Sedimentary Dynamics Within the Sedimentary Filling of Sebkha Sidi El Hani, Eastern Tunisia

The Sidi El Hani Wetland is located in Eastern Tunisia. It represents the natural outlet of an endorheic system, Mechertate-Chrita-Sidi El Hani, and it collects all the eroded sediment from this watershed. In this chapter, the visual core description focused on three reference sandy bands and on the concept of grey scale variability in order to infer the clay pan response to the climatic variability and erosion during the last two millennia. First, in the uppermost part, the stage Warming Present (WP) stretches from (1954-80= 1874) to 1993, i.e. ≈120yrs; the establishment of modern conditions is characterized by stable conditions with high grey scale. Added to a small salt crust, this period is dominated by a clayey sedimentation. Second, the stage C4 is called the Late Little Ice Age (Late LIA); it stretches between the 80yrBP and 400yrBP, i.e., 320yrs. It is characterized by intermediate GS values; the clayey sedimentation makes up the twofold and threefold laminates. Based on laser granulometer, the genetic approach shows the interplay of eolian and hydraulic erosion.

Problem-Solving in a Pandemic: How the Creation of a New Workflow Improved the Quality and Timeliness of Remote Core Descriptions

The COVID-19 pandemic limited global travel and access to core facilities. However, by adopting an innovative remote core description workflow, potential delays to an important reservoir characterisation study were avoided and mitigated. Over c.1700ft of middle Miocene core from an Onshore well in Abu Dhabi was described using high-resolution core photos, CT scans and CCA data. Detailed (1:20ft scale) descriptions of heterogeneous, mixed lithology sediments from a gas reservoir were produced. The aim when developing the workflow was not to try and replicate the process of in-person core description, but to create a workflow that could be executed remotely, whilst maintaining technical standards. Ideally, we wanted to find a solution that also had the potential to improve the overall quality of core description, by integrating more data from the onset. The workflow used a matrix to generate a confidence score for the description of each cored interval. Factors such as core condition were considered, which highly influences the extractable core information. The confidence score was used to make decisions, such as whether an in-person review of the core was necessary, especially where core condition was below a reasonable threshold. This helped prioritise cored intervals for review, ensuring time in the core store was focused, and allowed accuracy and reliability of the remote description to be assessed. The 4-phase workflow is summarised as: Image extraction of white light (WL), ultraviolet (UV) and computed tomography (CT) core images. Digital chart creation, core-to-log shifts and sample selection: Wireline data, CCA data and core images loaded Core images used to determine core-to-log shifts Thin section, SEM and XRD samples selected Remote core description: Conducted using all core imagery, CCA and wireline data Thin section, SEM and XRD data were used to refine the description when they became available A confidence score was given to each cored interval QC and finalization: Using the results from phase 3, a selection of cored intervals for in-person review was made. Intervals included those with a poor match between remote description and petrographic data, or areas with a low confidence score. Following the review, charts were finalised and quality-checked for data export Using this workflow, ensured work on an important study could continue during the pandemic. Such an approach has continued value for future studies as it increases efficiency and accounts for more data to be considered in core description prior to viewing the core in-person; it has been used on recent studies with great success. Another benefit to this approach is that less time in the core store is required, reducing potential HSE risks and helping to manage core store availability in busy facilities.

Indirect Estimation of Clastic Reservoir Rock Grain Size from Wireline Logs Using a Supervised Nearest Neighbor Algorithm: Preliminary Results

Reservoir rock textural properties such as grain size are typically estimated by direct visual observation of the physical texture of core samples. Grain size is one of the important inputs to petrophysical characterization, sedimentological facies classification, identification of depositional environments, and saturation models. A continuous log of grain size distribution over targeted reservoir sections is usually required for these applications. Core descriptions are typically not available over an entire targeted reservoir section. Physical core data may also be damaged during retrieval or due to plugging. Alternative methods proposed in literature are not sustainable due to their limitations in terms of input data requirements and inflexibility to apply them in environments with different geological settings. This paper presents the preliminary results of our investigation of a new methodology based on machine learning technology to complement and enhance the traditional core description and the alternative methods. We developed and optimized supervised machine learning models comprising K-nearest neighbor (KNN), support vector machines (SVM), and decision tree (DT) to indirectly estimate reservoir rock grain size for a new well or targeted reservoir sections from historical wireline logs and archival core descriptions. We used anonymized datasets consisting of nine wells from a clastic reservoir. Seven of the wells were used to train and optimize the models while the remaining two were reserved for validation. The grain size types range from clay to pebbles. The performance of the models confirmed the feasibility of this approach. The KNN, SVM, and DT models demonstrated the capability to estimate the grain size for the test wells by matching actual data with a minimum of 60% and close to 80% accuracy. This is an accomplishment taking into account the uncertainties inherent in the core analysis data. Further analysis of the results showed that the KNN model is the most accurate in performance compared to the other models. For future studies, we will explore more advanced classification algorithms and implement new class labeling strategies to improve the accuracy of this methodology. The attainment of this objective will further help to handle the complexity in the grain size estimation challenge and reduce the current turnaround time for core description.

Creating Opportunities for Successful Artificial Intelligence Applications in the Upstream Petroleum Industry

The petroleum industry has continued to show more interest in the application of artificial intelligence (AI). Most professional gatherings now have sub-themes to highlight AI applications. Similarly, the number of publications featuring AI applications has increased. The industry is facing the challenge of scaling up the applications to practical and impactful levels. Most of the applications end up in technical publications and narrow proofs of concept. For the industry's digital transformation objective to be fully achieved, efforts are required to overcome the current limitations. This paper discusses possible causes of the prevailing challenges and prescribes a number of recommendations to overcome them. The recommendations include ways to handle data shortage and unavailability issues, and how AI projects can be designed to provide more impactful solutions, regenerate missing or incomplete logs, and provide alternative workflows to estimate certain reservoir properties. The results of three successful applications are presented to demonstrate the efficacy of the recommendations. The first application estimates a log of reservoir rock cementation factors from wireline data to overcome the limitation of the conventional approach of using a constant value. The second application used the machine learning methodology to regenerate missing logs possibly due to tool failure or bad hole conditions. The third application provides an alternative approach to estimate reservoir rock grain size to overcome the challenges of the conventional core description. Tips on how these applications can be integrated to create a bigger impact on exploration and production (E&P) workflows are shared. It is hoped that this paper will enrich the current AI implementation strategy and practice. It will also encourage increased synergy and collaborative integration of domain expertise and AI methods to make better impact and achieve the digital transformation of E&P business goals.

Linear and Nonlinear Controls of Wireline Logs on Automated Grain Size Estimation Using Machine Learning Approach

Wireline logs have been utilized to indirectly estimate various reservoir properties, such as porosity, permeability, saturation, cementation factor, and lithology. Attempts have been made to correlate Gamma-ray, density, neutron, spontaneous potential, and resistivity logs with lithology. The current approach to estimate grain size, the traditional core description, is time-consuming, labor-intensive, qualitative, and subjective. An alternative approach is essential given the utility of grain size in petrophysical characterization and identification of depositional environments. This paper proposes to fill the gap by studying the linear and nonlinear influences of wireline logs on reservoir rock grain size. We used the observed influences to develop and optimize respective linear and machine learning models to estimate reservoir rock grain size for a new well or targeted reservoir sections. The linear models comprised logistic regression and linear discriminant analysis while the machine learning method is random forest (RF). We will present the preliminary results comparing the linear and machine learning methods. We used anonymized wireline and archival core description datasets from nine wells in a clastic reservoir. Seven wells were used to train the models and the remaining two to test their classification performance. The grain size-types range from clay to granules. While sedimentologists have used gamma-ray logs to guide grain size qualification, the RF model recommended sonic, neutron, and density logs as having the most significant grain size in the nonlinear domain. The comparative results of the models' performance comparison showed that considering the subjectivity and bias associated with the visual core description approach, the RF model gave up to an 89% correct classification rate. This suggested looking beyond the linear influences of the wireline logs on reservoir rock grain size. The apparent relative stability of the RF model compared to the linear ones also confirms the feasibility of the machine learning approach. This is an acceptable and promising result. Future research will focus on conducting more rigorous quality checks on the grain size data, possibly introduce more heterogeneity, and explore more advanced algorithms. This will help to address the uncertainty in the grain size data more effectively and improve the models performance. The outcome of this study will reduce the limitations in the traditional core description and may eventually reduce the need for extensive core description processes.

A Cohesive Approach in Identifying a Missed-pay of Carbonate Reservoir in a Brownfield

L Field is a brownfield located in the South Sumatra Basin with numerous producing wells. Adjacent to this field, there is a large carbonate reservoir with a significant recovery factor. Carbonate is found in L Field but it was deposited in distal environment with different characters. In attempt to prolong the life of L Field, its carbonate reservoir is evaluated. An integration between geology, petrophysics, reservoir and production engineering works has been done to get comprehensive results. The evaluation was put into 2 categories, qualitative and quantitative methods. The qualitative method is done by geologist whom deals with well-by-well review, reservoir correlations, depositional environment interpretation according to regional context, and qualitative candidates scoring. The quantitative method is divided into petrophysical and production data analyses as well as well integrity. The final screening candidates are the result of both methods. Based on the core description from adjacent field, carbonate in L Field has 2 different zones, zone A and B. From the qualitative perception only, zone A can be categorized as non-reservoir, due to high gamma-ray reading. However, the solubility test confirms that the zone has high calcareous content. After final scoring, L-14 well has the highest score for zone A and L-15 for zone B. This Poster highlighted the importance of a cohesive approach among multi-disciplines works which can successfully identify missed pay potential to proving up reserves. As a result, a significant amount of volumetric has been calculated for carbonate in L Field. Due to the good solubility result of the formation with HCl, matrix acidizing stimulation is also prepared. To prove-up reserves in L Field initially, it is recommended to open zone A of L-14 and zone B of L-15. The workover will continue with the remaining wells which have lower scores contingent on both wells' results

K-Mean Clustering Analysis and Logistic Boosting Regression for Rock Facies Characterization and Classification in Zubair Reservoir in Luhais Oil Field, Southern Iraq

Identifying rock facies from petrophysical logs is a crucial step in the evaluation and characterization of hydrocarbon reservoirs. The rock facies can be obtained either from core analysis (lithofacies) or from well logging data (electrofacies). In this research, two advanced machine learning approaches were adopted for electrofacies identification and for lithofacies classification, both given the well-logging interpretations from a well in the upper shale member in Luhais Oil Field, southern Iraq. Specifically, the K-mean partitioning analysis and Logistic Boosting (Logit Boost) were conducted for electrofacies characterization and lithofacies classification, respectively. The dataset includes the routine core analysis of core porosity, core permeability, and measured discrete lithofacies along with the well-logging interpretations include (shale volume, water saturation and effective porosity) given the entire reservoir interval. The K-Mean clustering technique demonstrated good matching between the vertical sequence of identified electrofacies and the observed lithofacies from core description as attained 89.92% total correct percent from the confusion matrix table. The Logit Boost showed excellent matching between the recognized lithofacies from the core description and the predicted lithofacies through attained 98.26% total correct classification rate index from the confusion matrix table. The high accuracy of the Logit Boost algorithm comes from taking into account the non-linearity between the lithofacies and petrophysical properties in the classification process. The high degree of lithofacies classification by Logit Boost in this research can be considered in a similar procedure at all sandstone reservoirs to improve the reservoir characterization. The complete facies identification and classification were implemented with the programming language R, the powerful open-source statistical computing language.

Classification of Void Space Types in Fractured-Vuggy Carbonate Reservoir Using Geophysical Logging: A Case Study on the Sinian Dengying Formation of the Sichuan Basin, Southwest China

The fractured-vuggy carbonate reservoirs display strong heterogeneity and need to be classified into different types for specific characterization. In this study, a total of 134 cores from six drilled wells and six outcrops of the Deng #2 and Deng #4 members of the Dengying Formation (Sichuan Basin, Southwest China) were selected to investigate the petrographic characteristics of void spaces in the fractured-vuggy carbonate reservoirs. Four void space types (VSTs) were observed, namely the solution-filling type (SFT), cement-reducing type (CRT), solution-filling breccia type (SFBT) and solution-enlarging fractures and vugs type (SEFVT). The CRT void spaces presented the largest porosity and permeability, followed by the SEFVT, SFBT and SFT. The VSTs presented various logging responses and values, and based on these, an identification method of VSTs using Bayes discriminant analysis (BDA) was proposed. Two test wells were employed for the validation of the identification method, and the results show that there is good agreement between the identification results and core description. The vertical distribution of VSTs indicates that the SFT and SEFVT are well distributed in both the Deng #2 and Deng #4 members. The CRT is mainly found in the Deng #2 member, and the SFBT occurs in the top and middle of the Deng #4 member.

Paleogeography of the West Siberian Sedimentary Basin in the Late Bajocian–Bathonian

—The paper presents results of regional paleogeographic reconstructions of the West Siberian sedimentary basin in the Late Bajocian–Bathonian. Regional paleogeographic maps of the Yu4, Yu3 and upper part of the Yu2 reservoir units were constructed and described for the first time ever. The implemented approach provided insights into the evolution of paleolandscapes and highlighted the deposition features of the Upper Tyumen Subformation and Malyshev Formation in the different parts of the West Siberian basin. The compilation of paleogeographic maps was based on the electrofacies analysis performed for individual parts of the Malyshev stratigraphic horizon, with regard to the core description materials, paleontological, sedimentological, geochemical data and other. The paleogeographic control of the reservoir’s formation in the Bathonian regional reservoir is discussed.

Evaluation of Favorable Shale Gas Intervals in Dawuba Formation of Ziyun Area, South Qian Depression

A series of qualitative descriptions and quantitative analyses was used to determine the lithofacies characteristics and recognize the favorable shale intervals of Dawuba Formation in the Ziyun area of South Qian Depression. The qualitative descriptions include core description and scanning electron microscope (SEM) observation. The quantitative analyses include X-ray diffraction, total organic content analysis, vitrinite reflectance, maceral composition, porosity, and permeability, as well as gas and element composition. The Dawuba Formation could be divided into four members. In general, the shale in the first and third members showed similarly high organic matter content with most samples in range of 2–2.5% and higher brittle mineral content with a content of quartz 40.53% and 33.21%, respectively, compared with the other two members, as well as high gas content. However, the first member shale samples exhibited much higher porosity and permeability than the third member shale samples. Furthermore, the shale gas in the first member was chiefly composed of methane (average: 83.63%), while that in the third member mainly consisted of nitrogen (average: 79.92%). Hence, the first member should be regarded as the most favorable target.