Petroleum Science最新文献

{"title":"Improved AVA imaging for vector-based elastic reverse time migration using angle-domain dot-product imaging condition","authors":"Shu-Kui Zhang,&nbsp;Shao-Ping Lu,&nbsp;Zhi-Jing Liu,&nbsp;Han Wu,&nbsp;Gang Fang","doi":"10.1016/j.petsci.2026.04.023","DOIUrl":"10.1016/j.petsci.2026.04.023","url":null,"abstract":"<div><div>This paper proposes modified angle-domain dot-product imaging conditions for vector-based elastic reverse time migration, which yields PP and PS angle gathers that capture improved amplitude-versus-angle (AVA) information. The vector P-wavefields and converted S-wavefields can be constructed by separating the coupled elastic wavefields. A simple and stable dot-product imaging condition can be employed to generate scalar PP and PS angle gathers. However, estimating amplitudes via migrated angle gathers using the conventional angle-domain dot-product imaging conditions leads to inaccurate AVA information. The inaccuracy arises because the dot-product imaging condition does not correctly represent seismic PP and PS reflectivity. Hence, the relationship between the dot-product imaging conditions and the reflection coefficients is explicitly derived in this paper. Then, the modified angle-domain dot-product imaging conditions for calculating PP and PS angle gathers are presented based on the kinematic characteristics of the vector P- and S-wavefields, along with an explanation of their amplitude correction mechanism. Finally, simple layer models with positive and negative reflection polarities are used to compute angle gathers to demonstrate the accuracy of the proposed imaging conditions in calculating AVA imaging. Numerical results from the Marmousi2 model validate the effectiveness and correctness of the proposed imaging conditions in complex media.</div></div>","PeriodicalId":19938,"journal":{"name":"Petroleum Science","volume":"23 9","pages":"Pages 5450-5461"},"PeriodicalIF":6.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Closed-loop internal multiple elimination","authors":"Zi-Lin He,&nbsp;Zhi-Na Li,&nbsp;Zhen-Chun Li,&nbsp;Yi-Peng Xu,&nbsp;Yan-Yun Leng","doi":"10.1016/j.petsci.2026.04.033","DOIUrl":"10.1016/j.petsci.2026.04.033","url":null,"abstract":"<div><div>Internal multiple suppression is a crucial and challenging task in seismic data processing, aiming to mitigate the impact of internal multiples on imaging and seismic interpretation. A major difficulty arises because internal multiples often overlap with primaries, particularly in complex geological settings, making their accurate suppression difficult. Conventional internal multiple elimination (IME) methods rely on adaptive subtraction, which may cause primary energy loss in regions where primaries and internal multiples overlap. To address this issue, this paper derives internal multiple suppression formulas based on the well-known feedback model from a novel perspective. On this basis, we propose a Closed-Loop Internal Multiple Elimination (CL-IME) method. By formulating a new objective function, the proposed CL-IME method accurately estimates and suppresses internal multiples through inversion, thereby avoiding the primary energy loss associated with adaptive subtraction. Numerical experiments demonstrate that CL-IME achieves significantly higher accuracy than conventional IME in suppressing internal multiples, particularly in regions where primaries and multiples strongly overlap, thereby providing a more reliable approach for seismic data processing in complex structural settings.</div></div>","PeriodicalId":19938,"journal":{"name":"Petroleum Science","volume":"23 9","pages":"Pages 5462-5473"},"PeriodicalIF":6.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synergistic effects of carbonated water flooding coupled with surfactant for EOR and CO2 storage: Pore-scale mechanisms and influencing factors analysis","authors":"Xiao-Bing Han,&nbsp;Hai-Yang Yu,&nbsp;Hai-Feng Yang,&nbsp;Peng Song,&nbsp;Jia-Bang Song,&nbsp;Yu-Meng Wang,&nbsp;Hui-Ting Tang,&nbsp;Yang Wang","doi":"10.1016/j.petsci.2026.03.044","DOIUrl":"10.1016/j.petsci.2026.03.044","url":null,"abstract":"<div><div>Active carbonated water (ACW) flooding combines the benefits of carbonated water (CW) and surfactant flooding, simultaneously enhancing oil recovery and facilitating CO₂ storage. Nevertheless, the enhanced oil recovery (EOR) mechanisms of ACW remain insufficiently understood, and neither its CO₂ storage performance nor its pore-scale oil displacement characterization have yet to be investigated. Additionally, the influence of different factors on the performance of ACW has not been systematically studied. In this study, core flooding and nuclear magnetic resonance scanning experiments were conducted to elucidate the EOR mechanisms of ACW, clarify for the first time its CO₂ storage performance and pore-scale oil displacement characterization, and examine the influence of various factors on its effectiveness. The results demonstrated that CW flooding enhanced the oil recovery by 12.24% compared to water flooding (46.19%). By leveraging the synergistic effects of CW and surfactant, ACW further increased oil recovery to 64.55%, with pore-scale recovery of 72.22%, 50.77%, and 29.29% for macropores, mesopores, and micropores, respectively, representing increases of 15.77%, 15.05%, and 10.39% relative to water flooding. Furthermore, both CW and ACW demonstrated effective CO₂ storage, with dissolution trapping emerging as a critical mechanism. Compared to the CO₂ storage efficiency of CW at 50.57%, ACW showed a higher efficiency of 52.84%. Within the parameter ranges studied, the oil recovery and CO₂ storage efficiency of ACW both increased with decreasing injection rate and with increasing permeability and surfactant concentration. Correlation analysis revealed that for both metrics, permeability had the most significant influence, followed by surfactant concentration and injection rate. This work provides new insights into the potential of ACW flooding for simultaneous EOR and CO₂ storage, offering practical guidance for its application in low-permeability reservoirs.</div></div>","PeriodicalId":19938,"journal":{"name":"Petroleum Science","volume":"23 9","pages":"Pages 5992-6003"},"PeriodicalIF":6.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Study on the cutting characteristics of different types of abrasive grains on workover bits in the high-temperature environment of the deep wellbore","authors":"Jia-Qi Che,&nbsp;Jia-Qi Qiao,&nbsp;Chang-Chang Chen,&nbsp;Yi-Han Fan,&nbsp;Yun-Fei Chen,&nbsp;Yan-Wen Zhang,&nbsp;Han-Xiang Wang","doi":"10.1016/j.petsci.2026.03.046","DOIUrl":"10.1016/j.petsci.2026.03.046","url":null,"abstract":"<div><div>At present, drilling bits for workover under high-temperature conditions are facing technical bottlenecks such as low work efficiency and rapid wear, especially their working characteristics in the high-temperature environment of the deep wellbore need to be improved urgently. To address this issue, first of all, a two-dimensional orthogonal cutting theoretical mechanical model was established based on Oxley's shear theory to analyze the relationship between cutting parameters and working characteristics. Then geometric models of six commonly used abrasive grains in oil fields, namely disc abrasive grain, cylindrical abrasive grain, honeycomb abrasive grain, long strips of abrasive grain, pointed teeth abrasive grain and prismatic abrasive grain, were established. Also, the thermodynamic coupling simulation models in a high-temperature environment of 180 °C were established based on the Johnson-Cook constitutive model. The accuracy of the simulation model was verified through the performance testing equipment of the drilling bit for workover. Single abrasive grain cutting simulation experiments were carried out based on Abaqus, and the cutting characteristics of different structural types of abrasive grains were analyzed from four aspects: cutting mechanism, work safety, work temperature and work efficiency. The analysis results show that: Firstly, the simulation model error of the abrasive grains of the drilling bit for workover is 9.98%, which meets the accuracy requirements for engineering analysis. Secondly, the cutting forces of the honeycomb abrasive grain and the disc abrasive grain are relatively small and have a smooth fluctuation pattern, being 1.27 and 1.45 kN, respectively. Thirdly, during operation, the cutting temperature of the honeycomb abrasive grain is the lowest, at 521 °C, while the cutting temperature of the prismatic abrasive grain is the highest, reaching 612 °C. Fourthly, the crushing ratio work of cylindrical abrasive grain is the lowest, at 14.58 J/mm³, while that of prismatic abrasive grain is the highest, reaching 15.54 J/mm³. Based on the analysis of work safety, work temperature and work efficiency, when cutting metal blockages in the high-temperature environment, honeycomb abrasive grain is recommended as the preferred choice. The research content can provide theoretical guidance and technical support for the development of an efficient drilling bit for workover in the high-temperature environment of the deep wellbore.</div></div>","PeriodicalId":19938,"journal":{"name":"Petroleum Science","volume":"23 9","pages":"Pages 5914-5927"},"PeriodicalIF":6.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classification of shale oil micro-occurrence types and flow behavior: Combining QSGSM, pore network, machine learning, and LBM","authors":"Yi-Fan Yin,&nbsp;Zhi-Xue Sun,&nbsp;Jing Wang,&nbsp;Kai-Jun Tong,&nbsp;Yong-Fei Yang","doi":"10.1016/j.petsci.2026.06.007","DOIUrl":"10.1016/j.petsci.2026.06.007","url":null,"abstract":"<div><div>Shale oil occurs in varying forms within porous media, with diverse micro-occurrences exhibiting intricate topological characteristics within the pores. The impact of shale oil presence on fluid flow patterns in these complex environments remains uncertain. This study investigates how different shale oil micro-occurrence types and saturation levels influence pore network characteristics and fluid flow behavior in shale reservoirs. Firstly, the shale digital core is established using the focused ion beam scanning electron microscope (FIB-SEM) method, and the pore skeleton is segmented via the watershed method. Utilizing the quartet structure generation set method, we constructed 12 digital cores representing floating, cementing, and coating shale oil micro-occurrence types at different oil saturations based on the real digital core model. The pore network analysis, conducted using the maximum ball method, revealed that increasing oil saturation generally leads to a reduction in pore radius and an increase in pore quantity due to pore subdivision, with the cementing type showing the most significant effect. Additionally, machine learning techniques, including random forest, support vector machine (SVM), and K-nearest neighbors (KNN), were employed to classify micro-occurrence types of shale oil based on topological features such as volume ratio, cross-sectional area ratio, three-dimensional shape factor, and Euler number. The support vector machine (SVM) method achieved the highest predictive accuracy (93%), outperforming the random forest (91%) and KNN (75%) methods, indicating its effectiveness in discerning subtle differences between micro-occurrence types. Lattice Boltzmann simulations were employed to study the impact of shale oil micro-occurrence type and saturation on fluid flow properties within the pore networks. Results showed that coating shale oil exhibited the highest permeability, followed by floating, whereas cementing shale oil caused a notable reduction in permeability due to pore blockage. This study enhances the understanding of the intricate relationship between shale oil geometric micro-occurrence patterns, pore structure, and fluid flow behavior within a digital-core framework, providing valuable insights into pore-scale fluid dynamics in shale reservoirs.</div></div>","PeriodicalId":19938,"journal":{"name":"Petroleum Science","volume":"23 9","pages":"Pages 5819-5835"},"PeriodicalIF":6.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-party collaboration: Enhancing the resilience of multi-energy logistics systems under demand uncertainty","authors":"Yong-Tu Liang,&nbsp;Guang-Tao Fu,&nbsp;Hao-Chong Li,&nbsp;Ren-Fu Tu,&nbsp;Xiao-Chen Gong,&nbsp;Yan-Ling Zhou,&nbsp;Rui Qiu,&nbsp;Lin Wang","doi":"10.1016/j.petsci.2026.06.049","DOIUrl":"10.1016/j.petsci.2026.06.049","url":null,"abstract":"<div><div>The global low-carbon transition is driving refining enterprises to shift from oil-dominant production toward diversified production, requiring the collaborative allocation of refined oil and new energy. However, logistics systems face significant challenges arising from nonlinear demand fluctuations and external disturbances, which traditional static approaches fail to address effectively. To this end, this study proposes a multi-party collaborative framework for multi-energy logistics systems. Specifically, a hybrid demand forecasting model integrating variational mode decomposition and bidirectional long short-term memory is developed to capture demand fluctuation characteristics. Based on the forecasting results, a multi-product, multi-modal rolling robust simulation model is constructed to dynamically balance economic benefits and system resilience under uncertainty. The proposed framework is validated through a case study of a large Chinese petrochemical enterprise, and a multi-dimensional evaluation method incorporating resilience, economic, environmental and energy indicators is proposed. The results show that: (i) compared with the deterministic scheme, the proposed simulation scheme increases operating costs by 3.64% under high volatility scenarios, while improving service level by 3.18%, reducing average stockout duration by 29.5%, and decreasing stockout quantity by 46.15%; (ii) the optimized energy product structure achieved by the model reduces carbon emissions by 7.7% and increases calorific value by 7.6%; and (iii) the study reveals integrated refinery and new energy configurations enabled by multi-party collaboration, providing quantitative support for enhancing system resilience. Based on these findings, policy implications are proposed to promote the development of energy logistics systems.</div></div>","PeriodicalId":19938,"journal":{"name":"Petroleum Science","volume":"23 9","pages":"Pages 5836-5852"},"PeriodicalIF":6.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel ultra-high-temperature emulsifier stable at 250 °C for oil-based drilling fluids: Synthesis, performance, and mechanism","authors":"Quan-De Wang,&nbsp;Guan-Cheng Jiang,&nbsp;Teng-Fei Dong,&nbsp;Sheng-Ming Huang,&nbsp;Yin-Bo He,&nbsp;Li-Li Yang,&nbsp;Qi Feng,&nbsp;Hua-Yan Mu","doi":"10.1016/j.petsci.2026.04.009","DOIUrl":"10.1016/j.petsci.2026.04.009","url":null,"abstract":"<div><div>The ultra-high temperature conditions encountered in deep oil and gas exploration represent a critical challenge to oil-based drilling fluid (OBDF) technology. Conventional emulsifiers suffer from rapid deterioration of interfacial stability under harsh environments exceeding 200 °C, significantly increasing the risk of emulsion breakdown and creating a critical bottleneck for ultra-high temperature drilling operations. To address this challenge, this study aimed to develop a novel high-efficiency ultra-high temperature emulsifier (UHT-EM). The UHT-EM was successfully synthesized via a three-step method, and its molecular structure and excellent thermal stability were confirmed by Fourier-Transform Infrared Spectroscopy (FT-IR) and Thermogravimetric Analysis (TGA). The key synthesis process was optimized using response surface methodology, establishing optimal conditions (molar ratio 1.8, temperature 53 °C, catalyst dosage 13.4%) with an actual yield of 85.23%. Performance evaluation demonstrated that UHT-EM significantly reduced oil-water interfacial tension. At a dosage of 1.0%, the emulsion maintained optimal rheological properties and electrical stability (ES &gt; 1400 V) after thermal aging at 230 °C. Systematic temperature resistance tests revealed that the UHT-EM system maintained structural stability at 250 °C, while experiencing sharp performance deterioration at 260 °C due to interfacial film disruption. Microscopic analysis revealed that stabilization mechanism arose from a dense interfacial adsorption layer, while interface failure was caused by intensified molecular thermal motion under high-temperature conditions. The innovation of this research lay in developing a novel emulsifier with well-defined temperature resistance and revealing its stabilization and failure mechanisms through multi-scale analysis, providing crucial material support and theoretical foundation for ultra-high temperature drilling fluid design.</div></div>","PeriodicalId":19938,"journal":{"name":"Petroleum Science","volume":"23 9","pages":"Pages 5648-5661"},"PeriodicalIF":6.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning-based upscaling for reservoir models on corner-point grids via finite-volume physics-informed Fourier neural operator","authors":"Jing-Qi Lin,&nbsp;Xia Yan,&nbsp;Kai Zhang,&nbsp;Qi Zhang,&nbsp;Zhao Zhang,&nbsp;Li-Ming Zhang,&nbsp;Pi-Yang Liu","doi":"10.1016/j.petsci.2026.04.037","DOIUrl":"10.1016/j.petsci.2026.04.037","url":null,"abstract":"<div><div>This study proposes a neural network (NN)-assisted, physics-informed framework for global flow-based upscaling to accelerate reservoir simulation. While traditional global upscaling methods can accurately capture fine-scale flow characteristics, their high computational cost hinders practical application in ensemble-based uncertainty quantification and optimization workflows. Existing NN-assisted upscaling approaches predominantly rely on numerical simulation data, which remains computationally expensive and often lacks physical interpretability. Furthermore, no current method enables physics-informed training for corner-point grid (CPG) models without simulation data, limiting the application of deep learning in practical geological model upscaling. To address these limitations, we develop a finite-volume physics-informed Fourier neural operator (FV-PIFNO) as a pressure-solution surrogate model for CPG models. This physics-driven approach eliminates the need for simulation data and inherently enforces inter-grid flux continuity during inference. A flow-based numerical post-processing procedure is designed to compute coarse-grid transmissibility and well index that are strictly equivalent to fine-scale fluxes, naturally extending to non-orthogonal CPG systems. Comparisons are designed between different mapping and driving methods. Validation on synthetic models demonstrates that the fully physics-constrained approach achieves high accuracy in both single-phase and two-phase flow simulations, along with strong generalization to heterogeneous scenarios. Application to a standard SAIGUP model confirms that the framework achieves accuracy comparable to numerical upscaling while significantly improving computational efficiency, demonstrating its potential for practical, high-fidelity reservoir upscaling.</div></div>","PeriodicalId":19938,"journal":{"name":"Petroleum Science","volume":"23 9","pages":"Pages 5662-5692"},"PeriodicalIF":6.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trans-layer inversion of logging-while-drilling azimuthal electromagnetic measurements guided by multi-boundary detection capability assessment","authors":"Yan-Xue Wang,&nbsp;Lei Wang,&nbsp;Xin-Min Ge,&nbsp;Yi-Ren Fan","doi":"10.1016/j.petsci.2026.04.044","DOIUrl":"10.1016/j.petsci.2026.04.044","url":null,"abstract":"<div><div>The inversion of logging-while-drilling azimuthal electromagnetic measurements is essential for geosteering in horizontal wells and optimizing reservoir development. Conventional fixed-layer inversion models lack adaptability to dynamically varying formations, resulting in limited applicability and a trade-off between accuracy and efficiency. This study introduces a trans-layer inversion method that adaptively optimizes model complexity. The method quantifies the tool's multi-boundary detection capability using eigenvalue analysis of the Fisher information matrix. Statistical analysis of synthetic models informs the construction of an inversion model library spanning two-to five-layer configurations, facilitating adaptation to diverse formation geometries. To address the dependence of multi-layer inversion on initial values, a progressively increasing model complexity hot-start mechanism is implemented, allowing lower-order inversion results to constrain higher-order models. A comprehensive quality score autonomously selects the optimal inversion model. Numerical examples demonstrate that: (1) in a three-layer sand-shale sequence, the method enhances early recognition of reservoir boundaries due to the model library's coverage of all tool positions; (2) in a six-layer thin-bed model, the trans-layer inversion reduces mean square error by 91.5% compared to conventional three-layer inversion, significantly improves thin-bed imaging resolution, and doubles computational efficiency relative to fixed five-layer inversion; (3) in an anticlinal reservoir model, the method accurately tracks both reservoir structure and internal oil-water contacts; (4) field data validation from a complex clastic reservoir confirms the method's ability to delineate thin shale layers and guide well trajectory in real drilling scenarios. This approach offers a robust solution to the challenges of model applicability and computational efficiency in LWD inversion.</div></div>","PeriodicalId":19938,"journal":{"name":"Petroleum Science","volume":"23 9","pages":"Pages 5418-5432"},"PeriodicalIF":6.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine-learning predictions of high-pressure high-temperature filtrate loss in oil-based drilling fluids from well-site measurements","authors":"Shadfar Davoodi,&nbsp;Arslan Gulniyazov,&nbsp;David A. Wood,&nbsp;Mohammed Al-Shargabi,&nbsp;Nikita Makarov,&nbsp;Evgeny Burnaev","doi":"10.1016/j.petsci.2026.03.053","DOIUrl":"10.1016/j.petsci.2026.03.053","url":null,"abstract":"<div><div>Precise and reliable predictions of filtrate loss (FL) from drilling fluids/muds under high-pressure-high-temperature (HPHT) conditions are required to prevent formation damage, maintain wellbore stability, and optimize drilling efficiency in complex reservoirs. Traditional laboratory-based measurements are too time consuming to provide HPHT FL values that are useable for decision-making while drilling. This study, therefore, develops machine learning (ML) models that enable frequent and prompt predictions of HPHT FL with high accuracy and reliable precision. To this end, a large dataset was compiled containing five input parameters, namely mud temperature (MT), mud weight (MW), funnel viscosity (FV), mud alkalinity (MA), and electrical stability (ES), and a single target variable HPHT FL. Following meticulous data preprocessing, four predictive models were developed using established ML algorithms: multilayer perceptron neural network (MLPNN), support vector regression (SVR), extreme gradient boosting (XGBoost), and extreme learning machine (ELM). For each ML algorithm, five separate model instances were developed and evaluated, with XGBoost providing the best performance in predicting the target parameter (root mean square error (RMSE) = 0.096 cc/30 min for the testing subset). The superior performance of the XGBoost model was further confirmed by residual, uncertainty, overfitting, and robustness evaluations, indicating its excellent generalization capability. Shapley additive explanations (SHAP) analysis identified ES as the most influential input parameter and FV as the least influential for XGBoost’s HPHT FL predictions. The XGBoost model as developed offers a substantial improvement compared to laboratory FL analysis, enabling more efficient and quicker monitoring of FL in challenging HPHT downhole environments.</div></div>","PeriodicalId":19938,"journal":{"name":"Petroleum Science","volume":"23 9","pages":"Pages 5543-5560"},"PeriodicalIF":6.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}