Energy Geoscience最新文献

{"title":"Clastic facies classification using machine learning-based algorithms: A case study from Rawat Basin, Sudan","authors":"Anas Mohamed Abaker Babai ,&nbsp;Olugbenga Ajayi Ehinola ,&nbsp;Omer.I.M. Fadul Abul Gebbayin ,&nbsp;Mohammed Abdalla Elsharif Ibrahim","doi":"10.1016/j.engeos.2024.100353","DOIUrl":"10.1016/j.engeos.2024.100353","url":null,"abstract":"<div><div>Machine learning techniques and a dataset of five wells from the Rawat oilfield in Sudan containing 93,925 samples per feature (seven well logs and one facies log) were used to classify four facies. Data pre-processing and preparation involve two processes: data cleaning and feature scaling. Several machine learning algorithms, including Linear Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GB) for classification, were tested using different iterations and various combinations of features and parameters. The support vector radial kernel training model achieved an accuracy of 72.49% without grid search and 64.02% with grid search, while the blind-well test scores were 71.01% and 69.67%, respectively. The Decision Tree (DT) Hyperparameter Optimization model showed an accuracy of 64.15% for training and 67.45% for testing. In comparison, the Decision Tree coupled with grid search yielded better results, with a training score of 69.91% and a testing score of 67.89%. The model's validation was carried out using the blind well validation approach, which achieved an accuracy of 69.81%. Three algorithms were used to generate the gradient-boosting model. During training, the Gradient Boosting classifier achieved an accuracy score of 71.57%, and during testing, it achieved 69.89%. The Grid Search model achieved a higher accuracy score of 72.14% during testing. The Extreme Gradient Boosting model had the lowest accuracy score, with only 66.13% for training and 66.12% for testing. For validation, the Gradient Boosting (GB) classifier model achieved an accuracy score of 75.41% on the blind well test, while the Gradient Boosting with Grid Search achieved an accuracy score of 71.36%. The Enhanced Random Forest and Random Forest with Bagging algorithms were the most effective, with validation accuracies of 78.30% and 79.18%, respectively. However, the Random Forest and Random Forest with Grid Search models displayed significant variance between their training and testing scores, indicating the potential for overfitting. Random Forest (RF) and Gradient Boosting (GB) are highly effective for facies classification because they handle complex relationships and provide high predictive accuracy. The choice between the two depends on specific project requirements, including interpretability, computational resources, and data nature.</div></div>","PeriodicalId":100469,"journal":{"name":"Energy Geoscience","volume":"6 1","pages":"Article 100353"},"PeriodicalIF":0.0,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143157530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"OFC","authors":"","doi":"10.1016/S2666-7592(24)00059-3","DOIUrl":"10.1016/S2666-7592(24)00059-3","url":null,"abstract":"","PeriodicalId":100469,"journal":{"name":"Energy Geoscience","volume":"5 4","pages":"Article 100344"},"PeriodicalIF":0.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ToC","authors":"","doi":"10.1016/S2666-7592(24)00061-1","DOIUrl":"10.1016/S2666-7592(24)00061-1","url":null,"abstract":"","PeriodicalId":100469,"journal":{"name":"Energy Geoscience","volume":"5 4","pages":"Article 100346"},"PeriodicalIF":0.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Recent advances in switchable surfactants for heavy oil production: A review","authors":"Qi Li ,&nbsp;Lingfei Liu ,&nbsp;Dejun Sun ,&nbsp;Zhenghe Xu","doi":"10.1016/j.engeos.2024.100342","DOIUrl":"10.1016/j.engeos.2024.100342","url":null,"abstract":"<div><p>Surfactants are extensively employed in the cold production of heavy oil. However, producing heavy oil emulsions using conventional surfactants poses a challenge to spontaneous demulsification, necessitating the addition of demulsifiers for oil-water separation. This inevitably increases the exploitation cost and environmental pollution risk. Switchable surfactants have garnered much attention due to their dual capabilities of underground heavy oil emulsification and surface demulsification. This study focuses on the fundamental working principles and classification of novel switchable surfactants for oil displacement developed in recent years. It offers a comprehensive overview of the latest advances in the applications of switchable surfactants in the fields of enhanced oil recovery (EOR), oil sand washing, and oil-water separation. Furthermore, it highlights the existing challenges and future development directions of switchable surfactants for heavy oil recovery.</p></div>","PeriodicalId":100469,"journal":{"name":"Energy Geoscience","volume":"5 4","pages":"Article 100342"},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S266675922400057X/pdfft?md5=6b6aecef06070c1c19f83014ce0b313c&pid=1-s2.0-S266675922400057X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142239950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating petrophysical data into efficient iterative cluster analysis for electrofacies identification in clastic reservoirs","authors":"Mohammed A. Abbas ,&nbsp;Watheq J. Al-Mudhafar ,&nbsp;Aqsa Anees ,&nbsp;David A. Wood","doi":"10.1016/j.engeos.2024.100341","DOIUrl":"10.1016/j.engeos.2024.100341","url":null,"abstract":"<div><p>Efficient iterative unsupervised machine learning involving probabilistic clustering analysis with the expectation-maximization (EM) clustering algorithm is applied to categorize reservoir facies by exploiting latent and observable well-log variables from a clastic reservoir in the Majnoon oilfield, southern Iraq. The observable well-log variables consist of conventional open-hole, well-log data and the computer-processed interpretation of gamma rays, bulk density, neutron porosity, compressional sonic, deep resistivity, shale volume, total porosity, and water saturation, from three wells located in the Nahr Umr reservoir. The latent variables include shale volume and water saturation. The EM algorithm efficiently characterizes electrofacies through iterative machine learning to identify the local maximum likelihood estimates (MLE) of the observable and latent variables in the studied dataset. The optimized EM model developed successfully predicts the core-derived facies classification in two of the studied wells. The EM model clusters the data into three distinctive reservoir electrofacies (F1, F2, and F3). F1 represents a gas-bearing electrofacies with low shale volume (<em>V</em>_sh) and water saturation (<em>S</em>_w) and high porosity and permeability values identifying it as an attractive reservoir target. The results of the EM model are validated using nuclear magnetic resonance (NMR) data from the third studied well for which no cores were recovered. The NMR results confirm the effectiveness and accuracy of the EM model in predicting electrofacies. The utilization of the EM algorithm for electrofacies classification/cluster analysis is innovative. Specifically, the clusters it establishes are less rigidly constrained than those derived from the more commonly used K-means clustering method. The EM methodology developed generates dependable electrofacies estimates in the studied reservoir intervals where core samples are not available. Therefore, once calibrated with core data in some wells, the model is suitable for application to other wells that lack core data.</p></div>","PeriodicalId":100469,"journal":{"name":"Energy Geoscience","volume":"5 4","pages":"Article 100341"},"PeriodicalIF":0.0,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666759224000568/pdfft?md5=d8916b0234b38221a0965d64b18973f9&pid=1-s2.0-S2666759224000568-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142239953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impacts of interactions with low-mineralized water on permeability and pore behavior of carbonate reservoirs","authors":"Dmitriy A. Martyushev ,&nbsp;Inna N. Ponomareva ,&nbsp;Vasiliy I. Chernykh ,&nbsp;Shadfar Davoodi ,&nbsp;Yousef Kazemzadeh ,&nbsp;Tianshou Ma","doi":"10.1016/j.engeos.2024.100340","DOIUrl":"10.1016/j.engeos.2024.100340","url":null,"abstract":"<div><p>Laboratory filtration experiments are employed to investigate effective well killing while minimizing its impacts on surrounding rocks. The novelty of this experimental study lies in the prolonged exposure of rock samples to the killing fluid for seven days, corresponding to the average duration of well workovers in the oilfields in Perm Krai, Russia. Our findings indicate that critical factors influencing the interactions between rocks and the killing fluid include the chemical composition of the killing fluid, the mineralogical composition of the carbonate rocks, reservoir pressure and temperature, and the contact time. Petrophysical analyses using multi-scale X-ray computed tomography, field emission scanning electron microscopy, and X-ray diffraction were conducted on samples both before and after the well killing simulation. The experiments were performed using real samples of cores, crude oil, and the killing fluid. The results from this study indicate that low-mineralized water (practically fresh water) is a carbonate rock solvent. Such water causes the dissolution of rock components, the formation of new calcite crystals and amoeba-like secretions, and the migration of small particles (clay, quartz, and carbonates). The formation of deep channels was also recorded. The assessment reveals that the change in the pH of the killing fluid indicates that the observed mineral reactions were caused by carbonate dissolution. These combined phenomena led to a decrease in the total number of voids in the core samples, which was 25% on average, predominantly among voids measuring between 45 and 70 μm in size. The change in the pore distribution in the bulk of the samples resulted in decreases in porosity of 1.8% and permeability of 67.0% in the studied core samples. The results from this study indicate the unsuitability of low-mineralized water as a well killing fluid in carbonate reservoirs. The composition of the killing fluid should be optimized, for example, in terms of the ionic composition of water, which we intend to investigate in future research.</p></div>","PeriodicalId":100469,"journal":{"name":"Energy Geoscience","volume":"5 4","pages":"Article 100340"},"PeriodicalIF":0.0,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666759224000556/pdfft?md5=45700afc99fe54653649ba54d514b699&pid=1-s2.0-S2666759224000556-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142122221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Key aspects of underground hydrogen storage in depleted hydrocarbon reservoirs and saline aquifers: A review and understanding","authors":"Rawaa A. Sadkhan ,&nbsp;Watheq J. Al-Mudhafar","doi":"10.1016/j.engeos.2024.100339","DOIUrl":"10.1016/j.engeos.2024.100339","url":null,"abstract":"<div><p>Underground hydrogen storage is critical for renewable energy integration and sustainability. Saline aquifers and depleted oil and gas reservoirs represent viable large-scale hydrogen storage solutions due to their capacity and availability. This paper provides a comparative analysis of the current status of hydrogen storage in various environments. Additionally, it assesses the geological compatibility, capacity, and security of these storage environments with minimal leakage and degradation. An in-depth analysis was also conducted on the economic and environmental issues that impact the hydrogen storage. In addition, the capacity of these structures was also clarified, and it is similar to storing carbon dioxide, except for the cushion gas that is injected with hydrogen to provide pressure when withdrawing from the store to increase demand. This research also discusses the pros and cons of hydrogen storage in saline aquifers and depleted oil and gas reservoirs. Advantages include numerous storage sites, compatibility with existing infrastructure, and the possibility to repurpose declining oil and gas assets. Specifically, it was identified that depleted gas reservoirs are better for hydrogen gas storage than depleted oil reservoirs because hydrogen gas may interact with the oil. The saline aquifers rank third because of uncertainty, limited capacity, construction and injection costs. The properties that affect the hydrogen injection process were also discussed in terms of solid, fluid, and solid-fluid properties. In all structures, successful implementation requires characterizing sites, monitoring and managing risks, and designing efficient storage methods. The findings expand hydrogen storage technology and enable a renewable energy-based energy system.</p></div>","PeriodicalId":100469,"journal":{"name":"Energy Geoscience","volume":"5 4","pages":"Article 100339"},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666759224000544/pdfft?md5=967b2126d3be0bb00a7f4599746f6251&pid=1-s2.0-S2666759224000544-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142094749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Shear wave velocity prediction: A review of recent progress and future opportunities","authors":"John Oluwadamilola Olutoki ,&nbsp;Jian-guo Zhao ,&nbsp;Numair Ahmed Siddiqui ,&nbsp;Mohamed Elsaadany ,&nbsp;AKM Eahsanul Haque ,&nbsp;Oluwaseun Daniel Akinyemi ,&nbsp;Amany H. Said ,&nbsp;Zhaoyang Zhao","doi":"10.1016/j.engeos.2024.100338","DOIUrl":"10.1016/j.engeos.2024.100338","url":null,"abstract":"<div><p>Shear logs, also known as shear velocity logs, are used for various types of seismic analysis, such as determining the relationship between amplitude variation with offset (AVO) and interpreting multiple types of seismic data. This log is an important tool for analyzing the properties of rocks and interpreting seismic data to identify potential areas of oil and gas reserves. However, these logs are often not collected due to cost constraints or poor borehole conditions possibly leading to poor data quality, though there are various approaches in practice for estimating shear wave velocity. In this study, a detailed review of the recent advances in the various techniques used to measure shear wave (S-wave) velocity is carried out. These techniques include direct and indirect measurement, determination of empirical relationships between S-wave velocity and other parameters, machine learning, and rock physics models. Therefore, this study creates a collection of employed techniques, enhancing the existing knowledge of this significant topic and offering a progressive approach for practical implementation in the field.</p></div>","PeriodicalId":100469,"journal":{"name":"Energy Geoscience","volume":"5 4","pages":"Article 100338"},"PeriodicalIF":0.0,"publicationDate":"2024-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666759224000532/pdfft?md5=2c2cd98daeb3201a53158d6709e7981b&pid=1-s2.0-S2666759224000532-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142041091","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correlation between hardness and SEM-EDS characterization of palm oil waste based biocoke","authors":"Asri Gani ,&nbsp;Erdiwansyah ,&nbsp;Hera Desvita ,&nbsp;Saisa ,&nbsp;Mahidin ,&nbsp;Rizalman Mamat ,&nbsp;Zulhaini Sartika ,&nbsp;Ratna Eko Sarjono","doi":"10.1016/j.engeos.2024.100337","DOIUrl":"10.1016/j.engeos.2024.100337","url":null,"abstract":"<div><p>This research investigates the relationship between hardness and microstructure obtained through SEM-EDS analysis of palm oil waste-based biocoke. The mechanical qualities and chemical composition of biocoke are being studied concerning the influence of temperature conditions. The manufacturing temperature of biocoke may vary between 150 °C and 190 °C. Utilizing SEM-EDS, we were able to characterize the microstructure and analyze the elemental composition, while the Hardness Shore D approach was used for the most complex materials. These results highlight the possibility of optimizing production temperature to produce biocoke with better mechanical performance. They show a positive correlation between biocoke hardness and structured carbon content. At 150 °C and 180 °C, respectively, the EFB biocoke reached its maximum hardness level of 62 ± 5. At 190 °C, OPM biocoke generated a 60 ± 5 times greater hardness than that of OPM and OPF biocoke. The OPT biocoke sample had the highest porosity with a score of 0.86, or 85.76%. Furthermore, compared to EFB biocoke, OPM and OPF biocokes had a priority of 0.84 (84.20%) and 0.83 (83.48%), respectively. Biocoke hardness is a quality indicator of physical and chemical qualities; the vital link between biocoke hardness, structural features, and elemental composition supports this idea.</p></div>","PeriodicalId":100469,"journal":{"name":"Energy Geoscience","volume":"5 4","pages":"Article 100337"},"PeriodicalIF":0.0,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666759224000520/pdfft?md5=64dfbb99bbe23a7bcbe6bfc07d1f333e&pid=1-s2.0-S2666759224000520-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141998570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Flow behavior of a coupled model between horizontal well and fractal reservoir","authors":"Peiqing Lian ,&nbsp;Jianfang Sun ,&nbsp;Jincai Zhang ,&nbsp;Zhihui Fan","doi":"10.1016/j.engeos.2024.100336","DOIUrl":"10.1016/j.engeos.2024.100336","url":null,"abstract":"<div><p>Many research findings have proven that the system of porous medium reservoirs exhibits different heterogeneous structures at various scales, demonstrating some form of self-similarity with fractal characteristics. In this paper, fractal theory is incorporated into the reservoir to investigate coupled flow between reservoir and horizontal well. By examining the pore structure of highly heterogeneous reservoirs, the fractal dimension can be determined. Analytical methods are utilized to solve the Green function of a point source in a reservoir with fractal characteristics. Employing Green's function and the principle of spatial superposition, a finite flow model for a horizontal well coupled with a fractal reservoir is developed to calculate the flow rate and flow profile of the horizontal well. The model also accounts for the impact of wellbore friction and is solved numerically. A specific example is used for calculation to analyze the influence of fractal parameters on the production and flow rate of the horizontal well. When considering the fractal characteristics of oil reservoirs, the flow rate of the horizontal well is lower than that in Euclidean space. As the fractal dimension increases, the connectivity of pores in the reservoir improves, making it easier to drive the fluid into the wellbore, and the flow distribution along the wellbore becomes more uniform. Conversely, as the anomalous diffusion index increases, the connectivity between pores deteriorates, thus the distribution of flow rate along the wellbore becomes more uneven.</p></div>","PeriodicalId":100469,"journal":{"name":"Energy Geoscience","volume":"5 4","pages":"Article 100336"},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666759224000519/pdfft?md5=daab3ac204c00a55d4c13b825bfe1fd5&pid=1-s2.0-S2666759224000519-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142089335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}