COVID-19 has significantly accelerated the adoption of digital technologies across all industries, and the oil and gas industry has been no exception. Consequently, interest in digital data acquisition, the backbone of all digital transformation work flows, also has increased significantly. This can clearly be seen in the multifold increase in the number of SPE papers on this topic since last year.
This feature will continue to focus on technologies to improve data accessibility and data acquisition, as well as entirely new data sources and their applications.
The papers chosen this year include real-time remote monitoring of steam traps and corrosion using wireless sensors, enabling faster and easier access to relevant subsurface information through deep learning of unstructured documents, and automation of real-time drilling work flows through digital transformation technologies.
While not reflected in these papers, a related emerging technology that has the potential to transform the data acquisition paradigm and that is garnering much attention, however, is edge computing. As the saying goes, if you cannot bring the data to the model, take the model to the data.
One of the main difficulties in faster adoption of digital transformation in oil and gas has been access to reliable real-time data that can be converted to real-time decisions. This is the case because of the remote and geographically distributed nature of most oil and gas assets and legacy outdated and piecemeal information-technology (IT) infrastructures, making it difficult to provide models with reliable, standardized data in a timely manner.
Edge-computing frameworks eliminate scale and capacity constraints and bypass limitations of current IT infrastructures, truly enabling operationalization of models for real-time decision making. Edge computing, together with machine learning and artificial intelligence, will be the real enablers of digital transformation.
This Month’s Technical Papers
Recommended Additional Reading
SPE 196259 Harnessing the Power of Natural Language Processing and Fuzzy Theory To Improve Oil and Gas Data Management Efficiency by Hasan Asfoor, Saudi Aramco, et al.
SPE 201319 Data Digitalization and Smart Work Flows Provide a Powerful Asset-Management-Optimization Tool in Margarita Field, Bolivia by Fernando Lema, Repsol, et al.
OTC 29130 Toward Automation of Satellite-Based Radar Imagery for Iceberg Surveillance—Machine Learning of Ship and Iceberg Discrimination by Desmond Power, C-CORE, et al.
|Pallav Sarma, SPE, is cofounder and chief scientist at Tachyus, responsible for the modeling and optimization technologies underlying the Tachyus platform. He is an expert in closed-loop reservoir management and holds multiple patents and has written more than 50 papers on various topics, including simulation, optimization, data assimilation, and machine learning. Sarma has more than 12 years of experience working for Chevron and Schlumberger before forming Tachyus. He has received many awards, including the Dantzig Dissertation award from INFORMS, Miller and Ramey Fellowships at Stanford University, Chevron’s Excellence in Reservoir Management award, and a SIAM award for excellence in research. Sarma holds a PhD degree in petroleum engineering, a PhD minor degree in operations research from Stanford University, and a bachelor of technology degree from the Indian School of Mines. He currently serves on committees for the SPE Reservoir Simulation Conference and the EAGE European Conference on the Mathematics of Oil Recovery and on the JPT Review Board.|