enhance performance while minimizing the cost of production per barrel, and a major opportunity for optimization resides in the vast reserve of data generated and collected in the oil and gas fields.The petroleum industry can seize the opportunity and leverage the technologies of Artificial Intelligence (AI), Knowledge-based Systems (KBS), and Machine Learning (ML) for building a foundation for long-term success [3].If volatility in oil prices is the new norm, which is expected to be the case, the push for “value over volume” is the key to achieving success going forward.

For example, using AI techniques and tools, upstream oil and gas companies can shift their approach from production at all costs to production in context, such that profit and loss management is performed at the well level to optimize the production cost per barrel.This objective can be achieved by integrating all aspects of production management, collecting and utilizing the data for analysis and forecasting, and applying AI technologies for optimizing operations.Alternatively, when remote sensors are connected to wireless networks, data can be collected and centrally analyzed from any location.The insights derived can then help optimize operations.According to the consulting firm McKinsey, the oil and gas supply chain stands to gain up to $50 billion in savings and increased profit by adopting AI and related technologies [4,5].

A number of issues related to the significant opportunity of leveraging advanced information technology in the petroleum industry are being explored in this special issue on“Recent progress and new developments of applications of Artificial Intelligence (AI), Knowledge-basedSystems (KBS), and Machine Learning (ML) in the Petroleum Industry”.Included in the special issue are papers sent from diverse research teams around the world, including those from USA, UK, Australia, Canada, China, UAE, Kuwait, Iran, Algeria, and Thailand.We hope that this special issue will be a valuable source of information for engineers, scientists, and decision makers working in the academia, industry, and government.We also hope that the special issue will be a useful resource for the next generation of young researchers working in this important research area.

We extend our special thanks to the authors and their research teams for their research contributions.In particular, we would like to mention the team led by Dr.David Wood from USA, and thank them for their work related to real-world applications of artificial neural networks (ANN) in the petroleum industry.We also would like to thank the team led by Dr.Farshid Torabi from Canada; they contributed an excellent review on the emerging trend of “Big Data Analytics in Oil & Gas Industry”.

In conclusion, we wish you an enjoyable time reading this special issue, and look forward to hearing about your current and planned research in this area in future issues of PETROLEUM.

Best regards.

Editorial Team for Special Issue on “Recent progress and new developments of applications of Artificial Intelligence (AI), Knowledge- based Systems (KBS), and Machine Learning (ML) in the Petroleum Industry".

References

[1] https://www.wsj.com/articles/ibm-chief-predicts-artificial-intelligence-wont-be-a- job-killer-1484669444.

[2] https://www.youtube.com/watch?v=iqzdD_n-bOs.

[3] http://insights.globalspec.com/article/2772/the-growing-role-of-artificial- intelligence-in-oil-and-gas.

[4] https://www.mckinsey.com/industries/oil-and-gas/our-insights/the-oil-and-gas- organization-of-the-future.

[5] Tim Haidar, “Digital Barrels: the Rise of Machine Learning in Oil and Gas”, www.OilandGasIQ.com (05/08/2017):.