Oil and gas companies are starting to invest more in the energy transition and establish emissions-reduction goals, such as an end to routine gas venting and flaring, with some going as far as setting net-zero goals by mid-century. A wide range of climate technologies with varying degrees of maturity levels are needed to pave the road to net zero. These include electrification and grid decarbonization, advances in battery technology, blue and green hydrogen fuels, bioenergy, carbon capture use and storage, and mitigating emissions of potent greenhouse gases such as methane.
The COVID-19 pandemic has helped accelerate the pace of the digital transformation in the oil and gas industry. Digitalization is, in effect, a part of the broader energy transition that is occurring in the industry. This includes a move from on-premises data centers to the cloud, building digital twins of physical assets, process automation using the Internet of Things (IoT), leveraging reams of data from oil and gas operations for artificial intelligence/machine leaning (AI/ML) applications, cloud-based high-performance computing for applications such as seismic imaging for carbon capture and storage, and predictive maintenance to fix leaky equipment to reduce the environmental footprint of operations. These technologies serve to improve productivity, increase operational efficiency, reduce downtime, increase cost savings, and reduce the carbon intensity of operations.
The International Energy Agency report “The Oil and Gas Industry in Energy Transitions” states that reducing methane leaks to the atmosphere is the single most important and cost-effective way for the industry to bring down these emissions. This is a domain that can benefit significantly from the use of AI/ML techniques for leak detection and remediation (LDAR) efforts. ML techniques such as computer vision and anomaly detection can be used to identify both large and localized methane leaks from remote-sensing data and data streaming in from IoT sensors in the field. A combination of data modalities, with varying spatiotemporal resolutions, together with appropriate AI/ML technologies, would be essential for an effective methane LDAR program.
As companies look to reduce their Scope 1, 2, and 3 emissions, breaking down data silos and establishing data standardization with common data models becomes critical in systems integration to develop an optimal emissions-reduction strategy. A seamless flow of information will enable the generation of high-fidelity data sets, which can be used to lower the operational footprint and drive business effects with AI solutions. With cloud-enabled technologies, driven by the application of ML and deep learning, companies can combine speed of implementation with scalability to accelerate their energy-transition efforts.
I would like to invite readers to review the selection of papers to get an idea of various applications in the upstream oil and gas space where ML methods have been used. The highlighted papers cover the use of transformer-based models to predict oil production, the use of data analytics to study parent/child well relationships in shale plays, and the use of convolutional neural networks in core analysis.
This Month’s Technical Papers
Transformer-Based Models Aid Prediction of Transient Production of Oil Wells
Data Analytics Study Clarifies Parent/Child Well Relationships in Unconventional Basins
Machine Learning Brings Vast Core-Analysis Legacy Data to Life
Recommended Additional Reading
SPE 207744 Accelerating Subsurface Data Processing and Interpretation With Cloud-Based Full Waveform Inversion Systems by Sirivan Chaleunxay, Amazon Web Services, et al.
SPE 205443 Natural-Language Processing and Text-Mining Approaches in Production-Shortfalls Analytics: Methodology, Case Study, and Value in the North Sea by Edgar Bernier, Total Denmark, et al.
URTEC 208367 Real-Time Applications for Geological Operations: Repeatable AI Use Cases by Alfio Malossi, Eni, et al.
Yagna Oruganti, SPE, is a senior data scientist with Microsoft in Houston. At Microsoft, her area of focus is artificial-intelligence and machine-learning applications for the energy industry, with a specific focus on sustainability. During the past 12 years, Oruganti has held various positions as research scientist, reservoir engineer, and data scientist. Her work experience includes 7 years at Baker Hughes, where she focused on reservoir simulations for unconventional shale plays and on machine learning for various subsurface applications. Oruganti has authored or coauthored more than 14 technical publications in the areas of reservoir engineering, carbon sequestration, and data analytics and machine learning in the oil and gas industry. She holds a bachelor’s degree in chemical engineering from the Indian Institute of Technology Madras and a master’s degree in petroleum engineering from The University of Texas at Austin. She is a member of the JPT Editorial Review Board and serves on the SPE Data Science and Engineering Analytics Advisory Committee. Oruganti can be reached at yagna.oruganti@microsoft.com.