- Home
- Conferences
- Conference Proceedings
- Conferences
EAGE Conference on Digital Innovation for a Sustainable Future
- Conference date: September 13-15, 2022
- Location: Bangkok, Thailand
- Published: 13 September 2022
1 - 20 of 26 results
-
-
Aggregation and Assimilation of Complex Laboratory Data to Remove Data Silos
Authors M. Crookes and C. HantonSummaryA key element of digital transformation is the promotion of actionable and accessible subsurface data. For most operators, scarcity of data is not a problem as much as a lack of trust in data quality and availability of tools to access and utilize that information in an effective manner to drive the business forwards. This paper details how - via collaboration with subject matter experts at a major European operator - a rich, varied, yet historically under-utilized dataset was able to power new insights into the subsurface.
-
-
-
Fast Well Control Optimization Using Machine Learning Based Proxy Models
Authors C.S.W. Ng and A. Jahanbani GhahfarokhiSummaryDevelopment of data-driven models has been one of the epitomes of the growth of digitalization in the oil and gas industry. These models can be established by using machine learning techniques. In reservoir engineering, they have been employed to solve reservoir management problems, including production optimization, history matching, and geological uncertainty quantification. One of the benefits of such data-driven models is the lower computational cost while preserving the accuracy of results. In this work, we have demonstrated the workflow for the construction of data-driven models (which are termed “proxy models” here) that act as a substitute of numerical reservoir simulation to conduct the well control optimization. For illustrative purposes, we have utilized the OLYMPUS model as benchmark. The results yielded from this work showcase the reliability of implementing the proxy models in resolving the reservoir engineering problems.
-
-
-
Carbon Dioxide Emission Monitoring Based on Prediction of Gas Fuel Rate using Machine Learning
By M.X. LeeSummaryCompanies have joined the effort in GHG emission by aligning their company objectives in achieving net zero emissions by 2050, to fulfill the Paris Agreement. The ambitious goal of Paris Agreement could be achieved only if change happen faster. This could be done starting from monitoring and disclosing the CO2 emission from energy consumed in platform.
We could track carbon footprint based on historical production data, however there is limited user interactive tool available for the operators to monitor their CO2 emission. This study focused on the scientific based commitment to the net zero ambition of oil and gas industry, by calculating the CO2 emission using the predicted fuel rate and flare rate.
The objective of this study is to use the optimal machine learning model in monitoring the fuel rate and gas flare rate which is affecting the amount of CO2 emitted. The calculated CO2 emission based on the forecasted energy consumption, would be visualized for future decision making and carbon emissions hotspot identification.
-
-
-
Reinventing Digital Subsurface of Operator through DELFI PTS cloud digital solution at Enterprise Scale
Authors Y. Kang and T.T.T. NguyenSummaryThe latest 12th Malaysia Plan is directing the nation aggressively towards low-carbon nation. Current application system and infrastructure for most of the operators simply may not be able to support this green growth. This will cause delay in planning and execution along the value-chain and risking most operators in Malaysia to miss their decarbonization targets. These challenges can be solved by migrating operators’ aging architecture and workflows completely onto DELFI E&P cognitive environment, a new modern cloud-based solution which unlocks significantly higher computing and simulation power leveraging on latest cutting-edge technology.
Through project transition planning, petabytes of data including enterprise applications and databases can be migrated from on premise to cloud. Strengthened by a robust enabling environment in cloud E&P environment, petrotechnical experts can be onboarded with minimal interruption to their technical delivery included their complex key integrated workflows. In fact, higher efficiency was recorded with users’ satisfaction scores regularly exceeding 90% from deployment surveyed.
Cloud digital solution has proven to significantly accelerate its efforts towards decarbonizing its assets and build a strong, solid foundation for a fully digitalized end-to-end asset modelling and management platform. This will unlock new opportunities to leverage on other technologies such as AI to study new possibilities for production optimization, cost reduction and sustainable development.
-
-
-
Application of Hough Transform in Fracture Lineament Extraction
Authors S. Utitsan, S. Chantraprasert and W. PromrakSummaryWe demonstrate the application of Hough transform as a tool to automatically detect and digitize fracture lineaments from seismic attribute map of a carbonate reservoir and outcrop photo in Thailand. The tool greatly improves the efficiency in identifying and characterizing fractures, which are critical for hydrocarbon exploration and production in tight reservoir. It can extract hundreds of fracture lineaments in a few seconds, while the manual picking would take at least a day to finish such task.
-
-
-
Deep Learning Technologies to Assist the Processing of Geological Data: a Support to Optimize E&P Workflows?
Authors D. Bonté, A. Bouziat, M. Ferraille, A. Lechevallier, A. Koroko and S. RohaisSummaryThe use of Deep Learning on unstructured data, like images and text, has recently made some significant advancement both in capability but also on simplicity of utilisation. As a contribution to E&P, we present three practical cases where these technologies are producing an excellent contribution to geoscience. In this study, we would like to highlight how Deep Learning, and more specifically computer vision, can support geoscientists in their activities. The first case is an identification tool that allow to classify macroscopic rocks sample into lithological classes, useful for both support to non-geoscientists in industrial setting and to promote geodiversity to citizens. The second case is a detection and categorization algorithm for microfossils on thin sections, which can be used on fast identification from microfossils or adapted for mineral to serve as lithological recognition. The third case is a lithofacies identification algorithm on core images that helps, based on expert identification, to perform an automatic recognition for the rest of the core. All these technologies can be easily adjusted to the needs of sustainable georessources and integrated to the E&P workflows.
-
-
-
Application of Tomographic Augmented Progressive Transfer Learning for Full Waveform Inversion
More LessSummaryThe lack of low-frequency data components has been a major obstacle in FWI applications for velocity model building. Many theoretical approaches have been proposed to extrapolate low-frequency components. Progressive transfer learning was proposed to solve the problem by using a deep learning-based approach to predict low-frequency components. In this paper, we demonstrate the effectiveness of the progressive transfer learning workflow by building a practical workflow and applying it to the field data.
-
-
-
Developing a user interface to define wettability in real time using digital techniques: proof-of-concept
Authors F. Amrouche, M. Short, M. Blunt and D. XuSummaryThe move towards digitalization of the oil industry is a must for the time and cost saving. All actual methods for the wettability determination have a negative impact on altering the in-situ wettability and longer time of determination. Our methodology provides instant determination without altering the initial wettability.
-
-
-
Optimization of Inflow Control Valves under Different Lifting and Injection Costs
Authors I.G.A.G. Angga, P.E.S. Bergmo and C.F. BergSummaryThis study focuses on optimizing the configuration of inflow control valves (ICVs) under different lifting/injection costs as this value will determine the level of importance of lowering water production and injection, and hence reducing energy use and CO₂ emissions. In this study eleven optimization scenarios are defined: each imposing a unique lifting/injection cost for its objective calculation. Herein we use a cut-off of the Norne full-field reservoir model, i.e., the E-segment. Producers with ICVs are modelled as multi-lateral multi-segment wells. For solving the optimization problems, we adopt the collaborative optimization framework which has the capability to share results of the heavy reservoir simulation among all search processes, thus enhancing the algorithm sampling size and its optimization performance. We particularly employ the collaborative version of genetic algorithm. Enforcing a higher lifting/injection cost in the optimization objective means putting a stronger emphasis on minimizing water production/injection, and this will usually produce an optimal ICV configuration that dampens the field water cut. Reducing the cross-sectional area of some ICVs will lower not only the water production and injection, but also the oil production. The reduction of oil production is smaller than the reductions of both water production and injection.
-
-
-
Acceleration of Calculations of Integrated Fields Using Machine Learning Methods
Authors K. Pechko, I. Senkin, N. Brovin and E. BelonogovSummaryThis article proposes a new approach to well modeling in integrate modelling of oil and gas fields. Using machine learning describe the well as the dependence of bottomhole pressure on fluid flow rate, water cut, GOR and wellhead pressure.
The well model was implemented using the “Random Forest” assembly of “Decision Trees” using the gradient boosting technique. The model was tested on synthetic and real data from various fields.
The proposed approach outperforms linear interpollation of VFP tables in terms of speed and prediction score.
-
-
-
Large-scale Drilling Dynamics Simulations Powered by Cloud
By Y. ShiSummaryDrillPlan is armed with powerful domain-knowledge-and-machine-learning-based applications, including a realtime three-dimensional drilling simulator, the IDEAS engine. To optimize the drilling parameters and BHA design, a large number of drilling simulations are required. On average, it takes 4 hours to run a single full-scale IDEAS simulation. Previously, we have servers on-premises to tackle the computations. It requires recurring fees for maintenance, and continuous efforts on all-level (including IaaS, PaaS, and SaaS) development, test, and deployment. However, the local clusters could not be scaled easily as the requested amount varies. Therefore, it was either losing opportunities or wasting resources. Now, a novel workflow is established taking advantage of the cloud technologies. The computing resources can be quickly and easily scaled in and out, up and down, corresponding to the requests from clients. The pay-as-use model significantly reduced the cost as well as the lead time from the request received to the report delivered.
-
-
-
The Art and Science of Integrated Data Visualization and Opportunity Generation
By W.D. GanSummaryLet’s take a break from our daily high-tech race, zoom out a little and fallback. In this paper, we would share a case study with our integrated data strategy (A tweak of classical way) – where we would visually present some of the simple yet effective way how we condense our highly complex information (multi-disciplinary data: PP, Geological, Geophysical and RE production data) into the most condense form of visualizations that would pack the most information in a simplistic manner, aiding interpreter to conceptualize geology, screening for infill/NFE opportunity, while bridging communications - giving ability to interpreters to connect the dots from the most fundamental perspective of geology and rock physics, and how our integrated data visualization strategy could bridge both worlds where Interpreter can intuitively analyze and describe these visuals, and how insights and opportunity is generated in a simplistic, classical manner.
Method and/or Theory
- Problem Statement - The complex nature of GnG dataset
- Methodology – Fundamental Rock Physics to Geomorphology Visualization
- Application – Integrated Dataspace for opportunity screening and Visualization
- Integrated Seismic to Well calibrations
- Integrated Litho-Fluid Atlases
- Classical multi-attribute visualization, validation and interpretations
- Result – Opportunity and Way Forwards
-
-
-
A Single Stop Data-driven Decision Premises for Execution Phase of Gulf of Thailand Drilling Projects
Authors K. Laitrakull, D. Tungthansamma, R. Sampoonachot, C. Boonmeelapprasert and P. YuhunSummaryThe application was developed by user-centric agile approach (design thinking combined with scrum methodology) to improve the decision quality and streamline execution well factory process of drilling operations in Gulf of Thailand which normally encounters 150+ drilled wells annually. This was a cross-functional attempt to integrate all required data from the subsurface, drilling and planning team. The data collaboration brings people, technology, and data together to break down the silos to gain trust and utilized to build four main features - 1) Project Summary and Lookback, 2) Project and Well Performance Dashboard, 3) Real-time Drilled and Undrilled Reserves, and 4) Decision Making Functions for Operational Issues. The application was developed and tested for feedback for a total of 14 sprints (two weeks per sprint). This application is now a main tool in drilling operations in Thailand business units and truly improves decision quality, de-risk investments, and maximizes the return. The tangible benefit is to reduce the rathole section of 148 wells annually which is equivalent to $1.5 million of cost saving. The reduction of nonproductive activities also reduces the CO2 discharge to the atmosphere. In addition, the recycling work is significantly minimized.
-
-
-
Interactive Interpretation for Deterministic Reservoir Characterization
Authors A. Ab Fatah, L. Weston, M. Bawden, K.A. Zamri and W.L. LiewSummaryThe objective of this case study is to predict the extension of sand reservoir intervals to guide the location of infill wells and their trajectories. The reservoirs are deposited in fluvial system of channel point bar and deltaic complexes. The field suffers the problem of uncertain reservoir connectivity and complex fluid distribution due to multiple sedimentation processes and different rock provinces. An efficient approach of machine assisted interactive classification was taken to effectively classify the lithologies and fluids of different intervals to assist in infill wells placement based on the seismic and its attribute volumes available.
-
-
-
Automatic Seismic Interpretation Mistie Identification and Correction
Authors W. Seeyangnok, W. Inthung and W. PromrakSummaryWe have proposed the methodology to automatically identify, and correct seismic interpretation mis-tie based on statistical comparison of crossing seismic interpretation. The results are quite satisfying as the tool can correct most of interpretation mis-tie errors in a few minutes, while manual correction would take at least a week. Having an automated seismic interpretation mis-tie corrector yields a significant business impact as we could speed up seismic interpretation twice as fast, which would accelerate time to market and raise project net present value.
-
-
-
Developing a Smart EOR Monitoring System for Thailand’s Largest Onshore Oilfield
SummaryA new EOR monitoring system was internally developed for the large-scaled polymer injection projects in the Thailand’s largest onshore oilfield. The EOR monitoring system comprises an EOR monitoring dashboard and an EOR daily report dashboard, which improve the work process, save manpower in data preparation and analysis, and more importantly provide the insights of ongoing flood performance leading to improved decision making and prompt actions. This system helps assure and maximize the incremental oil gain from EOR.
-
-
-
Utilizing Machine Learning to Gain Geological Insights through Unstructured Data for Sustainable Exploration Activities - Brazil Pre-Salt
Authors T. Looi, F. Baillard, N.M. Hernandez, H. Minhat, T.S. Tuan Ab Rashid and M.D.M. RamlanSummaryUnderstanding the basin regional trends and identifying the anomalies is a crucial background research during basin exploration activities. One way to gain a sound knowledge about the geology and the exploration history is to analyse the vast amount of data accumulated over the years in an unstructured manner. A sustainable data driven strategy leveraging on the latest advancement of Machine Learning (ML) and Analytics is applied on vast amount of unstructured data. By highlighting the data driven strategy, the paper demonstrates such a strategy applied to pre-salt carbonates prospects located in the Campos and Santos Basins, offshore Brazil. The research shows the effectiveness of using ML/AI technologies and Analytics to mine through the vast amount of unstructured data and gain insights related to the regional trends and anomalies of important geological, reservoir and production parameters to minimize the risk of exploration and reduce carbon footprint.
-
-
-
Digital Field Management of Sand Control Monitoring (SPCM) Using Web-Based Interfaces to Improve Operation Efficiency
Authors C. Chaiyasart, P. Toprasert, P. Sooksawat, W. Pongsripian, S. Dhadachaipathomphong, S. Chang and F. NazirSummaryFor digital field management in the oil and gas industry, digital transformation opens up a world of new possibilities. The objective is to increase operation efficiency of sand monitoring and control by using web-based interfaces to reference with operation efficiency improvement. Vardoulakis I. and et al (1996) were the first proposed the hydro-erosion model based on rigid porous media in 1996. The erosion models were extended to include the effect of the deformation of porous media in a consistent manner ( Wan and Wang, 2002 ) and geomechanics in a consistent manner ( Wang et al., 2004 ). Methodology was starting from data collection, conducted Simplified Representative Elementary Volume (SREV), model calibration, monitoring, integration of well, facility for prediction of sand accumulation. In addition, a data driven was imbedded to integration as well as workflow automation and user surveillance dashboard in web-based interfaces. The calibration process has been proved the models results with greater than 87% accuracy of sand production. It was found that SREV model approach to sand prediction and control monitoring (SPCM) successful gave an improvement in operations efficiency by reducing time spent on manual analysis and decision-making process through digital web-based dashboards.
-
-
-
A Quantitative Bayesian Implementation on Assisted Machine Learning Framework for Lithology Prediction on Well Log Data
Authors A. Satria, M. Suryapranata, T. Rusady, M. Mordekhai and C. ChaiyasartSummaryLithology prediction is one of the most important processes in petrophysical workflow since it is useful for knowing the prospective reservoir zone in the target well. Unfortunately, this process sometimes takes a long time and results in inaccurate interpretations due to the massive amount of data and the inconsistency in manual interpretation. We present an assisted lithology interpretation framework with additional feature to compute prior and posterior probabilities during lithology prediction in order to help geoscientists if there are some irrelevant prediction results. We use various references to oil and gas basins data around the world resulting more than 60 pre-built models included in this framework. The framework can select model automatically based on the similarity between the well log curve in test data and references data. The data used in this study is from one of the most productive oil and gas field that has a varied number of wells and lithology. This application is proven to be able to provide reliable results by producing F1 score above 0.6. This framework can also assist geoscientists to interpret exploration wells that do not yet have a valid lithology label.
-
-
-
High Resolution Fluid Based Prospect Imaging Using Elastic Cloud Computing Power
Authors D. Das, D. Chakraborty and J. MukherjeeSummaryThe technical abstract is aimed at highlighting an innovative approach to reduce the sub-surface uncertainty for prospect imaging through a fluid simulation model based approach in integration with advanced geophysical properties to evaluate the preferred migration scenario coupled with the seal integrity analysis. This approach helps in mitigating the risk associated with seal and charge in addition to the trap and reservoir condition to augment the existing conventional approach for prospect evaluation. This modeling approach integrates the data from regional scale to the prospect scale through a seamless connection through scalability. But, in order to capture the original resolution of the model, the key challenge comes in terms of the slow and high computing power intensive Darcy migration model and limitation in hardware capability. In this abstract we have highlighted the cloud elasticity feature which helps in retaining the original resolution of the model without compromising the geological consistency. Additionally, the advanced Invasion Percolation migration model has been used to have the robust migration scenario in lesser time and investigate uncertainty analysis for more informed decision.
-