Machine-Learning in Oil and Gas Exploration: A New Approach to Geological Risk Assessment

Author(s):  
F. Silva ◽  
S. Fernandes ◽  
J. Casacão ◽  
C. Libório ◽  
J. Almeida ◽  
...  
Nafta-Gaz ◽  
2021 ◽  
Vol 77 (5) ◽  
pp. 283-292
Author(s):  
Tomasz Topór ◽  

The application of machine learning algorithms in petroleum geology has opened a new chapter in oil and gas exploration. Machine learning algorithms have been successfully used to predict crucial petrophysical properties when characterizing reservoirs. This study utilizes the concept of machine learning to predict permeability under confining stress conditions for samples from tight sandstone formations. The models were constructed using two machine learning algorithms of varying complexity (multiple linear regression [MLR] and random forests [RF]) and trained on a dataset that combined basic well information, basic petrophysical data, and rock type from a visual inspection of the core material. The RF algorithm underwent feature engineering to increase the number of predictors in the models. In order to check the training models’ robustness, 10-fold cross-validation was performed. The MLR and RF applications demonstrated that both algorithms can accurately predict permeability under constant confining pressure (R2 0.800 vs. 0.834). The RF accuracy was about 3% better than that of the MLR and about 6% better than the linear reference regression (LR) that utilized only porosity. Porosity was the most influential feature of the models’ performance. In the case of RF, the depth was also significant in the permeability predictions, which could be evidence of hidden interactions between the variables of porosity and depth. The local interpretation revealed the common features among outliers. Both the training and testing sets had moderate-low porosity (3–10%) and a lack of fractures. In the test set, calcite or quartz cementation also led to poor permeability predictions. The workflow that utilizes the tidymodels concept will be further applied in more complex examples to predict spatial petrophysical features from seismic attributes using various machine learning algorithms.


2011 ◽  
Vol 148-149 ◽  
pp. 1000-1006 ◽  
Author(s):  
Chang Yong Wang ◽  
Hong Huan Zhang ◽  
Meng Lan Duan

That the oil and gas exploration and development is extending into deep water proceeds the rapidly shift to subsea production system. However, complex subsea equipment and frequency offshore accidents aroused the concern on the risk assessment of subsea system. The paper illustrates the hazard aspects which should be focused on in the subsea equipment compared with the surface equipment. The hazards identification and risk analysis on subsea X-tree system is carried out. A general risk-prevent process of subsea X-tree system is illustrated, so does the reliability analysis process. Besides, some commendations on subsea detection and maintenance are presented in the paper.


2008 ◽  
Vol 11 (05) ◽  
pp. 858-865 ◽  
Author(s):  
Emad A. Elrafie ◽  
Jerry P. White ◽  
Fatema H. Awami

Summary Saudi Aramco strives to implement new and innovative techniques and approaches to assist in meeting the industry's increasing challenges. One of these is the new study approach, "the Event Solution," which leads to better synergy among different stakeholders and enables faster decisions that fully encompass the complex uncertainties associated with today's gasfield and oilfield developments. The Event Solution is a short, intensively collaborative event, which compresses major decision cycles, embraces uncertainty, and provides a wider range of alternative solutions. The Event Solution approach has been implemented successfully on 24 major studies worldwide, with the last eight projects conducted on Saudi Aramco megareservoirs. The concept is simple: Identify the most important study objective, and focus the collective skills and creativity of a team of experts to meet the study objective in a special event that lasts just for 2 months. The team is enabled with the latest hardware and software technologies in a large team room, specially designed for collaboration, where they can work together. A facilitator leads the team to implement the Event Solution process that helps the team to see "the big picture" and understand what matters to the bottom line. The team composition is enriched with representatives from all of the stakeholders (including technical experts, management, facilitators, and sometimes government and joint-venture partner's representatives) so the results can be concluded and implemented immediately, with maximum buy-in. The Event Solution process includes detailed uncertainty analysis and risk-assessment workflows that have been implemented successfully in many events. The most important deliverable of the Event Solution, however, is that all the stakeholders develop a clear and common understanding of the critical uncertainties, project risk, and the agreed plans to move forward--the decisions. This volume of work, which traditionally requires years, is completed in 2 months on average using the Event Solution process. This paper presents the elements and processes of this new approach. Critical elements to a successful Event Solution include software, workroom, team members, and a facilitator. Once the elements are in place, the facilitator leads the team through processes that include project preparation, parallel workflows, uncertainty analysis, critical information plans, project risk assessment, and mitigation plans. Note that uncertainty analysis is not a simple byproduct of the study, but an integral component of success. Introduction The oil and gas industry spends more than USD 130 billion in capital and exploration expense worldwide each year (OGJ 2000a, 2000b) on complex and uncertain ventures, highlighting the significant added value that can be achieved through processes that create synergy while reducing the decision cycle time. Warren (1994) notes that the success of an individual team can be variable when he states, "the fundamental idea of cross functional teams and goals appears to surface about every 10 years with a new label. Usually, attempts to implement this concept in the E&P business ended with utter failure for a variety of reasons" (Ching et al. 1993) The Event Solution extends the crossfunctional-team concept by formalizing key success factors:identifying the most important study objective,focusing the collective skills and creativity of a team of experts on meeting the study objective, andcollaborating in a special event that lasts 2 months rather than years. In the 1980s, the concept of asset teams was introduced by E&P companies around the globe to downsize and streamline operations. Unfortunately, integrated software was not mature enough at that time to enable real integration of the asset-team members. As integrated software became available and hardware became more powerful in the early-to-mid 1990s, asset teams began to achieve more success. By the late 1990s, common processes were adapted by most major oil and gas companies to ensure consistency and repeatable success across teams. Highly formalized processes, often employing gatekeepers, were developed to integrate the management (decision makers) and technical (asset) teams. Although integrated software and formalized processes enhanced the quality of the decision process, generating fully synergized analyses from a wide variety of data and skills was still a lengthy process. Furthermore, the decision makers often received different messages from different disciplines, which may not have incorporated a comprehensive image of uncertainty surrounding the decision. Between 2004 and 2005, several synergized study approaches (Williams et al. 2004; Landis and Benson 2005) were introduced to the industry as a means to bridge the gap between the technical asset teams and decision makers. These approaches were set either as workshop-style projects or facilitated teams focused on a set of business objectives. In 2001, the Event Solution approach was introduced to the industry (Ghazi and Elrafie 2001). Like asset teams, the Event Solution is a group of multidiscipline professionals working on a dedicated project. The Event Solution focuses on creating better synergy among all stakeholders (asset teams, managers, decision makers, and partners) by enabling faster decisions that fully encompass the complex uncertainties associated with today's projects. The focus is on specific, well-stated business objectives aligned to company strategy. The team follows a process in which each team member assesses uncertainties within his/her own analysis, with outputs subsequently rolled up into a studywide uncertainty assessment.


2014 ◽  
Vol 919-921 ◽  
pp. 500-506
Author(s):  
Fei Li ◽  
Guang Zhang

As the leading of oil and gas exploration and development, oil-gas drilling operations with high investment, high technology, and other industries interchange and perennial wild characteristics, there are various HSE risks during operation. Constructing HSE risk assessment system of oil-gas drilling operations, using AHP to construct indicators were analyzed and compared, and calculate the index weight. Then build fuzzy evaluation matrix based on expert evaluation method, get fuzzy evaluation result is "high risk". Finally, from four aspects (people, object, environment, and management) proposed HSE control measures.


2020 ◽  
Author(s):  
Leonardo Guerreiro Azevedo ◽  
Renan Souza ◽  
Raphael Melo Thiago ◽  
Elton Soares ◽  
Marcio Moreno

Machine Learning (ML) is a core concept behind Artificial Intelligence systems, which work driven by data and generate ML models. These models are used for decision making, and it is crucial to trust their outputs by, e.g., understanding the process that derives them. One way to explain the derivation of ML models is by tracking the whole ML lifecycle, generating its data lineage, which may be accomplished by provenance data management techniques. In this work, we present the use of ProvLake tool for ML provenance data management in the ML lifecycle for Well Top Picking, an essential process in Oil and Gas exploration. We show how ProvLake supported the validation of ML models, the understanding of whether the ML models generalize respecting the domain characteristics, and their derivation.


2020 ◽  
Author(s):  
JingJing Liu ◽  
JianChao Liu

<p>In recent years, China's unconventional oil and gas exploration and development has developed rapidly and has entered a strategic breakthrough period. At the same time, tight sandstone reservoirs have become a highlight of unconventional oil and gas development in the Ordos Basin in China due to its industrial and strategic value. As a digital representation of storage capacity, reservoir evaluation is a vital component of tight-oil exploration and development. Previous work on reservoir evaluation indicated that achieving satisfactory results is difficult because of reservoir heterogeneity and considerable risk of subjective or technical errors. In the data-driven era, this paper proposes a machine learning quantitative evaluation method for tight sandstone reservoirs based on K-means and random forests using high-pressure mercury-injection data. This method can not only provide new ideas for reservoir evaluation, but also be used for prediction and evaluation of other aspects in the field of oil and gas exploration and production, and then provide a more comprehensive parameter basis for “intelligent oil fields”. The results show that the reservoirs could be divided into three types, and the quantitative reservoir-evaluation criteria were established. This method has strong applicability, evident reservoir characteristics, and observable discrimination. The implications of these findings regarding ultra-low permeability and complex pore structures are practical.</p>


Sign in / Sign up

Export Citation Format

Share Document