Semiautomatic, Semantic Assistance to Manual Curation of Data in Smart Oil Fields

Chelmis, Charalampos; Zhao, Jing; Sorathia, Vikram; Agarwal, Suchindra; Prasanna, Viktor K.

doi:10.2118/153271-ms

Cited by 8 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also showed that transferring the developed model to a web-based platform can facilitate user/system interactions [110]. Big data were used to improve the reservoir modelling by predicting the affective parameters using artificial intelligence, machine learning and data mining technologies [111]- [115]. To improve the modelling of hydraulically fractured reservoirs, work presented in [116] used big data analytics technologies to analyse the production data.…”

Section: Decision Support Through Big Data Analyticsmentioning

confidence: 99%

Human Centric Digital Transformation and Operator 4.0 for the Oil and Gas Industry

et al. 2021

View full text Add to dashboard Cite

Working at an oil and gas facility, such as a drilling rig, production facility, processing facility, or storage facility, involves various challenges, including health and safety risks. It is possible to leverage emerging digital technologies such as smart sensors, wearable or mobile devices, big data analytics, cloud computing, extended reality technologies, robotic systems, and drones to mitigate the challenges faced by oil and gas workers. While these technologies are not new to the oil and gas industry, most of its existing digital transformation initiatives follow business or process-centric approaches, in which the critical driver of the technology adoption is the enhancement of production, efficiency, and revenue. As a result, they may not address the challenges faced by the workers. As oil and gas workers are among the essential assets in the oil and gas industry, it is vital to address the challenges faced by these workers. This paper proposes a human-centric digital transformational framework for the oil and gas industry to deploy existing digital technologies to enhance their workers' health, safety, and working conditions. The paper outlines the critical challenges faced by oilfield workers, introduces a system architecture to implements a human-centric digital transformation, discusses the opportunities of the proposed framework, and summarizes the key impediment for the proposed framework.

show abstract

Section: Decision Support Through Big Data Analyticsmentioning

confidence: 99%

Human Centric Digital Transformation and Operator 4.0 for the Oil and Gas Industry

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Other use cases include the ability to optimize enhanced oil recovery in real time from water flood, steam flood, and CO 2 flood (Angelo and Mershon, 2012), to monitor and control downhole equipment such as submersible pumps in real time (Medina et al, 2012), and to fully automate in real-time the curation of digital oilfield data (Chelmis, 2012).…”

Section: Fig 5: Real-time Streaming Integration Infrastructurementioning

confidence: 99%

Real-Time Streaming Data Management as a Platform for Large-Scale Mission Critical Sensor Network Applications.

Beggs¹,

Abadie²

2013

All Days

View full text Add to dashboard Cite

Oil and gas operators must process, analyze, and react in real time to increasing volumes and rates of streaming data in order to improve safety, compliance, and profit. For example, real-time analysis of streaming data from drilling rig sensors, intelligent wells, and digital oilfield installations enables early detection of drilling hazards and pending equipment failures, thereby reducing rig time, intervention, and shut-ins.Data problems include the need for real-time integration of operational systems and an inability to maintain accurate and current information across all systems and data warehouses. Poor integration leads to duplication of data and systems, and a lack of visibility across all monitored assets, resulting in the delayed identification of the root cause of problems. This paper presents a streaming data architecture that is capable of processing and analyzing rig data and smart oilfield data in real time. Further, the architecture supports the continuous, streaming integration of any and all of an organization's sensor data, operational platforms, and data warehouses. The approach aggregates and analyzes live, streaming data on the fly, without the need to store the data first. Large volumes of high velocity streaming data in any format and from all sources can be processed continuously and delivered to existing operational systems and data warehouses.The architecture increases efficiency by removing data silos and by ensuring that all systems and data warehouses are kept accurate and up to date in real time. This results in faster decisions that are better informed and based on consistent, accurate, and timely information. Achieving new levels of operational efficiencyThe oil and natural gas industry faces challenges to increase production, reserves, and profit while becoming safer and complying with ever more stringent environmental regulation. Global oil production capacity is forecast to grow to 102 million barrels a day by 2017, an annual average increase of 1.5 million barrels a day (Kent, 2012), and demand for liquefied natural gas has doubled in the last decade, and is forecast to double again over the next decade (The Economist, 2012). Meeting objectives such as these will require the industry to attain new levels of operational efficiency.

show abstract

“…During annotation [16], we annotate terms based on the domain ontology, and represent the terms as ontology instances belonging to corresponding ontology classes. For example, since the terms "fslt" is used to represent the algorithm name "Full_Salt", the ontology class "Full_Salt" should be used for annotation.…”

Section: Annotationmentioning

confidence: 99%

Recovering Linkage Between Seismic Images and Velocity Models

Zhao¹,

Chelmis²,

Sorathia

et al. 2012

SPE Western Regional Meeting

Self Cite

View full text Add to dashboard Cite

Seismic processing and interpretation involves resource intensive processing in the petroleum exploration domain. By employing various types of models, seismic interpretations are often derived in an iterative refinement process, which may result in multiple versions of seismic images. Keeping track of the derivation history (a.k.a. provenance) for such images thus becomes an important issue for data management. Specifically, the information about what velocity model was used to generate a seismic image is useful evidence for measuring the quality of the image. The information can also be used for audit trail and image reproduction. However, in practice, existing seismic processing and interpretation systems do not always automatically capture and maintain this type of provenance information.In this paper, by employing state-of-the-art techniques in text analytics, semantic processing and machine learning, we propose an approach that recovers the linkage between seismic images and their ancestral velocity models when no provenance information is recorded. Our approach first retrieves information from file/directory names of the images and models, such as project names, processing vendors, and algorithms involved in the seismic processing and interpretation. Along with the creation timestamps, the retrieved information is associated with corresponding images and models as metadata. The metadata of a seismic image and its ancestral models usually satisfy certain relationships. In our approach, we detect and represent such relationships as rules, and a matching process utilizes the rules and retrieved metadata to find the best-matching images and models.In practice, images' and models' file names often do not adhere to naming standards and they are stored without following well established record keeping practices. Users may also use different terms to express the same information in file/directory names. We employ Semantic Web technologies to address this challenge. We develop domain ontologies with OWL/RDFs, based on which we provide an interactive way for users to semantically annotate terms contained in file/directory names. All metadata used by the image-model matching process is represented as ontology instances. Matching can be performed using the standard semantic query language. The evaluation results show that our approach can achieve satisfying accuracy.

show abstract

Semiautomatic, Semantic Assistance to Manual Curation of Data in Smart Oil Fields

Cited by 8 publications

References 31 publications

Human Centric Digital Transformation and Operator 4.0 for the Oil and Gas Industry

Human Centric Digital Transformation and Operator 4.0 for the Oil and Gas Industry

Real-Time Streaming Data Management as a Platform for Large-Scale Mission Critical Sensor Network Applications.

Recovering Linkage Between Seismic Images and Velocity Models

Contact Info

Product

Resources

About