Assessment of Unconventional Resources Opportunities in the Middle East Tethyan Petroleum System in a Transfer Learning Context

Mapping Intimacies ◽

10.2118/207723-ms ◽

2021 ◽

Author(s):

Cyrus Ashayeri ◽

Birendra Jha

Keyword(s):

Middle East ◽

Transfer Learning ◽

Fine Tuning ◽

Data Driven ◽

Learning Context ◽

Eagle Ford ◽

Field Development ◽

Unconventional Resources ◽

Basin Scale ◽

The Impact

Abstract Decision making in new fields with little data available relies heavily on physics-based simulation models. However, due to a lack of full understanding of the physical processes governing flow in the unconventional resources, data-driven modeling has emerged as an alternative and complimentary tool to create recovery forecasts that honor the available data. Transfer Learning provides an opportunity to start early-stage analysis of the asset before adequate data becomes available. New challenges in the energy industry as well as shifting dynamics in both domestic and global supply and demand has encouraged some of the petroleum exporting countries in the Middle East to strategize the development of unconventional resources. In this research we have developed a data-driven Transfer Learning framework that allows the basin-wide assessment of new shale gas and tight oil prospects. The proposed Transfer Learning method is developed on real-world data from several thousand horizontal multistage wells in the Eagle Ford super-basin in South Texas. In this method we have integrated reservoir engineering domain expertise in the data pre-processing and feature generation steps. We have also considered the temporal and spatial balancing of the training data to assure that the predictive models honor the real practice of unconventional field development. Our full cycle Transfer Learning workflow consists of dimensionality reduction and unsupervised clustering, supervised learning, and hyperparameter fine-tuning. This workflow enables reservoir engineers to experiment with multiple hypothetical scenarios and observe the impact of additional data in the learning process. We use the developed workflow to examine the performance of a data-driven model of the Eagle Ford Basin on potential plays in the Middle East. Existence of all liquid types of oil, condensate and dry gas in the Eagle Ford has resulted in training a model flexible enough to be tested on various types of assets in a new location. We first present the successful deployment of our model within the Eagle Ford. Next, we use the information from major formations such as Tuwaiq Mountain and Hanifa and show the value of a pre-existing model from a fully-developed shale play on achieving acceptable accuracies with minimal information available in a new field. Our model is developed by data types with relatively low resolution that minimizes overfitting effects and allows generalization to different geologies with basin-wide accuracy. This approach allows conducting accelerated assessment of various sections of a large asset to enhance field development planning processes. This is a first example of such an effort on a basin scale that examines the effectiveness of Transfer Learning on some of the major unconventional plays in the Middle East region. This workflow allows investigating the relationship among geologic and petrophysical variables, drilling and completion parameters, and productivity of a large group of wells in a new asset.

Download Full-text

Data Driven Workflow to Optimize Eagle Ford Unconventional Asset Development Plan Based on Multidisciplinary Data

10.2118/206276-ms ◽

2021 ◽

Author(s):

Tarik Abdelfattah ◽

Ehsaan Nasir ◽

Junjie Yang ◽

Jamar Bynum ◽

Alexander Klebanov ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Subject Matter ◽

Data Driven ◽

Well Performance ◽

Eagle Ford ◽

Field Development ◽

Well Design ◽

Machine Learning Model ◽

Feature Importance

Abstract Unconventional reservoir development is a multidisciplinary challenge due to complicated physical system, including but not limited to complicated flow mechanism, multiple porosity system, heterogeneous subsurface rock and minerals, well interference, and fluid-rock interaction. With enough well data, physics-based models can be supplemented with data driven methods to describe a reservoir system and accurately predict well performance. This study uses a data driven approach to tackle the field development problem in the Eagle Ford Shale. A large amount of data spanning major oil and gas disciplines was collected and interrogated from around 300 wells in the area of interest. The data driven workflow consists of: Descriptive model to regress on existing wells with the selected well features and provide insight on feature importance, Predictive model to forecast well performance, and Subject matter expert driven prescriptive model to optimize future well design for well economics improvement. To evaluate initial well economics, 365 consecutive days of production oil per CAPEX dollar spent (bbl/$) was setup as the objective function. After a careful model selection, Random Forest (RF) shows the best accuracy with the given dataset, and Differential Evolution (DE) was used for optimization. Using recursive feature elimination (RFE), the final master dataset was reduced to 50 parameters to feed into the machine learning model. After hyperparameter tuning, reasonable regression accuracy was achieved by the Random Forest algorithm, where correlation coefficient (R2) for the training and test dataset was 0.83, and mean absolute error percentage (MAEP) was less than 20%. The model also reveals that the well performance is highly dependent on a good combination of variables spanning geology, drilling, completions, production and reservoir. Completion year has one of the highest feature importance, indicating the improvement of operation and design efficiency and the fluctuation of service cost. Moreover, lateral rate of penetration (ROP) was always amongst the top two important parameters most likely because it impacts the drilling cost significantly. With subject matter experts’ (SME) input, optimization using the regression model was performed in an iterative manner with the chosen parameters and using reasonable upper and lower bounds. Compared to the best existing wells in the vicinity, the optimized well design shows a potential improvement on bbl/$ by approximately 38%. This paper introduces an integrated data driven solution to optimize unconventional development strategy. Comparing to conventional analytical and numerical methods, machine learning model is able to handle large multidimensional dataset and provide actionable recommendations with a much faster turnaround. In the course of field development, the model accuracy can be dynamically improved by including more data collected from new wells.

Download Full-text

Force Myography-Based Human Robot Interactions via Deep Domain Adaptation and Generalization

Sensors ◽

10.3390/s22010211 ◽

2021 ◽

Vol 22 (1) ◽

pp. 211

Author(s):

Umme Zakia ◽

Carlo Menon

Keyword(s):

Transfer Learning ◽

Domain Adaptation ◽

Applied Force ◽

Training Data ◽

Fine Tuning ◽

Data Driven ◽

Target Distribution ◽

Source Data ◽

Force Myography ◽

Using Data

Estimating applied force using force myography (FMG) technique can be effective in human-robot interactions (HRI) using data-driven models. A model predicts well when adequate training and evaluation are observed in same session, which is sometimes time consuming and impractical. In real scenarios, a pretrained transfer learning model predicting forces quickly once fine-tuned to target distribution would be a favorable choice and hence needs to be examined. Therefore, in this study a unified supervised FMG-based deep transfer learner (SFMG-DTL) model using CNN architecture was pretrained with multiple sessions FMG source data (Ds, Ts) and evaluated in estimating forces in separate target domains (Dt, Tt) via supervised domain adaptation (SDA) and supervised domain generalization (SDG). For SDA, case (i) intra-subject evaluation (Ds ≠ Dt-SDA, Ts ≈ Tt-SDA) was examined, while for SDG, case (ii) cross-subject evaluation (Ds ≠ Dt-SDG, Ts ≠ Tt-SDG) was examined. Fine tuning with few “target training data” calibrated the model effectively towards target adaptation. The proposed SFMG-DTL model performed better with higher estimation accuracies and lower errors (R2 ≥ 88%, NRMSE ≤ 0.6) in both cases. These results reveal that interactive force estimations via transfer learning will improve daily HRI experiences where “target training data” is limited, or faster adaptation is required.

Download Full-text

$40 Billion Learning Curve: Leveraging Lessons Learned to Minimize the Overall Investment in Unconventional Plays

10.2118/spe-172973-ms ◽

2015 ◽

Author(s):

C.N.. N. Fredd ◽

J.L.. L. Daniels ◽

J.D.. D. Baihly

Keyword(s):

North America ◽

Learning Curve ◽

Lessons Learned ◽

Barnett Shale ◽

Eagle Ford Shale ◽

Eagle Ford ◽

Horizontal Drilling ◽

Unconventional Resources ◽

Retrospective Assessment ◽

The Impact

Abstract The industry has made significant advances in the way we exploit unconventional resources such as source rock and tight reservoirs. Innovations in horizontal drilling and multistage fracturing have unlocked previously uneconomical plays, and technology has brought a step change in operational efficiency. Lessons learned from unconventional resources highlight collaboration and integrated reservoir-centric workflows as common traits for economic success. The development of unconventional resources in North America was aided by the readily available infrastructure, water resources, expertise, and a general understanding of potential sweet spots due to numerous well penetrations. Even with these favorable conditions, an estimated 40% of unconventional wells are uneconomical due to spatial variability in reservoir characteristics, lateral heterogeneity along the wellbores, accuracy of well placement, and variability in drilling, completion, and stimulation practices. This non-ideal economic performance also ineffectively consumes local resources such as water and proppant. This paper provides a retrospective assessment of the Barnett Shale and Eagle Ford Shale to highlight lessons learned and the associated value of those learnings. The impact of applying technology and utilizing a data-driven approach based on measurements will be assessed in terms of the investment required to achieve a given hydrocarbon production. The results indicate that these unconventional plays could have been developed with well counts reduced by the thousands, water consumption reduced by billions of gallons, and investment savings in the billions of dollars if initially exploited by applying the key lessons learned from over the past 30 years. This potential reduction in investment amounts to $40 billion for the Barnett Shale (shale gas) plus the Eagle Ford Shale (oil window) and represents the significant value of moving along the learning curve. Fortunately, there is no need to repeat this learning curve investment, as key lessons learned can be applied to other unconventional plays around the world. This learning curve is of specific value in international plays where local infrastructure, supply, and market conditions may not be as favorable as in North America, hence necessitating a different approach to optimize the overall investment when developing unconventional plays.

Download Full-text

60 Years Field Performance Data-Driven Analytics to Generate Updated Waterflood Field Development Plan in a North Kuwait Giant Carbonate Reservoir

10.2118/207231-ms ◽

2021 ◽

Author(s):

Basel AL-Otaibi ◽

Issa Abu Shiekah ◽

Manish Kumar Jha ◽

Gerbert de Bruijn ◽

Peter Male ◽

...

Keyword(s):

Oil Recovery ◽

Water Injection ◽

Oil Production ◽

Horizontal Wells ◽

Carbonate Reservoir ◽

Development Plan ◽

Data Driven ◽

Water Flooding ◽

Field Development ◽

The Impact

Abstract After 40 years of depletion drive, a mature, giant and multi-layer carbonate reservoir is developed through waterflooding. Oil production, sustained through infill drilling and new development patterns, is often associated with increasingly higher water production compared to earlier development phases. A field re-development plan has been established to alleviate the impact of reservoir heterogeneities on oil recovery, driven by the analysis of the historical performance of production and injection of a range of well types. The field is developed through historical opportunistic development concepts utilizing evolving technology trends. Therefore, the field has initially wide spacing vertical waterflooding patterns followed by horizontal wells, subjected to seawater or produced water injection, applying a range of wells placement or completion technologies and different water injection operating strategies. Systematic categorization, grouping and analyzing of a rich data set of wells performance have been complemented and integrated with insights from coarse full field and conceptual sector dynamic modeling activities. This workflow efficiently paved the way to optimize the field development aiming for increased oil recovery and cost saving opportunities. Integrated analysis of evolving historical development decisions revealed and ranked the primary subsurface and operational drivers behind the limited sweep efficiency and increased watercut. This helped mapping the impact of fundamental subsurface attributes from well placement, completion, or water injection strategies. Excellent vertical wells performance during the primary depletion and the early stage of water flooding was slowly outperformed by a more sustainable horizontal well production and injection strategy. This is consistent with a conceptual model in which the reservoir is dominated by extensive high conductive features that contributed in the early life of the field to good oil production before becoming the primary source of premature water breakthrough after a limited fraction of pore volume water was injected. The next level of analysis provided actual field evidence to support informed decisions to optimize the front runner horizontal wells development concept to cover wells length, orientation, vertical placement in the stratigraphy, spacing, pattern strategy and completion design. The findings enabled delivering updated field development plan covering the field life cycle to sustain and increase field oil production through adding ~ 200 additional wells and introducing more structured water flooding patterns in addition to establishing improved wells reservoir management practices. This integrated study manifests the power, efficiency and value from data driven analysis to capture lessons learned from evolving wells and development concepts applied in a complex brown field over six decades. The workflow enabled the delivery of an updated field development plan and production forecasts within a year through utilizing data analytics to compensate for the recognized limitations of subsurface models in addition to providing input to steer the more time-consuming modeling activities.

Download Full-text

Melanoma Classification from Dermoscopy Images Using Ensemble of Convolutional Neural Networks

Mathematics ◽

10.3390/math10010026 ◽

2021 ◽

Vol 10 (1) ◽

pp. 26

Author(s):

Rehan Raza ◽

Fatima Zulfiqar ◽

Shehroz Tariq ◽

Gull Bano Anwar ◽

Allah Bux Sargano ◽

...

Keyword(s):

Skin Cancer ◽

Human Skin ◽

Transfer Learning ◽

Fine Tuning ◽

Acral Lentiginous Melanoma ◽

Augmentation Techniques ◽

Exposed Part ◽

Detection And Diagnosis ◽

Melanoma Classification ◽

The Impact

Human skin is the most exposed part of the human body that needs constant protection and care from heat, light, dust, and direct exposure to other harmful radiation, such as UV rays. Skin cancer is one of the dangerous diseases found in humans. Melanoma is a form of skin cancer that begins in the cells (melanocytes) that control the pigment in human skin. Early detection and diagnosis of skin cancer, such as melanoma, is necessary to reduce the death rate due to skin cancer. In this paper, the classification of acral lentiginous melanoma, a type of melanoma with benign nevi, is being carried out. The proposed stacked ensemble method for melanoma classification uses different pre-trained models, such as Xception, Inceptionv3, InceptionResNet-V2, DenseNet121, and DenseNet201, by employing the concept of transfer learning and fine-tuning. The selection of pre-trained CNN architectures for transfer learning is based on models having the highest top-1 and top-5 accuracies on ImageNet. A novel stacked ensemble-based framework is presented to improve the generalizability and increase robustness by fusing fine-tuned pre-trained CNN models for acral lentiginous melanoma classification. The performance of the proposed method is evaluated by experimenting on a Figshare benchmark dataset. The impact of applying different augmentation techniques has also been analyzed through extensive experimentations. The results confirm that the proposed method outperforms state-of-the-art techniques and achieves an accuracy of 97.93%.

Download Full-text

Food Safety Security: A new Concept for Enhancing Food Safety Measures

International Journal for Vitamin and Nutrition Research ◽

10.1024/0300-9831/a000114 ◽

2012 ◽

Vol 82 (3) ◽

pp. 216-222 ◽

Cited By ~ 4

Author(s):

Venkatesh Iyengar ◽

Ibrahim Elmadfa

Keyword(s):

Food Safety ◽

Hazard Analysis ◽

Warning System ◽

Shared Responsibility ◽

Fine Tuning ◽

Strategic Action ◽

Surveillance Network ◽

Measurement Systems ◽

Critical Control Points ◽

The Impact

The food safety security (FSS) concept is perceived as an early warning system for minimizing food safety (FS) breaches, and it functions in conjunction with existing FS measures. Essentially, the function of FS and FSS measures can be visualized in two parts: (i) the FS preventive measures as actions taken at the stem level, and (ii) the FSS interventions as actions taken at the root level, to enhance the impact of the implemented safety steps. In practice, along with FS, FSS also draws its support from (i) legislative directives and regulatory measures for enforcing verifiable, timely, and effective compliance; (ii) measurement systems in place for sustained quality assurance; and (iii) shared responsibility to ensure cohesion among all the stakeholders namely, policy makers, regulators, food producers, processors and distributors, and consumers. However, the functional framework of FSS differs from that of FS by way of: (i) retooling the vulnerable segments of the preventive features of existing FS measures; (ii) fine-tuning response systems to efficiently preempt the FS breaches; (iii) building a long-term nutrient and toxicant surveillance network based on validated measurement systems functioning in real time; (iv) focusing on crisp, clear, and correct communication that resonates among all the stakeholders; and (v) developing inter-disciplinary human resources to meet ever-increasing FS challenges. Important determinants of FSS include: (i) strengthening international dialogue for refining regulatory reforms and addressing emerging risks; (ii) developing innovative and strategic action points for intervention {in addition to Hazard Analysis and Critical Control Points (HACCP) procedures]; and (iii) introducing additional science-based tools such as metrology-based measurement systems.

Download Full-text