Geoenergy Science and Engineering最新文献

{"title":"Study on the computational model and distribution characteristics of rock fracture energy induced by supercritical CO2 phase transition","authors":"Erdi Abi ,&nbsp;Qifu Zeng ,&nbsp;Mingwei Liu ,&nbsp;Yingren Zheng ,&nbsp;Yafeng Han ,&nbsp;Mingjing Jiang ,&nbsp;Fayou Wu ,&nbsp;Deying Tang ,&nbsp;Hongbo Du ,&nbsp;Jie Zhang","doi":"10.1016/j.geoen.2025.213862","DOIUrl":"10.1016/j.geoen.2025.213862","url":null,"abstract":"<div><div>The current research on the energy distribution characteristics of supercritical CO₂ phase transition fracturing (CDPTF) is relatively lacking, particularly for effective quantitative calculation methods. This study develops models to calculate CO₂ shock wave and gas expansion energy, quantifying their roles in rock damage and energy distribution. Five field tests measured acoustic wave velocity, rock damage, and energy distribution during CO₂ rock fracturing. The results indicate that supercritical CO₂ creates large rock fragments, with a small crushing zone, forming numerous through-cracks on the surface and causing weak seismic effects. Additionally, the radius of rock failure ranges from 4.3 to 5.6 m, with gas expansion energy accounting for 84.36 % and shock wave energy only 15.64 %. Specifically, the average energy proportion of the shock wave used for rock fragmentation, crack formation, and surface vibration is 2.57 %, 12.13 %, and 1.94 %, respectively. The average energy proportion of gas expansion used for crack propagation is 42.15 %, while the energy used for gas ejection (i.e., wasted energy) accounts for 41.21 %, reflecting a relatively high overall energy efficiency. Furthermore, reducing the initial phase change pressure or increasing the tensile strength of the rock can effectively improve energy utilization efficiency. Minimizing gas leakage or applying the method in high-strength rock areas can further enhance the efficiency of gas expansion energy in rock fracturing. This study provides a theoretical basis for optimizing CDPTF energy utilization in rock fracturing.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"251 ","pages":"Article 213862"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143760758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experimental and application research on sweep efficiency for non-condensable gases assisted vertical-horizontal steam drainage in extra-heavy reservoirs","authors":"Yuting Wang ,&nbsp;Peng Liu ,&nbsp;Daode Hua ,&nbsp;Zhongyi Zhang ,&nbsp;Chao Wang ,&nbsp;Pengcheng Liu ,&nbsp;Jipeng Zhang ,&nbsp;Shuo Yang ,&nbsp;You Zhou","doi":"10.1016/j.geoen.2025.213857","DOIUrl":"10.1016/j.geoen.2025.213857","url":null,"abstract":"<div><div>The vertical-horizontal steam drainage (VHSD) method, combining vertical and horizontal wells, enhances steam-assisted gravity drainage to improve sweep efficiency and oil-steam ratios in extra-heavy oil reservoirs. This approach has become an effective alternative to steam stimulation in aging oil fields, particularly in China. However, thermal losses in late-stage VHSD can reduce the oil-steam ratio. The use of non-condensable gases like CO₂, CH₄, and N₂ may improve this process. Previous research on non-condensable gases mainly focused on steam-assisted gravity drainage (SAGD) with parallel, closely spaced wells, whereas VHSD uses wells positioned 50–60 m apart, affecting steam chamber dynamics and gas behavior.</div><div>This study is the first systematic investigation of non-condensable gases in VHSD, using the Z1 block of Xinjiang Oilfields in China as a case study. It examines the effects of CO₂, CH₄, and N₂ in enhancing VHSD, combining lab experiments with field research. A novel approach emphasizes well arrangement's impact on gas distribution and steam chamber development. The results show that CO₂ outperforms CH₄ and N₂ in solubility and viscosity reduction, leading to the highest sweep efficiency. At 1 MPa, CO₂ and CH₄ increased oil recovery by 4.47 % and 1.63 % respectively. At 2 MPa, the increases were 8.01 % and 5.1 %, while N₂ slightly reduced efficiency. Non-condensable gases accumulated at the steam chamber boundary, impacting heat loss, chamber morphology, and expansion rates. CO₂-assisted development yielded the best results, with a 4.3 % recovery rate increase. While N₂ effectively enhanced the oil-steam ratios, its influence on the recovery rate was relatively modest.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"251 ","pages":"Article 213857"},"PeriodicalIF":0.0,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of solid concentration profiles in particle sedimentation in directional reservoirs using the gamma-ray attenuation technique","authors":"R.S. Schimicoscki ,&nbsp;E.A. Souza ,&nbsp;F.M. Fagundes ,&nbsp;J.J.R. Damasceno ,&nbsp;F.O. Arouca","doi":"10.1016/j.geoen.2025.213865","DOIUrl":"10.1016/j.geoen.2025.213865","url":null,"abstract":"<div><div>Sedimentation of solid particles in drilling fluids poses significant challenges in directional drilling operations. This study investigates the dynamics of solid sedimentation in directional wells, considering various fluid rheologies. Experimental tests were conducted using three types of suspensions: aqueous media with calcium carbonate, aqueous media with glycerin, and aqueous media with xanthan gum, the latter two containing glass microspheres. These experiments were conducted across inclinations ranging from 0° to 60°, employing the gamma-ray attenuation technique. Results revealed that inclination intensifies the Boycott effect and alters concentration curve behaviors. Particularly, fluids with re-established gel structures exhibited accelerated sedimentation velocities, indicating the profound influence of fluid rheology on sedimentation dynamics. These findings underscore the pivotal roles of inclination and fluid rheology in governing sedimentation behavior, critical for designing directional wells and optimizing oil extraction processes. Insights from this study offer potential to mitigate operational risks, enhance drilling efficiency, and advance drilling practices for challenging environments.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"251 ","pages":"Article 213865"},"PeriodicalIF":0.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust multi-objective production optimization with CO2 emissions reduction","authors":"Dean S. Oliver ,&nbsp;Jon Sætrom ,&nbsp;Arne Skorstad ,&nbsp;Trond Saksvik ,&nbsp;Odd Kolbjørnsen","doi":"10.1016/j.geoen.2025.213845","DOIUrl":"10.1016/j.geoen.2025.213845","url":null,"abstract":"<div><div>In this paper, we describe an efficient methodology for simultaneously maximizing the expected profitability of oil field production and minimizing the expected emission of greenhouse gasses associated with the production through optimizing controls of the reservoir injection and production wells. Instead of simply minimizing water production and injection as is often done as a surrogate for energy consumption, we use an emissions calculator to account for the energy efficiency of the injection and compression system. Because our approach to minimization is efficient, we are able to account for uncertainty in geology during the minimization and to use the operational simulation model for the field.</div><div>The most common approach to solving for Pareto optimal solutions is through some type of scalarization of the optimization problem. In this study, we apply the weighted-sum method, which despite its limitations when applied to problems with feasible regions for objective outcomes that are not convex provides Pareto optimal solutions at a relatively low cost.</div><div>Finally, we apply the methodology to the problem of well controls for a three-well field in the Norwegian Sea with platform facilities shared by another field. The reservoir model has 330,000 active cells with an active aquifer. The emissions calculator uses pump characteristics to account for fuel usage attributed to water injection. Gas compression, water treatment, and base energy costs are estimated by calibration of allocated energy usage to historical production data. The expectation of the objective functions is approximated by the sample average of the objective functions over the ensemble of 50 history-matched model realizations. Control variables are the injector and producer rates over one-month intervals. The Stochastic Simplex Approximate Gradient (StoSAG) method was used to estimate the gradient of the scalarized objective function and a quasi-Newton method (BFGS) was used for minimization. Results showed that moderately large reductions in CO2 emissions from a reference case optimized purely for profitability could be obtained at the cost of modest reductions in NPV. Larger reductions in CO<span><math><msub><mrow></mrow><mrow><mi>2</mi></mrow></msub></math></span> emissions were costlier. Additionally, the optimized reservoir production strategies were not intuitively obvious, indicating that a formal multi-objective optimization approach was beneficial.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"251 ","pages":"Article 213845"},"PeriodicalIF":0.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143760757","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":"Effect of surfactants C12PO6 and SW320 on oil/CO2 minimum miscibility pressure of unconventional liquid reservoirs - molecular dynamics simulation study","authors":"Zhenzhen Dong ,&nbsp;Tong Hou ,&nbsp;Weirong Li ,&nbsp;Changbin Hou ,&nbsp;Chenhong Guo ,&nbsp;Zhanrong Yang ,&nbsp;Xueling Ma","doi":"10.1016/j.geoen.2025.213863","DOIUrl":"10.1016/j.geoen.2025.213863","url":null,"abstract":"<div><div>CO₂ flooding has been identified as an effective method for enhancing the recovery rate of unconventional oil and gas. However, in many oilfields, the miscibility pressure of CO₂ with crude oil exceeds the oilfield pressure, preventing them from achieving miscibility. This impedes the desired recovery outcomes. Surfactants present a solution to this challenge, as they can reduce the miscibility pressure between CO₂ and crude oil, thereby elevating the recovery rate. Yet, the microscopic dynamics of how surfactants modulate the MMP in CO₂ flooding within ULRs remain under-explored.</div><div>This research aims to delve into this gap, using molecular dynamics to elucidate the underlying mechanisms and potential benefits of surfactant inclusion in CO₂ flooding applications for unconventional reservoirs.</div><div>Our study, rooted in molecular dynamics, seeks to demystify these dynamics and understand surfactants' role more profoundly. Delving into the CO₂-n-decane system, we discovered that C₁₂PO₆ and SW320 significantly alter the interfacial width by forming a molecular film, which enhances CO₂'s solubility in crude oil. Notably, SW320 emerged as more potent than C₁₂PO₆ in this regard. Both C₁₂PO₆ and SW320 managed to reduce the MMP of the CO₂-n-decane system by more than 15 %. However, in terms of cost-effectiveness, C12PO6 offers a compelling balance between performance and affordability compared to SW320. Further insights revealed that the structure of the C₁₂PO₆ surfactant plays a crucial role in determining its MMP reduction capacity. Intriguingly, the addition of low carbon alcohols, especially n-pentanol, enhances the C₁₂PO₆ surfactant's surface activity, underscoring its superiority over ethanol in reducing interfacial tension.</div><div>In essence, this research offers a microscopic lens to view the intricate dance of surfactants in CO₂ flooding within ULRs. Our findings provide a robust framework for refining recovery strategies in unconventional reservoirs, potentially transforming the landscape of CO₂ flooding methodologies to ensure more sustainable and efficient oil and gas extraction.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"251 ","pages":"Article 213863"},"PeriodicalIF":0.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent multiple parameters optimization methods integrating hydraulic model and SIAs with various constraints for extended reach drilling","authors":"Hailong Jiang ,&nbsp;Tao Zhang ,&nbsp;Yan Xi ,&nbsp;Gonghui Liu ,&nbsp;Jun Li","doi":"10.1016/j.geoen.2025.213846","DOIUrl":"10.1016/j.geoen.2025.213846","url":null,"abstract":"<div><div>Extended reach drilling (ERD) plays a crucial role in deep water and ultra-deep reservoirs exploitation. Cuttings are prone to deposit to the lower side of wellbore when rate of penetration (ROP) is high in ERD. Drilling problems caused by insufficient wellbore cleaning will increase drilling costs and decrease ROP. Therefore, keeping a high ROP and ensuring wellbore cleaning is very important by optimizing hydraulic parameters. This paper proposes intelligent multiple hydraulic parameters optimization methods integrating accurate hydraulic model and particle swarm optimization algorithm (PSO) as well as sparrow search algorithm (SSA) with various constraints to maximize drill bit hydraulic power, which are abbreviated as MPOM-PSO and MPOM-SSA. Rheological parameters of seven rheological models are calculated regressively and the best rheological model is preferred to improve accuracy of pressure loss. Interrelationship between rock breaking and wellbore cleaning as well as constraints of formation pressure, rated pressure of circulation system, rated flow rate of pump and cuttings bed thickness are considered in MPOM-PSO and MPOM-SSA. It overcomes defects of computation-intensive and inability to perform multi-parameters optimization simultaneously compared to traditional optimization methods. The accuracy of hydraulic model is validated by comparing with results calculated by Landmark. The rheological parameter calculation errors of both Power–Law model and Herschell–Bulkley model are less than 1%. In terms of frictional pressure losses in annulus and in drillstring and standpipe pressure, the average errors are 1.8% and 3.5% for Power-law mode and Herschell–Bulkley mode respectively. The efficacy of MPOM-PSO and MPOM-SSA is proved by Case studies and statistic analysis. The maximum errors of optimal flow rate and density are less than 4% and 1% respectively contrasting to traditional method through 50 simulation experiments. However, the variance of optimal flow rate obtained by MPOM-SSA is larger, demonstrating MPOM-PSO is a litter better than MPOM-SSA. Also the optimization speed of MPOM-PSO is increased by more than 25 times. Through the application of MPOM-PSO and MPOM-SSA, hydraulic parameters can be optimized speedy and drilling efficiency of ERD can be improved.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"251 ","pages":"Article 213846"},"PeriodicalIF":0.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of domain-adaptive network with data augmentation in lithology identification of buried hill igneous rocks","authors":"Wenlong Liao ,&nbsp;Bin Zhao ,&nbsp;Chuqiao Gao ,&nbsp;Huanhuan Wang ,&nbsp;Hangyu Zhu","doi":"10.1016/j.geoen.2025.213848","DOIUrl":"10.1016/j.geoen.2025.213848","url":null,"abstract":"<div><div>Lithology identification is crucial in oil and gas exploration and development. Although traditional logging techniques and existing intelligent identification technologies have achieved significant progress in identifying lithology within conventional reservoirs, challenges persist in recognizing buried hill igneous rocks. Traditional logging methods rely on empirical rules and static models, which are inadequate for complex geological environments — particularly when severe overlap of logging response values occurs among different lithologies — resulting in poor identification capabilities. While intelligent identification technologies can enhance recognition accuracy by learning complex nonlinear features, they still face issues of insufficient generalization ability and model bias when dealing with data imbalance, feature crossover, and significant data distribution shifts between different wells. To address these limitations, we propose a data-analytically optimized Domain Adversarial Neural Network (DANN) framework for lithology identification. The main contributions of this paper include: (1) proposing an optimized data augmentation strategy to alleviate problems of data imbalance and feature overlap; (2) introducing an automatic feature weighting mechanism within the DANN framework to effectively tackle challenges associated with multi-source feature fusion and data distribution shifts; and (3) validating the proposed method on a real dataset from buried hill reservoirs in the northern South China Sea. The results demonstrate that, compared with traditional logging lithology identification methods and existing intelligent approaches, the proposed method exhibits superior performance in cross-well lithology identification. Additionally, the optimized data augmentation strategy significantly reduces model bias caused by data imbalance and overlapping logging response features, enhancing the overall accuracy of lithology identification.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"251 ","pages":"Article 213848"},"PeriodicalIF":0.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143760756","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":"Energy transition, mechanical response and rock fragmentation in percussion drilling: A review","authors":"Yanliang Li ,&nbsp;P.G. Ranjith","doi":"10.1016/j.geoen.2025.213838","DOIUrl":"10.1016/j.geoen.2025.213838","url":null,"abstract":"<div><div>Depleting shallow resources and the growing climate crisis have increased demand for deep resource development and surface waste storage. This necessitates advancements in drilling engineering to address the high costs associated with low drilling rates, particularly in deep hard rock formations. Percussion drilling has emerged as a preferred method for its efficiency in hard rocks. This study reviews the historical development of percussion drilling and discusses existing experimental testing methods, emphasizing the challenges related to automation and data collection. This review article quantifies energy transfer, distribution, and transition during the multiphase interactions in the percussion drilling process. Key factors affecting the mechanical response of the bit-rock interaction during percussion drilling are explored. Finally, the review discusses how these factors influence rock fragmentation performance and damage characteristics. Despite extensive research, key gaps persist in understanding rock failure under high-temperature and in-situ pressure conditions. This review highlights current research gaps and proposes future directions, including the need for comprehensive experimental studies, the development of advanced modeling techniques, and the consideration of deep high-temperature and high-pressure conditions. Addressing these gaps can significantly enhance drilling efficiency and contribute to more sustainable resource extraction strategies. Additionally, the insights and conclusions from this study are not exclusive to drilling engineering but can also provide references for mining, underground space construction, and tunnel excavation fields.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"250 ","pages":"Article 213838"},"PeriodicalIF":0.0,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143679410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing post-stack seismic inversion through music-inspired harmony search optimization technique. A case study","authors":"Ravi Kant ,&nbsp;Brijesh Kumar ,&nbsp;S.P. Maurya ,&nbsp;Satya Narayan ,&nbsp;A.P. Singh ,&nbsp;G. Hema","doi":"10.1016/j.geoen.2025.213854","DOIUrl":"10.1016/j.geoen.2025.213854","url":null,"abstract":"<div><div>A novel post-stack seismic inversion algorithm has been developed to estimate acoustic impedances using P-wave reflection seismic data, employing the music-inspired harmony search global optimization (HSO) technique. This optimization seeks to find the global minimum of the objective function, which measures the misfit between synthetic and observed post-stack seismic data. During the iterative inversion process, acoustic impedance models are randomly perturbed, and synthetic seismic data are recalculated to match observed data. To enhance stability, the algorithm uses constraints from a well-log-derived low-frequency impedance model. The proposed algorithm was tested on synthetic and real data to demonstrate its effectiveness in post-stack seismic data inversion. On synthetic test, we found high accuracy of the HSO-generated traces, with average correlations of 0.99, 0.99, 0.97, and 0.96, and RMS errors of 0.12, 0.40, 0.50, and 0.62, for noise levels of 0 %, 10 %, 20 %, and 30 %, respectively. For real data from the Blackfoot Field, Alberta, Canada, the algorithm achieved a 0.93 correlation and 0.22 RMS error, enabling seismic data inversion for acoustic impedance estimation. The inverted section identified low acoustic impedance (8000–9000 m/s∗g/cc), matching the high seismic amplitude anomaly, suggesting a sand channel reservoir between 1040 and 1065 ms two-way travel time. While, high acoustic impedance (9000–12000 m/s∗g/cc) indicating background shale facies. This study explores potential hydrocarbon reservoirs in the Blackfoot Field, Alberta, using HSO-based advanced global optimization for efficient and accurate seismic data inversion.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"250 ","pages":"Article 213854"},"PeriodicalIF":0.0,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143704568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting mud weight in carbonate formations using seismic data: A data-driven approach","authors":"Georgy Peshkov ,&nbsp;Kerim Khemraev ,&nbsp;Sergey Safonov ,&nbsp;Nikita Bukhanov ,&nbsp;Ammar Alali ,&nbsp;Mahmoud Abughaban","doi":"10.1016/j.geoen.2025.213850","DOIUrl":"10.1016/j.geoen.2025.213850","url":null,"abstract":"<div><div>Accurate mud weight prediction is crucial for safe and efficient drilling operations in overpressured formations. Especially. Traditional approaches heavily rely on manual seismic interpretation, which is limited by data noise and high dimensionality, and the need for well log data. This study aims to address these challenges by integrating advanced machine learning techniques with seismic and mud weight data, focusing on developing an automated, data-driven workflow that can reliably predict appropriate mud weight trends across large-scale geological fields. The methodology employs a neural network (NN) autoencoder for seismic dimensionality reduction, retaining critical geological features in latent layers. Optimized input features are selected using statistical and interpretability-driven techniques. A k-nearest neighbors model, tuned through grid search, serves as the predictive core, with kriging applied to refine spatial predictions and reduce errors. The approach demonstrates improved geological interpretability and accuracy compared to conventional methods. Applied to a large carbonate field, the workflow effectively predicts spatial mud weight variations, highlighting its scalability and reliability. By combining autoencoding, feature selection, and geostatistical refinement, this methodology offers a robust and interpretable framework for tackling complex geological challenges in drilling operations.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"250 ","pages":"Article 213850"},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}