Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
Results
Neural Network-Assisted Clustering for Improved Production Predictions in Unconventional Reservoirs
Cornelio, Jodel (University of Southern California) | Mohd Razak, Syamil (University of Southern California) | Cho, Young (University of Southern California) | Liu, Hui-Hai (Aramco Americas) | Vaidya, Ravimadhav (Aramco Americas) | Jafarpour, Behnam (University of Southern California)
Abstract Given sufficiently extensive data, deep-learning models can effectively predict the behavior of unconventional reservoirs. However, current approaches in building the models do not directly reveal the causal effects of flow behavior, underlying physics, or well-specific correlations; especially when the models are trained using data from multiple wells of a large field. Field observations have indicated that a single reservoir does not have similar production behaviors. This makes pre-filtering the data to build local models that capture region specific correlations more pertinent than a single global model that will provide averaged-out predictions from different correlations. In this work, we investigate a sophisticated network architecture to expedite the clustering process by training the global model. We utilize attention-based (transformer) neural networks for the input data before mapping to the target variable to extract the attention scores between well properties and the production performance. We leverage the interpretability from these attention-based models to improve the prediction performance for data-centric models derived from clustered datasets. We show the benefits of building local models that are more accurate as they learn correlations that are more region/data specific. Specifically, by utilizing the attention mechanism, we can separate and curate data subsets to train local models, improving the prediction performance by reducing the variability in the entire field.
- Geology > Geological Subdiscipline (0.68)
- Geology > Petroleum Play Type > Unconventional Play > Shale Play (0.47)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock > Mudrock > Shale (0.31)
Abstract West Sak is a shallow viscous oil reservoir located partially within the Kuparuk River Unit on the North Slope of Alaska. The poorly consolidated reservoir is prone to sand production, leading to a significant risk for the development of void space conduits, locally known as matrix bypass events (MBEs). MBEs result in pattern breakage and lost production capacity, and this needs to be accounted for in production forecasting. In this study, a data-driven analysis is performed to identify factors that cause differential risk for MBE formation in each well. This analysis is then used to inform the creation of a tool that determines the expected production impacts of future MBEs and derates the forecast accordingly. The well patterns and MBE history in the West Sak reservoir are analyzed for differential risk based on sand geomechanics and producer/injector well completions. Specifically, the B sand was found to have the highest MBE risk due to its lower geomechanical strength, the D sand was found to have a significant yet lesser risk, and the A sand was found to have negligible risk. MBE risk is greater for patterns with horizontal production laterals without sand control and is negligible for horizontal producers with sand-exclusion screens or vertical producers. MBE risk is reduced when vertical injectors are used instead of horizontal injection laterals. This history is used to inform the development of MBE risk type curves based on the fatigue life distribution family of curves. These curves are used as input into an MBE deration forecasting tool, which produces a range of risk-informed MBE schedules. Based on each schedule, the tool "breaks" and "repairs" patterns accordingly, determining production losses based on allocation to each pattern. These individual production loss forecasts are then averaged to provide the expected outcome for forecast deration attributed to MBEs. The tool was successful in developing reasonable deration expectations on a well-by-well basis. The work done offers a probabilistic workflow to predict well downtime due to MBEs. Data-driven evidence is provided for factors that influence MBE risking, providing a means to capture expected production losses. This evidence proves to be consistent with physical models of this enigmatic phenomenon and informs future development opportunities to mitigate this risk. The approach pursued here can be applied to other known risks to production.
- Geology > Geological Subdiscipline > Geomechanics (0.86)
- Geology > Geological Subdiscipline > Economic Geology > Petroleum Geology (0.70)
- Geology > Petroleum Play Type > Unconventional Play > Heavy Oil Play (0.46)
Abstract The current industry-wide practice of generating asset production curves is over-simplified and does not account for a lot of factors. This may lead to reporting errors and challenges in accurately and quickly quantifying well performance and asset potential. The present paper leverages Gaussian Mixture models and principal components to propose a new workflow for production modeling that incorporates all contributory factors while improving accuracy as well as speed. We began by selecting ~2600 gas wells with at least 2 years of production history. Exploratory data analysis was conducted on the geology, petrophysics, well design and completion characteristics of the wells. Gaussian Mixtures were selected as the clustering model due to their performance and synergies with factor distributions. Singular Vector Decomposition was then used to extract the most predictive Eigenvectors (principal components) for each cluster. Cluster-level production profiles are created from these eigenvectors. Thus, this process leverages the predicting factors as well as heterogeneity in each of the well’s production profiles while creating a representative type curve. RMSE values were calculated between the cluster-level predicted production profile and the individual well production curves. GMM-based models performed strongly with an RMSE of 0.146 for the training data and 0.746 for the test data. Additionally, type curves were calculated using more traditional means by taking monthly averages over the region as well as on an operator level. These type curves were then compared to the monthly production values for the populations they represent and the RMSE’s were calculated. The regional type curve had an RMSE of 9.3 and the company-level had an RMSE of 5.9, quantifying the marked improvement from our process. The proposed approach simplifies forecasting by providing rapid, reliable production heuristics for early-life wells without the need for complex, models that may need to be built individually from well to well. The proposed workflow builds upon existing literature on clustering and principal components, to create a novel workflow for reliable and more comprehensive type curve generation. Additionally, it adds to the existing knowledge-based by showcasing how multiple statistical techniques can benefit our modeling work within the industry as well as provide valuable support on early life production forecasting, which is a key challenge.
Abstract Artificial lift is the backbone of unconventional field production. Lifting oil and gas in an optimal manner and economically is one of the most challenging phases of field development with depleting reservoir energy. Traditional approaches of lift selection are not sufficient to manage unconventional wells effectively, with high decline rates initially. It is of prime interest to understand production behavior under different lift conditions since the decision on timing and design of lift method are crucial for optimizing the well performance. This paper presents an artificial-lift timing and selection (ALTS) methodology based on a hybrid data-driven and physics-based workflow to maximize the value of unconventional oil and gas assets. Our formulation employs a reduced physics model that is based on identification of Dynamic Drainage Volume (DDV) using commonly measured data (daily production rates and wellhead pressure) to calculate reservoir pressure depletion, transient productivity index (PI) and dynamic inflow performance relationship (IPR). Transient PI as the forecasting variable allows normalizing both surface pressure effects and considers phase behavior, thus reducing noise. The PI-based forecasting method is used to predict future IPRs and subsequently oil, water, and gas rates for any bottom hole pressure condition. The workflow allows estimating well deliverability under different artificial lift types and design parameters. The ALTS workflow was applied to real field cases for wells flowing under different operating conditions to optimize the best strategy to produce the well amongst several candidate scenarios. Transient PI and dynamic IPR results provided valuable insights on how and when to select different AL systems. The workflow is run periodically with everchanging subsurface and wellbore conditions against each candidate scenario with various pump models and other operating parameters (pressure, speed etc.). The method was applied to several wells in a hindcasting mode to evaluate lost production opportunity and validate the results. In certain cases, the optimal recommendation pointed to selecting a different artificial lift system than the chosen method in the field to significantly improve long term well performance. In addition, optimal artificial lift operating point recommendations are made for wells including optimal gas lift rates for gas lifted wells, optimal pump unit selection and speed for wells on ESP and SRP. The proposed method allows predicting future unconventional reservoir IPR consistently and has allowed continuous evaluation of artificial lift timing and selection scenarios for multiple lift types and designs in unconventional reservoirs. This can transform incumbent practices based on broad field heuristics, which are often ad hoc, inefficient, and manually intensive, towards well-specific ALTS analysis to improve field economics. Continuous application of this process is shown to improve production, reduce deferred production and increase life of lift equipment.
- North America > United States > Texas (0.28)
- North America > United States > Mississippi > Marion County (0.24)
- Reservoir Description and Dynamics > Unconventional and Complex Reservoirs (1.00)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Well performance, inflow performance (1.00)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Drillstem/well testing (1.00)
- (2 more...)
Abstract The development of shale plays requires accurate forecasting of production rates and expected ultimate recoveries, which is challenging due to the complexities associated with production from hydraulically fractured horizontal wells in unconventional reservoirs. Traditional empirical models like Arps decline are inadequate in capturing these complexities, and long-term forecasting is hindered by the challenges posed by 3 phase flow. In response, a new physics-augmented, data-driven forecasting method has been proposed that efficiently captures these complexities. The proposed PI-based forecasting (PIBF) method combines data-driven techniques with the physics of propagation of dynamic drainage volume under transient flow conditions observed by unconventional wells for a prolonged period. The model requires only routinely measured inputs such as production rates and wellhead pressure, and efficiently captures the trend shift in gas-to-oil ratio caused by free gas liberation in the near-wellbore region. By using material balance and productivity index models, the proposed approach can forecast well performance and handle changing operational conditions during the well's lifecycle. Compared to existing empirical or analytical methods like Arps decline and RTA, the proposed method yields more accurate forecasting results, while still using easily available inputs. Empirical methods like Arps decline have low input requirements but lack physical insights, leading to inaccuracies and inability to handle changing operational conditions. Pure physics-based methods like RTA and reservoir simulation require more input properties that are often difficult to obtain, resulting in a low range of applicability. Overall, the proposed method offers a promising alternative to existing methods, effectively combining data-driven techniques with physics-based insights to accurately forecast well performance and handle changing operational conditions in unconventional reservoirs.
- Europe (0.68)
- Africa (0.68)
- North America > United States > Texas (0.48)
- Geology > Petroleum Play Type > Unconventional Play > Shale Play (0.48)
- Geology > Rock Type (0.30)
Abstract Routinely analyzing producing well performance in unconventional field is critical to maintain their profitability. In addition to continuous analysis, there is an increasing need to develop models that are scalable across entire field. Pure data-driven approaches, such as DCA, are prevalent but fail to capture essential physical elements, compounded by lack of key operational parameters such as pressures and fluid property changes across large number of wells. Traditional models such as numerical simulations face a scalability challenge to extend to large well counts with rapid pace of operations. Other widely used method is rate transient analysis (RTA), which requires identification of flow regimes and mechanistic model assumptions, making it interpretive and non-conducive to field-scale applications. The objective in this study is to build data-driven and physics-constrained reservoir models from routine data (rates and pressures) for pressure-aware production forecasting. We propose a hybrid data-driven and physics informed model based on sparse nonlinear regression (SNR) for identifying rate-pressure relationships in unconventionals. Hybrid SNR is a novel framework to discover governing equations underlying fluid flow in unconventionals, simply from production and pressure data, leveraging advances in sparsity techniques and machine learning. The method utilizes a library of data-driven functions along with information from standard flow-regime equations that form the basis for traditional RTA. However, the model is not limited to fixed known relationships of pressure and rates that are applicable only under certain assumptions (e.g. planar fractures, single-phase flowing conditions etc.). Complex, non-uniform fractures, and multi-phase flow of fluids do not follow the same diagnostics behavior but exhibits more complex behavior not explained by analytical equations. The hybrid SNR approach identifies these complexities from combination of the most relevant pressure and time features that explain the phase rates behavior for a given well, thus enables forecasting the well for different flowing pressure/operating conditions. In addition, the method allows identification of dominant flow regimes through highest contributing terms without performing typical line fitting procedure. The method has been validated against synthetic model with constant and varying bottom hole pressures. The results indicate good model accuracies to identify relevant set of features that dictate rate-pressure behavior and perform production forecasts for new bottom-hole pressure profiles. The method is robust since it can be applied to any well with different fluid types, flowing conditions and does not require any mechanistic fracture or simulation model assumptions and hence applicable to any reservoir complexity. The novelty of the method is that the hybrid SNR can resolve several modes that govern the flow process simultaneously that can provide physical insights on the prevailing multiple complex flow regimes.
- North America > United States > Texas > Fort Worth Basin > Barnett Shale Formation (0.99)
- Africa > Tanzania > Indian Ocean > K Formation (0.99)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Production forecasting (1.00)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Drillstem/well testing (1.00)
- Production and Well Operations > Well & Reservoir Surveillance and Monitoring > Production logging (1.00)
- Data Science & Engineering Analytics > Information Management and Systems (1.00)
Abstract Changing thermodynamic and compositional conditions of producing fields can cause decreased asphaltene stability and initiate aggregation, subsequent precipitation, and eventual deposition within flowlines. Usage of asphaltene inhibitors that prevent aggregation and tackle the problem right at the inception is widely preferred. However, such chemistries were observed to be counter-productive and led to higher asphaltene deposition in many cases. Thus, raising the question of what approach works best for assessing asphaltene stability: Dispersion or Deposition? The focus of this study is to explore the relationship between the underlying working mechanism of dispersion and deposition-based test methods. Multiple crude oil samples produced from different regions of the world were evaluated using asphaltene inhibitor chemistries with optical transmittance, thermoelectric, and flow loop methods. Optical transmittance method evaluates sedimentation rate and cluster size distribution of asphaltene cluster within the test fluid medium. Thermoelectric method describes the dispersion state of asphaltenes within native crude oil. Flow loop setup assesses total mass deposited when the oil (blank or dosed) and precipitant mixture is flown through capillary tubes. The results from these tests indicated that a fine balance between the dispersion and deposition mechanisms must be maintained as these may not respond linearly or in direct relationship at all conditions. It was seen that dispersing the asphaltene clusters too small may lead to high diffusional rate within the low flow shear regime and build up more deposit in depositional dominant test methods. Variation in treatment concentration (especially overtreatment) of an effective asphaltene inhibitor can result in lowering of cluster size to a range which in effect can cause more deposition. The overall assessment suggests that not having a holistic overlook at these test methods and following the standard process of giving specific focus on a singular approach, can mislead the asphaltene stability and inhibitor performance evaluation. The key role of asphaltene cluster size as a bridge relating the dispersion and deposition-based test method is revealed in this paper. It is seen that there exists an effective range of cluster size within which the results from different test methods correlate well. Therefore, it is imperative that the asphaltene inhibitor development philosophy must include test screening methods focusing on each instability stage (precipitation, aggregation, and deposition) individually and combine the learnings to come up with the best recommendation.
- North America > United States (1.00)
- Asia > Middle East (0.68)
- Africa > Middle East > Algeria (0.28)
- Materials > Chemicals > Commodity Chemicals > Petrochemicals (1.00)
- Energy > Oil & Gas > Upstream (1.00)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (23 more...)
- Production and Well Operations > Well & Reservoir Surveillance and Monitoring (1.00)
- Production and Well Operations > Production Chemistry, Metallurgy and Biology > Inhibition and remediation of hydrates, scale, paraffin / wax and asphaltene (1.00)
- Facilities Design, Construction and Operation > Flow Assurance > Precipitates (paraffin, asphaltenes, etc.) (1.00)
A Novel Approach to Determining Carrying Capacity Index Through Incorporation of Hole Size and Pipe Rotation
Rathgeber, David (Montana Tech) | Johnson, Erick (Montana State University) | Lucon, Peter (Montana Tech) | Anderson, Ryan (Montana State University) | Todd, Burt (Montana Tech) | Downey, Jerome (Montana Tech) | Richards, Lee (Montana Tech)
Abstract Current API RP13D guidelines outline 3 methods for determining hole-cleaning efficiency based on wellbore angle. Method 1, used in low-angle wellbores (<30°) compares cuttings slip velocity with annular velocity to determine a transport ratio and cuttings concentration. Method 2, also used for low-angle wellbores (<30°) derives a carrying capacity index (CCI) based on bulk annular velocity, fluid density and power-law rheology. Method 3, used in high-angle wellbores (<30°) derives a transport index (TI) based on fluid rheology, density, and flow rate. TI is then plotted on an empirically derived chart (Luo et al., 1992, 1994) to determine maximum allowable rate of penetration (ROP) that should ensure efficient hole cleaning. Although these methods are considered recommended practices by API, Method 3 (TI) is based on an outdated study (Luo et al., 1992) with limited scope (one flow loop, one field test). Additionally, this method neglects the importance of drill pipe rotation and pipe eccentricity in cuttings transport efficiency, which has been proven to be a factor in other studies (Akhshik et al., 2015; Sanchez et al., 1997b). This paper highlights the shortcomings of current API standards and identifies what effects contributing factors such as pipe eccentricity and drill pipe rotation rates may have on cuttings transport efficiency. Further, this paper discusses the impact pipe-to-hole area ratio and wellbore flow area have on the effects of drill pipe rotation and flow channeling. Five horizontal wellbores were modeled using Siemens Star CCM+ Computational Fluid Dynamics (CFD) software, with bottom-eccentric 4 ½″ drill pipe placement, in annular diameters of 6¾″, 7 ⅞″, 8 ⅜″ 8 ½″ and 8 ⅝″. Additionally, one bottom-eccentric 5″ drill pipe in an 8 ¾" wellbore was modeled to compare identical pipe-to-hole area ratios with different flow areas. Simulations were run with drill pipe rotation speeds increasing from 0 to 180 RPM, in 30 RPM increments. In order to determine the impact fluid rheology has on flow channel development, both medium density oil-based muds and light density water-based muds were modeled and compared. Bulk annular flow velocity was set to 100 ft/min, to maximize the observable effects of drill pipe rotation. Bulk average velocity was calculated from cross sectional area, determining both annular velocity (velocity parallel to wellbore) and absolute velocity (fluid velocity magnitude regardless of direction). The resultant velocity profiles were used as the annular velocity component in API CCI and TI calculations and compared to bulk annular velocity. In addition to observing fluid velocity for CCI and TI calculations, changes in effective viscosity from the onset of pipe rotation was also analyzed to determine changes in wellbore parameters that may affect cuttings transport.
- Well Drilling > Wellbore Design > Wellbore integrity (1.00)
- Well Drilling > Drillstring Design > Drill pipe selection (1.00)
- Well Drilling > Drilling Fluids and Materials > Drilling fluid selection and formulation (chemistry, properties) (1.00)
- Production and Well Operations > Well & Reservoir Surveillance and Monitoring > Production logging (1.00)
A Comprehensive Review of RTA/DCA Methods in Unconventional Reservoirs
Aydin, Hakki (Middle East Technical University) | Boppano, Narendra (University of Texas Permian Basin) | Yurukcu, Mesut (University of Texas Permian Basin) | Liu, Shuhao (Texas A&M University) | Yegin, Cengiz (Incendium Technologies LLC) | Temizel, Cenk (Saudi Aramco)
Abstract Rate Transient Analysis (RTA) and Decline Curve Analysis (DCA) have been utilized as critical tools in calculation of oil production for unconventional reservoirs. Due to the ultra-low permeability of these wells, time scales of flow regimes are different than those of conventional reservoirs, where transient regimes last longer, and the decline behaviors change, factors that make forecasts more challenging. There are several RTA/DCA methods for originally developed conventional and unconventional reservoirs including recent techniques. However, petroleum engineers require a single comprehensive reference where RTA/DCA methods are covered with detailed explanations, as well as an outline of their assumptions, limitations, strengths, and appropriate applications. This study tackles the lack of such a resource, delivering a comparative work that includes theory, practice, and examples. A comprehensive literature review has been carried out to investigate the RTA/DCA methods for unconventional reservoirs in detail, explore the newest techniques and the different methods repurposed from existing conventional approaches with a longer history of use, robustness, and applicability. We also provide a detailed account of the limitations and the advantages of different methods when applied to different types of fields. We achieve this by developing real field applications in different parts of the world and discussing the challenges and opportunities of each RTA/DCA method for a particular type of well. RTA/DCA methods have shown to be a practical tool for both conventional and unconventional reservoirs, and can be applied across many types of oil and gas wells throughout the world. This work shows the parameters best suited for a successful application of these recovery methods in unconventional sites. Moreover, the evidence collected here will serve as a resource for engineers looking for a summary of the most important criteria to be followed in order to apply oil recovery methods in new wells. We expect that future oil production in unconventional reservoirs can be boosted by the results provided in this work. The novelty of this study centers on the lessons drawn from the real-world applications of RTA/DCA methods like Duong's, or stretched exponential decline, to recover oil from unconventional reservoirs. We expect these lessons to define the proper utilization of distinct methods for different reservoirs in future studies and the field.
- Geology > Petroleum Play Type > Unconventional Play > Shale Play > Shale Gas Play (0.48)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock > Mudrock > Shale (0.32)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (39 more...)
Implementation of an Optimized Solution using a Cloud-Based Production Data Management System for Production Operations
Tello Bahamon, Cristhian Camilo (Sensia) | Claib Meinhardt, Amin Adolfo (Sensia) | Perez de la Cruz, Francisco (Sensia) | Ramirez Olarte, Hector Eric (Sensia) | Soberanes Hernandez, Roberto Eduardo (Sensia) | Lozano, Henry Andrey (Sensia) | Sena de Lima, Jesley (Sensia) | Vasquez Garcia, Claudia (Sensia) | Garibay, Francisco (Sensia) | Gomez, John (Sensia) | Gonzalez Ordonez, Abraham (Sensia) | Parra, Javier (Sensia)
Abstract Major oil and gas operators often face performance issues related to on-premises applications when dealing with huge amounts of data. A cloud-based digital solution was developed for an oil and gas company in Colombia to upgrade the production data management system (PDMS) by migrating from on-premises to a secure cloud-based environment, enhancing the performance of the solution and the remote access experience for end users. This implementation was carried out under a cloud-based infrastructure using a platform-as-a-service (PaaS) scheme, which includes middleware, database management systems, and backup services. The user access to the PDMS is through virtual desktop services, which enables load balancing of the users to avoid performance issues. The performance of the previous infrastructure was evaluated and considered when designing the new architecture, the database sizing, licensing, and integration with third-party applications. The data from the on-premises solution were analyzed and validated to guarantee correspondence with the cloud-based solution, and both solutions were run in parallel to verify consistency and reliability. The release of the cloud-based application was done in stages, with a stabilization period during which any issues could be detected and corrected. The PDMS solution was improved by faster data processing, reducing the execution time of calculation and allocation processes by 50%, while some heavy processes as data carry forward reached a 90% reduction. Enhancements included the generation of complex reports, such as hierarchy production allocation results, that did not run on the on-premises servers. As a result of this implementation, the application can be accessed from a personal computer as well as from a mobile phone, allowing the user access from any place or device, without security risks. The cloud-based solution reduced OPEX and increased flexibility due to lower maintenance costs for physical infrastructure and the cloud server's capacity based on demand.
- Information Technology > Information Management (1.00)
- Information Technology > Communications > Web (0.47)
- Information Technology > Communications > Networks (0.47)
- Information Technology > Communications > Mobile (0.34)