Prediction of Wells Productive Characteristics with the Use of Unsupervised Machine Learning Algorithms (Russian)

Balashov, Dmitry; Egorov, Dmitry; Belozerov, Boris; Slivkin, Stanislav

doi:10.2118/196857-ru

Cited by 3 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the application of artificial intelligence technology, 19−21 Balashov et al 19 can also provide corresponding emergency response and rescue measures for artificial intelligence through analysis and learning of accident cases. For example, Statoil in Norway uses artificial intelligence technology for safety monitoring and accident prevention of its offshore oil and gas platforms, effectively reducing the likelihood of accidents occurring.…”

Section: Application Status Of Artificial Intelligence In the Oil And...mentioning

confidence: 99%

Current Status and Prospects of Artificial Intelligence Technology Application in Oil and Gas Field Development

Wang,

Wei,

Xiong

et al. 2024

ACS Omega

View full text Add to dashboard Cite

Artificial intelligence technology will be increasingly applied in the oil and gas industry. The rapid development of artificial intelligence technology can solve problems such as high environmental sensitivity and complex production processes in the oil and gas industry. In recent years, emerging technologies represented by artificial intelligence have developed rapidly, assisting petroleum enterprises in digital transformation and intelligent upgrading. This article elaborates on the development trend of artificial intelligence technology. Based on the business scenarios and characteristics of the oil and gas industry, the application status of artificial intelligence technology in domestic and foreign petroleum technology service enterprises was summarized and analyzed. The application scenarios of artificial intelligence technology in the fields of dynamic analysis of oil and gas reservoirs, intelligent historical fitting, numerical simulation proxy models, and production plan optimization were analyzed with emphasis. Based on the problems and challenges faced in the development process of oil and gas reservoirs, it is proposed that petroleum enterprises should attach importance to the "three modernizations" innovation of data standardization, oil and gas field intelligence, and platform collaboration, in order to achieve more refined intelligent analysis and management of oil and gas reservoirs and quickly develop more targeted oil and gas reservoir development plans to assist in the intelligent transformation of oil and gas reservoir development. On this basis, prospects for future artificial intelligence technology are proposed, pointing out that the development of artificial intelligence technology will be faster and faster, and there will be higher demand for artificial intelligence technology in the construction of digital oil and gas fields in China in the future. The research results have important reference value for the development of the oil and gas industry.

show abstract

Section: Application Status Of Artificial Intelligence In the Oil And...mentioning

confidence: 99%

Current Status and Prospects of Artificial Intelligence Technology Application in Oil and Gas Field Development

Wang,

Wei,

Xiong

et al. 2024

ACS Omega

View full text Add to dashboard Cite

show abstract

SmartVessel-v2: A Faster, Better, Stronger, Safety Monitoring Solution for Marine Vessels

Egorov,

Sharan,

Tahiri

et al. 2023

Day 2 Tue, October 03, 2023

View full text Add to dashboard Cite

At ADIPEC'2022, SmartVessel, a vision-based HSE monitoring system, showed remarkable results in addressing HSE challenges in Marine Vessels. Despite its innovative features, SmartVessel was limited in its analysis of operational situation on working site as it relies solely on images, lacking temporal context. This deficiency leads to numerous false alarms and unnecessary operations interruptions. To address this issue, the new version of AI solution called SmartVessel-v2 was proposed. Despite the large number of advances, the main one can be called features tracking capabilities and temporal modeling. The brand-new version promises higher accuracy and efficiency, less false alarms and at higher running speed, increasing the safety of workers on-site. The goal of this paper is to present the recent advances of previously presented AI based HSE surveillance system. The paper covers new safety related business cases introduced in the solution and corresponding novel algorithms to process and analyze them. It also highlights overall advances of AI pipeline helped to achieve higher level of accuracy and outstanding reduction in number of false alarms. The last but not least, experience of solution large scale deployment for a whole fleet is described to share the knowledge about challenges, lessons learned and best practices how to handle this process in the optimal way. It can be extremely useful for all steps of design, development and deployment for any AI-based CCTV because it helps organize the process in correct way and avoid potential issues related to hardware and infrastructure, environmental, business and operational issues.

show abstract

Ensemble Machine Learning Assisted Reservoir Characterization Using Field Production Data–An Offshore Field Case Study

et al. 2021

View full text Add to dashboard Cite

Estimation of fluid saturation is an important step in dynamic reservoir characterization. Machine learning techniques have been increasingly used in recent years for reservoir saturation prediction workflows. However, most of these studies require input parameters derived from cores, petrophysical logs, or seismic data, which may not always be readily available. Additionally, very few studies incorporate the production data, which is an important reflection of the dynamic reservoir properties and also typically the most frequently and reliably measured quantity throughout the life of a field. In this research, the random forest ensemble machine learning algorithm is implemented that uses the field-wide production and injection data (both measured at the surface) as the only input parameters to predict the time-lapse oil saturation profiles at well locations. The algorithm is optimized using feature selection based on feature importance score and Pearson correlation coefficient, in combination with geophysical domain-knowledge. The workflow is demonstrated using the actual field data from a structurally complex, heterogeneous, and heavily faulted offshore reservoir. The random forest model captures the trends from three and a half years of historical field production, injection, and simulated saturation data to predict future time-lapse oil saturation profiles at four deviated well locations with over 90% R-square, less than 6% Root Mean Square Error, and less than 7% Mean Absolute Percentage Error, in each case.

show abstract

Prediction of Wells Productive Characteristics with the Use of Unsupervised Machine Learning Algorithms (Russian)

Cited by 3 publications

References 4 publications

Current Status and Prospects of Artificial Intelligence Technology Application in Oil and Gas Field Development

Current Status and Prospects of Artificial Intelligence Technology Application in Oil and Gas Field Development

SmartVessel-v2: A Faster, Better, Stronger, Safety Monitoring Solution for Marine Vessels

Ensemble Machine Learning Assisted Reservoir Characterization Using Field Production Data–An Offshore Field Case Study

Contact Info

Product

Resources

About