📚 Eksplorasi & Komparasi Topik Dokumen
Pencarian topik
Hasil Dokumen
Ditemukan: 14 dokumenROCK TYPING BERBASIS LOG MENGGUNAKAN UNSUPERVISED MACHINE LEARNING YANG DIEVALUASI TERHADAP REFERENSI DISCRETE ROCK TYPE TURUNAN HFU DI LAPANGAN 'X'
Core-based rock typing is limited by the sparse availability of core data, whereas well logs are recorded continuously along the wellbore. This study evaluates whether unsupervised machine learning applied to well logs can reproduce a core-derived petrophysical rock type reference in the 'X' field, Central Sumatra Basin. A reference was built from 85 routine core analysis (RCAL) samples using the RQI–????z–FZI–DRT framework, and the eight original DRT classes were lumped into four hydraulic-flow-unit (HFU)-derived rock types (RT1 – RT4). Four unsupervised methods: K-Means, FCM, GMM, and MRGC, were applied to five standardized log features (GR, DT, SP, RHOB_STD, and a harmonized deep resistivity proxy, RES_DEEP) from three wells, with all core-derived variables excluded to prevent data leakage. The clusters were mapped using the Hungarian algorithm and evaluated per well and for all wells combined. GMM gave the best combined agreement (accuracy 42.35%, ARI 0.0367), but the per well results were weak (near random in the most sampled well (WS-002) and collapsed to a single rock type in WS-004) indicating that the available conventional logs only partially reproduce the HFU-derived rock types.
ENSEMBLE STACKING BERBASIS NEURO-FUZZY UNTUK PREDIKSI GAS KUMULATIF PADA RESERVOIR DELTAIK: STUDI KASUS DI CEKUNGAN NATUNA
Reservoir characterization is essential in field development planning, particularly in heterogeneous formations where accurate interpretation of well log data strongly influences production decisions. Conventional interpretation methods are often subjective and inconsistent due to reliance on expert judgment. To overcome these limitations, this study proposes a data-driven workflow that integrates unsupervised clustering for reservoir zonation based on similar petrophysical characteristics, which is subsequently used to support supervised modeling. A supervised machine learning framework is developed for cumulative gas prediction using conventional well log data, including gamma ray, resistivity, bulk density, and neutron porosity. Data preprocessing is conducted through normalization to ensure feature scale consistency. Multiple base learners are trained to capture nonlinear relationships between log responses and cumulative gas, and their outputs are integrated using a stacking ensemble with a metalearner to improve predictive robustness. To enhance interpretability, an Adaptive Neuro-Fuzzy Inference System (ANFIS) is incorporated into bridge data-driven learning with rule-based geological reasoning. In addition, Sobol normalized sensitivity analysis is applied to quantify feature contributions and assess model reliability in a consistent interpretability framework. A case study from Field X, Natuna Basin, Indonesia, is used to validate the proposed approach using labeled production and well log data. The results demonstrate that the proposed framework improves cumulative gas prediction while maintaining interpretability and provides a robust data-driven basis for identifying prospective perforation intervals in field development planning.
OPTIMASI SISTEM HIDRAULIKA PENGEBORAN PADA SUMUR Y DI LAPANGAN Z DALAM KONDISI NARROW MUD WINDOW
This study aims to evaluate the drilling hydraulics of Well Y located in Jambi Province, which is characterized by dominant claystone, sandstone, shale, and siltstone formations. Well Y also exhibits pore pressure and fracture gradient conditions that are closely spaced, indicating the presence of a narrow mud window that increases the technical risks during drilling operations. The research focuses on analyzing the relationship between minimum flow rate and rate of penetration (ROP), pressure losses, equivalent circulating density (ECD), flow regime, annular velocity, as well as bit optimization using the hydraulic horsepower per square inch (HSI) parameter. The study was conducted using reference data from wells X-1 and X-2, and modeling was performed with Landmark software. Compass was used for trajectory design, StressCheck for casing design and strength evaluation, and WellPlan for BHA design and hydraulic optimization. The evaluation covered the relationship between minimum flow rate and ROP, distribution of pressure losses, ECD analysis, flow regime and annular velocity, and bit optimization by considering nozzle size and pump rate. The results indicate that the minimum flow rate requirement increases with higher ROP. In Section 9 5/8”, the required flow rate ranged from 380–410 GPM at low ROP and increased to >740 GPM at 320 ft/hr, while in Section 7” the requirement was lower, ranging from 170–340 GPM, and started to increase after the ROP exceeded 160–200 ft/hr. The relationship between flow rate and ROP was strongly influenced by annulus geometry. The largest pressure losses occurred in the drill string, recorded at 1,448.96 psi (59.05%) in Section 9 5/8” and 1,761.76 psi (70.55%) in Section 7”, although the resulting standpipe pressure remained below the maximum operating limit of 2,500 psi. The ECD values were within the mud window, ranging from 9.13–9.16 ppg in Section 9 5/8” and 10.17–10.32 ppg in Section 7”. Flow regime analysis showed laminar flow in Section 9 5/8” at pump rates below 1,100 GPM, while in Section 7” turbulent flow occurred beyond 3,653 ft MD at pump rates greater than 350 GPM. HSI evaluation also indicated optimum conditions, with HSI of 3.0 (TFA = 0.862 in², pump rate 916.5 GPM) in Section 9 5/8” and HSI of 2.1 (TFA = 0.985 in², pump rate 602.6 GPM) in Section 7”, ensuring effective hole cleaning without exceeding the surface pressure limit. This study provides a comprehensive approach to drilling hydraulics optimization by integrating casing design, BHA configuration, and hydraulic system performance. It presents an evaluation of the interaction between flow rate, pressure losses, ECD, and bit hydraulics optimization under geological conditions with a narrow mud window.
PETA KUALITAS RESERVOIR DENGAN PENDEKATAN TOP-DOWN MENGGUNAKAN POLA PENGENALAN FUZZY: STUDI KASUS LAPANGAN
This study proposes an AI-driven approach for reservoir quality mapping, integrating Fuzzy Logic and Fuzzy Pattern Recognition (FPR) within the Top-Down Reservoir Modelling (TDRM) framework. The goal is to identify the most effective method for defining reservoir boundaries and representing quality variations over time. Three methods 4x4 uniform grid, fuzzy boundaries, and gradient-based (linear regression) segmentation are compared for accuracy and consistency. Cumulative production data from 70 wells in the Northwest Java Basin (1970-2025) were processed using Fuzzy C-Means clustering into four quality classes: “poor,” “average,” “good,” and “excellent.” Reservoir segmentation was performed using spatial attributes and tested across multiple time intervals, with blind testing to evaluate robustness. Findings show that the uniform grid method cannot capture actual reservoir complexity, while fuzzy boundaries yield dynamic but overly broad, literature-inconsistent results. The gradient-based method, using slope variations in production curves, provides the most accurate and consistent boundaries, aligning with fuzzy clustering outcomes. Observed quality shifts, such as between “poor” and “average,” were effectively represented, supporting better field development decisions. The study concludes that gradient-based segmentation is the most reliable for boundary delineation, while fuzzy clustering effectively classifies reservoir quality in complex, uncertain conditions.
COMPUTATIONAL FLUID DYNAMICS SIMULATION OF DRILLING FLUID CIRCULATION IN INCLINED WELLS: ASSESSING FLOW BEHAVIOR, VELOCITY PROFILE, PRESSURE DISTRIBUTION, AND EROSION RISK
Efficient drilling fluid circulation is required to maintain wellbore stability, transport cuttings, and manage formation pressure. In deviated wells, flow behavior becomes progressively asymmetric, resulting in uneven distribution of velocity and pressure, as well as secondary flows such as swirl, which affect hydraulic performance. This study employs Computational Fluid Dynamics (CFD) to simulate water-based drilling fluid circulation under steady-state, single-phase, and isothermal conditions. The modeling was carried out by defining the well geometry, applying appropriate meshing and boundary conditions, and solving the governing equations until convergence. Sensitivity analyses were then conducted on flow rate and inclination angles ranging from 30° to 90°. The study found that cuttings transport requires an outlet velocity of 0.75 m/s, which can only be achieved at flow rates of 300 GPM or above. Pressure loss peaked at 45°, while outlet velocity reached its maximum at 60°, indicating a non-linear trend. Distinct flow features were detected, including jetting near the bit, asymmetric velocity profiles, and swirl-induced turbulence in the lower annulus. These conditions were also associated with potential erosion zones, particularly around the nozzle exit and lower curved sections of the wellbore. The findings contribute to a better understanding of flow dynamics in inclined wells and offer practical guidance for improving drilling fluid circulation design and minimizing erosion risks in complex geometries.
ANALISA PENGUSULAN INVESTASI PROYEK PENGEMBANGAN SUMUR MINYAK DAN GAS PADA STRUKTUR MUGI 2B PT PERTAMINA HULU ROKAN ZONA 4
Lifting produksi minyak dan gas bumi setiap tahun terus mengalami penurunan. Dalam rangka upaya peningkatan produksi minyak dan gas bumi diperlukan pengusulan investasi proyek pengembangan sumur minyak dan gas bumi. Suatu investasi proyek pengembangan sumur minyak dan gas bumi akan mendapatkan persetujuan pembiayaan oleh negara , jika parameter keekonomian dikatakan layak untuk dilaksanakan. Dalam pengusulan investasi proyek pengembangan sumur minyak dan gas bumi ini, dilakukan analisa terhadap 2 opsi pengembangan, yaitu opsi pertama adalah melakukan sewa Early Production Facilities dan membangun fasilitas produksi permanen atau opsi yang kedua adalah melakukan sewa Early Production Facilities dan tidak membangun fasilitas produksi permanen. Studi ini mengidentifikasi usulan proyek investasi untuk pengembangan sumur minyak dan gas dengan Net Present Value (NPV) sebesar $42,555 MUSD, Internal Rate of Return (IRR) sebesar 40,20%, dan Pay Out Time selama 4,50 tahun. Analisis sensitivitas menunjukkan bahwa lifting minyak (produksi) & harga minyak merupakan variabel yang paling sensitif. Selain itu, analisis skenario dengan skenario maksimum (terbaik) menghasilkan NPV sebesar 79,210 dan skenario minimum (terburuk) menghasilkan NPV sebesar 8,557 MUSD, sedangkan simulasi Monte Carlo menunjukkan probabilitas NPV < 0 sebesar 0% dan NPV > 0 sebesar 100%.
ENHANCING OIL-WATER RELATIVE PERMEABILITY PREDICTION USING HYBRID MACHINE LEARNING
In oil and gas reservoirs, understanding how multiple fluids flow simultaneously is crucial for optimizing production, and relative permeability is the key parameter governing this complex process. Traditional barriers of resource-intensive and costly core flooding experiments have motivated our study to overcome these challenges, using machine learning models for a comprehensive understanding of fluid behavior within reservoirs. This research aims to explore the potential of machine learning to enhance the accuracy of oil and water relative permeability prediction.. This study utilizes data from core samples representing different lithologies, specifically sandstone from the Talang Akar Formation and carbonate from the Baturaja Formation, collected from three oil fields in Indonesia. This initial dataset, comprised of 519 data points, was obtained after removing data points exhibiting the impact of fine migration to ensure the accuracy of the machine learning models. This study introduces the use of hybrid machine learning models to predict oil and water relative permeability curves without relying on absolute permeability as an input feature. Altough absolute permeability has been shown to be strongly correlate ted with relative permeability in previous studies, this research deliberately excludes it to explore alternative predictive parameters. By utilizing readily available data, including water saturation, irreducible water saturation, residual oil saturation, and porosity, our models achieve accurate and rapid predictions of relative permeability. This novel approach has the potential to make reservoir characterization easier and reduce the need for time-consuming and expensive special core analysis. Furthermore, our study explores the potential of these models to correct core sample data affected by fine migration, a common challenge in special core analysis. This finding offers a promising approach for improving the reliability of relative permeability data, particularly in cases where fine migration is an important consideration.
SCREENING POTENTIAL OIL WELLS FOR FRACTURING CAMPAIGN PROGRAM AT BX FIELD
This study focuses on selecting well candidates for hydraulic fracturing in the BX Field, with the main objective of increasing oil and gas production. The BX Field, which was discovered in 1975 and started production in 2004, experienced significant production decline due to reservoir complexities, such as severe compartmentalization and low gas lift efficiency. To overcome these challenges, hydraulic fracturing was identified as a potential method to stimulate production in zones with low and medium permeability. The well candidate selection process was conducted by analyzing reservoir and well properties, and estimating production enhancement using Decline Curve Analysis and Unified Fracture Design approaches. The study also considered screening parameters such as water cut, permeability, and productivity index to determine the best well candidates. The study results showed that four wells, namely A6, A28, A33, and A42, were selected for hydraulic fracturing. Production projections after one year of hydraulic fracturing showed a significant increase in production, with the best production at A6 achieving an additional production of 5692.15 bbl and a net profit of $12,879,971.41. In conclusion, hydraulic fracturing of selected wells in the BX Field can improve production efficiency and provide substantial economic benefits. This study provides optimal well selection based on parameters such as permeability, productivity index, and water cut, as well as economic analysis to ensure the profitability of hydraulic fracturing operations. The screening parameters were modified to align with the capabilities of the wells in the BX Field. The results of this study provide insights into well selection strategies to maximize production potential in the BX Field.
OPTIMUM GAS LIFT INJECTION DESIGN TO IMPROVE WELL X PERFORMANCE
This study aims to optimize the gas lift injection design to improve the performance of well X. The steps taken include evaluating the current gas lift system, determining the gas lift deepening design for future performance, sensitivity analysis of gas lift design parameters at well X, and determining the time required for optimum design gas lift system. The methodology used includes literature study, data collection, well modeling, and sensitivity analysis. Well X, which has been producing since 2020, uses a gas lift method with three gas lift mandrels installed at a certain depth. This study evaluates two gas lift deepening methods, namely using a siphon string and retrofit gas lift (RGL). The results show that both methods are not better than the existing gas lift system in the current condition. Sensitivity analysis on injection depth in both methods and coiled tubing size in RGL was conducted to obtain optimum results. Since in the present condition both methods of deepening the injection point in the gas lift are not better than the existing gas lift system, a sensitivity analysis of the gas lift design is carried out to improve the performance of well X in the future. Determining under what conditions the X well requires optimum design of the gas lift system. reservoir conditions with a pressure of 550 psi and a GOR of 172 SCF/STB, it was found that the well would not flow without deepening the gas lift. Deepening the gas lift under these conditions made the well flowable, using a siphon string at the injection points of 5176 ft MD and 6800 ft MD, obtained fluid rates of 385 BFPD and 696 BFPD, respectively. Using Retrofit gas lift (RGL), a rate of 452 BFPD was obtained for a deepening of 500 ft TVD and 729 BFPD for a deepening of 1000 ft TVD. The results of sensitivity analysis on RGL showed that the deeper the injection point, the greater the production rate obtained, but higher injection pressure is required. This study concludes that optimum gas lift deepening design can significantly improve the performance of well X under certain reservoir conditions, and provides guidance for further development in gas lift technology
MAXIMIZING PRODUCTIVITY IN TALANG AKAR FORMATION THROUGH HYDRAULIC FRACTURING WITH LINEAR GEL AND CROSSLINKED GEL FLUIDS
Hydraulic fracturing stimulation is commonly used in oil and gas extraction to enhance the flow of hydrocarbons from a well. This method is valuable implemented in a low to even high permeability reservoir. The stimulation is carried out in an oil field in Indonesia, Abis Field, with a candidate well has been selected to be Well Susanto. The objectives of this study are to estimate the quality of reservoir before stimulation, design optimum fracture geometry, and determine the increase in well productivity post-fracturing job. First, well log interpretation is required for geomechanic data such as closure stress. Then, the permeability of the pay zone in the Talang Akar Formation that has been obtained through well test data is reconfirmed using a Step Rate Test (SRT). This step is essential for the efficient fracture design that is made. After that, several proppants and fluids type are selected to make 4 scenarios that are simulated using a 3D modelling software. Through the software, the optimum fracture geometry such as fracture half-length, height, and width are generated. The best scenario is attained based on the largest value from the comparison of Folds of Increase (FOI).
MAXIMIZING PRODUCTIVITY IN TALANG AKAR FORMATION THROUGH HYDRAULIC FRACTURING WITH LINEAR GEL AND CROSSLINKED GEL FLUIDS
Hydraulic fracturing stimulation is commonly used in oil and gas extraction to enhance the flow of hydrocarbons from a well. This method is valuable implemented in a low to even high permeability reservoir. The stimulation is carried out in an oil field in Indonesia, Abis Field, with a candidate well has been selected to be Well Susanto. The objectives of this study are to estimate the quality of reservoir before stimulation, design optimum fracture geometry, and determine the increase in well productivity post-fracturing job. First, well log interpretation is required for geomechanic data such as closure stress. Then, the permeability of the pay zone in the Talang Akar Formation that has been obtained through well test data is reconfirmed using a Step Rate Test (SRT). This step is essential for the efficient fracture design that is made. After that, several proppants and fluids type are selected to make 4 scenarios that are simulated using a 3D modelling software. Through the software, the optimum fracture geometry such as fracture half-length, height, and width are generated. The best scenario is attained based on the largest value from the comparison of Folds of Increase (FOI).
DATUM HIDROGRAFI LEPAS PANTAI: PEMBUATAN MODEL SEPARASI HIDROGRAFI DI SEKITAR DELTA MAHAKAM, KALIMANTAN TIMUR
The Mahakam Delta in East Kalimantan is crucial for oil and gas exploration in Indonesia. However, the reliance on a single chart datum (CD) at Handil for sea level measurements has led to operational disruptions due to the uncertain sea level values. To address these issues, developing a robust system to better define sea level values is essential. One effective solution is to build a hydrographic separation model. The offshore hydrographic separation model is essential for accurately describing and transforming the positions of tidal datums relative to an ellipsoid. This model is particularly useful for converting the position of Mean Sea Level (MSL) to Lowest Astronomical Tide (LAT). In this project, the goal is to create such a model for the area extending from the Mahakam Delta to Peciko-Bekapai, leveraging Global Mean Sea Surface (MSS) models and tidal models. The hydrographic separation model was developed to address the challenges of sea level uncertainty in the Mahakam Delta, crucial for oil and gas exploration and maritime operations. The project utilized the CNES CLS2022 MSS model for Mean Sea Surface (MSS) and the TPXO9v5a tidal model for Lowest Astronomical Tide (LAT) due to their minimal absolute mean error values. The model was implemented as a WebGIS application to enhance accessibility and usability. The implementation of hydrographic separation model as a website application has facilitated real-time, accurate sea level predictions, greatly enhancing shipping operations and safety. The product analysis yielded results indicating an 111.94% increase in the frequency of ship shipping operation windows around the Mahakam area.
KARAKTERISASI RESERVOIR LAPANGAN KELUANG, FORMASI MUARAENIM, CEKUNGAN SUMATRA SELATAN
Lapangan Keluang merupakan salah satu lapangan penghasil minyak dan gas bumi yang berada di Cekungan Sumatra Selatan. Studi penelitian difokuskan pada Formasi Muaraenim yang berumur Miosen yang memiliki potensi reservoir yang baik. Penelitian ini bertujuan untuk melakukan analisis fasies, asosiasi fasies, dan interpretasi lingkungan pengendapan untuk memahami jenis geometri reservoir pada daerah penelitian, melakukan identifikasi dan analisis korelasi stratigrafi sikuen untuk memahami hubungan fasies secara genetik dalam kerangka kronostratigrafi, menentukan nilai properti petrofisika meliputi volume serpih, porositas efektif, dan saturasi air serta menentukan batas pancung reservoir pada daerah penelitian. Data yang digunakan dalam penelitian ini, yaitu deskripsi batuan inti samping, log tali kawat dan deskripsi keratan bor dari sepuluh sumur, laporan biostratigrafi, dan laporan akhir sumur. Hasil analisis litofasies dengan data laporan batuan inti samping menunjukkan pada interval penelitian memiliki litofasies berupa Ssvf, Ssf, Sscb, Ssa, Fc, Fs dan empat jenis elektrofasies berupa irregular, symmetrical, bell shape, cylindrical/blocky dan asosiasi fasies tersusun oleh tidal flat, tidal bar dan marine shelf deposits/shelf muds. Laporan biostratigrafi menunjukkan bahwa daerah penelitian berada dalam zonaLitoral hingga Sublitoral sehingga dapat diinterpretasikan lingkungan pengendapan yaitu estuari dominasi pasang surut hingga marine shelf deposits. Analisis petrofisika menghasilkan nilai batas pancung untuk volume serpih 0,5; porositas efektif 0,0753; dan saturasi air 0,827. Penerapan batas pancung menunjukkan reservoir potensial dengan nilai properti rata-rata volume serpih 0,167, porositas efektif 0,241, dan saturasi air adalah 0,702.
OFFSHORE HYDROGRAPHIC DATUM: ESTABLISHMENT OF HYDROGRAPHIC SEPARATION MODEL AROUND MAHAKAM DELTA, IN EAST KALIMANTAN
The Mahakam Delta in East Kalimantan is crucial for oil and gas exploration in Indonesia. However, the reliance on a single chart datum (CD) at Handil for sea level measurements has led to operational disruptions due to the uncertain sea level values. To address these issues, developing a robust system to better define sea level values is essential. One effective solution is to build a hydrographic separation model. The offshore hydrographic separation model is essential for accurately describing and transforming the positions of tidal datums relative to an ellipsoid. This model is particularly useful for converting the position of Mean Sea Level (MSL) to Lowest Astronomical Tide (LAT). In this project, the goal is to create such a model for the area extending from the Mahakam Delta to Peciko-Bekapai, leveraging Global Mean Sea Surface (MSS) models and tidal models. The hydrographic separation model was developed to address the challenges of sea level uncertainty in the Mahakam Delta, crucial for oil and gas exploration and maritime operations. The project utilized the CNES CLS2022 MSS model for Mean Sea Surface (MSS) and the TPXO9v5a tidal model for Lowest Astronomical Tide (LAT) due to their minimal absolute mean error values. The model was implemented as a WebGIS application to enhance accessibility and usability. The implementation of hydrographic separation model as a website application has facilitated real-time, accurate sea level predictions, greatly enhancing shipping operations and safety. The product analysis yielded results indicating an 111.94% increase in the frequency of ship shipping operation windows around the Mahakam area.