Search Results (144)

Deep coalbed methane (CBM) reservoirs exhibit ultralow permeability, high in situ stress, and pronounced stress sensitivity. The resulting feedback between reservoir deliverability, wellbore liquid transport, and surface choking cannot be represented reliably by isolated reservoir or wellbore calculations. This study develops an integrated reservoir–wellbore–choke coupling model for deep CBM wells. The reservoir submodel adopts a dual-porosity, single-permeability formulation for matrix-to-natural-fracture mass transfer, incorporates hydraulic fractures through non-neighboring connections, and accounts for Langmuir adsorption/desorption and effective-stress-dependent permeability. Gas–liquid flow in the tubing or annulus is calculated with the Beggs–Brill correlation, whereas critical and subcritical flow through the wellhead choke is evaluated with the Sachdeva mechanistic model. Bottom-hole flowing pressure (BHP) serves as the coupling variable in a partitioned sequential-iterative scheme. For each time step, the reservoir model predicts gas and water rates at a prescribed BHP; these rates are passed to the choke and wellbore models, whose returned BHP updates the reservoir boundary until convergence. Newton iterations solve the reservoir equations, and the critical liquid-carrying rate identifies the end of stable natural flow and the onset of liquid-loading risk. Application to Well H1 yielded agreement scores of 80.99%, 79.93%, 94.17%, and 90.48% for the gas rate, water rate, BHP, and wellhead tubing pressure, respectively, with an overall mean of 86.39%. Gas content governed the mid- to late-time deliverability, while tubing and choke sizes controlled the trade-off between friction loss, drawdown, and liquid unloading. A 2–3/8 in tubing string combined with a 12 mm choke provided the most balanced performance. The model supports life-cycle production forecasting and integrated completion and production optimization for deep CBM wells. Full article

Fully implicit simulation of multiphase flow in porous media requires repeated solution of large, sparse, nonsymmetric Jacobian systems, where linear solvers and preconditioners often dominate the computational cost. In field-scale models with strong well controls and well–reservoir coupling, bottom-hole pressure (BHP) constraints may introduce slowly converging pressure-related error modes that are not fully represented by pressure-only constrained pressure residual (CPR) preconditioning. This paper develops a Schur-consistent graphics processing unit (GPU) implementation of constrained pressure residual with wells and algebraic multigrid (CPRW-AMG) for the Open Porous Media (OPM) Flow simulator. The method augments the pressure coarse space with one auxiliary BHP unknown per active well while preserving a reservoir-only fine-level Krylov system. The pressure–BHP coarse operator is constructed from the same assembled effective reservoir Jacobian used by the Krylov matrix–vector product and the GPU diagonal incomplete lower–upper (DILU) smoother, avoiding inconsistent treatment of well contributions between fine and coarse levels. A GPU-resident sparse update strategy refreshes well-related coarse entries, and the NVIDIA AMGX library is used for the scalar coarse solve. Benchmarks on SPE9, SPE10, Sleipner, and Norne cover small well-coupled, highly heterogeneous carbon dioxide storage and field-realistic reservoir models. Compared with CPU CPRW-AMG, the GPU implementation reduces total runtime by factors of 1.69–8.78 and achieves linear-solve speedups of up to 17.96×. Compared with GPU CPR-AMG, the performance benefit is case-dependent, indicating that CPRW-AMG is most effective when the reduction in well-induced slow error modes compensates for the additional coarse-level cost. Full article

Structural fractures and karst cavities are widely developed in deep and ultra-deep carbonate reservoirs, providing preferential pathways for rapid fluid migration while increasing the risk of severe drilling fluid loss. To investigate the lost-circulation mechanism in fractured-vuggy formations, a hydro-mechanically coupled gas–liquid two-phase seepage model was established by considering the multiple-media characteristics of matrix, fractures and cavities, as well as rock deformation and fluid compressibility. We hypothesize that gas–liquid property differences and hydro-mechanical changes in conductivity jointly control drilling fluid loss, with the gas–liquid property contrast exerting the stronger effect under the simulated conditions. In the model, flow in the matrix and fractures is described by Darcy’s law, while high-velocity flow in cavities is characterized using the Forchheimer non-Darcy equation. The coupling between the seepage field and stress field is achieved by incorporating the effective stress relationship, using the Kozeny–Carman porosity–permeability evolution model and the Goodman fracture deformation model. The coupled equations were implemented in COMSOL. Model validation confirms the reliability of the proposed model in predicting drilling fluid loss. The fracture–vug system significantly enhances fluid exchange between the wellbore and formation. Pressure propagates rapidly along fractures and vugs at the early stage and subsequently diffuses into the surrounding matrix, while the loss rate generally decreases with time. After 120 min, hydro-mechanical coupling increased the loss rate from 1.15 × 10⁻³ to 1.23 × 10⁻³ m³/s and the cumulative loss volume from 11.41 to 12.06 m³. Compared with the single-phase model, the gas–liquid two-phase model predicted a 4.82-fold higher loss rate. Fracture aperture, vug size, bottomhole pressure differential, and rock mechanical properties are the principal factors controlling loss intensity and pressure propagation. Through effective stress variations, hydro-mechanical coupling modifies porosity, permeability, and fracture aperture, thereby affecting formation conductivity and dynamic loss behavior. These results provide theoretical guidance for lost-circulation mechanism analysis, risk assessment, and plugging optimization in deep fractured-vuggy carbonate formations. Full article

With the continuous advancement of deep and ultra-deep well drilling technologies, formations with complex pressure windows are becoming increasingly common. During casing running operations, it is necessary to ensure both leak prevention in loss-prone formations and pressure stabilization in high-pressure formations, demanding increasingly higher accuracy in wellbore pressure calculation. This study establishes a wellbore pressure calculation model for managed pressure casing (MPC) running in deep wells, specifically addressing the scenario where a multi-density gradient drilling fluid column exists in the annulus after tripping out. The model’s novelty lies in integrating transient surge pressure calculation with a dynamic fluid column structure model that tracks the displacement of multi-density drilling fluid layers during casing running. The governing equations based on one-dimensional unsteady flow theory are solved using the method of characteristics with adaptive time stepping and a grid independence study confirming the discretization scheme. Quantitative analysis reveals that casing running speed is the dominant factor affecting surge pressure; when the speed increases from 0.5 m/s to 1.5 m/s, the surge pressure increases from approximately 1.2 MPa to 3.5 MPa at a 2000 m depth. Drilling fluid properties also significantly influence surge pressure: increasing the density from 2.0 g/cm³ to 2.22 g/cm³ results in a surge pressure increase of approximately 0.6 MPa; increasing the yield value from 2.85 Pa to 15 Pa leads to an increase of about 1.1 MPa; the surge pressure shows a clear increasing trend with both the consistency coefficient and flow behavior index. Casing running depth affects the buffering effect of the bottomhole flow channel; when the casing is run to 7000 m, the surge pressure is approximately 0.5 MPa higher than at 2000 m. Taking a typical deep well (8578 m) with a negative pressure window of −0.008 g/cm³ as an example, three casing running speed plans were designed and evaluated. Plan 1 was selected with running speeds ranging from 0.16 m/s in the upper section to 0.115 m/s in the lower section, maintaining the equivalent circulating density (ECD) within the safe density window throughout the entire operation. Field application of this plan proceeded smoothly without any occurrences of lost circulation or overflow. This provides a practical basis for MPC running technology in deep wells with narrow or negative pressure windows. Full article

Coal-bearing tight gas and deep coalbed methane (CBM) widely co-occur in China, and integrated commingled production outperforms separate development. Conventional separated simulation fails to capture coupled reservoir–wellbore gas–water flow. This study develops an integrated geomechanical coupled numerical model with multi-scale fractures and multi-phase wellbore flow: tight gas reservoirs use a stress-sensitive single-porosity model, deep CBM adopts a dual-porosity model for matrix desorption, and EDFM characterizes non-Darcy flow in hydraulic fractures. The Gray gas column and liquid column methods calculate layered bottomhole pressure according to reservoir vertical distribution, and matrix bordering solves the whole coupled system. Validated by field data of Well C-1 in Shanxi, the model yields average relative errors of 8.76% for daily gas output and 2.92% for daily water output. Sensitivity analysis on Well C-2 indicates vertical reservoir stacking controls interlayer pressure difference, and commingled gas curves show dual peaks with shifting dominant gas sources over production stages. A 3.9% rise in deep coalbed methane gas content significantly boosts mid-term peak production and cumulative gas output, making reservoir gas content the dominant geological factor governing commingled production performance. A 120.0% increase in tight gas saturation only delivers a slight uplift in cumulative production under low-porosity conditions. Elevated reservoir stress sensitivity triggers a cumulative gas production reduction of over 50%. Cumulative gas output varies proportionally with hydraulic fracture length, while fracture network width brings mismatched production improvement due to pressure drawdown funnel effects. Therefore, hydraulic fracturing operations should prioritize extending artificial fractures to expand the drainage area of commingled wells. Schemes with constant bottomhole flowing pressure and constant gas rate exert marginal influences on ultimate cumulative production and can be flexibly switched on site. To stabilize daily gas deliverability throughout the early, middle and late production stages, a bottomhole pressure drawdown rate of 0.05 MPa/d or a fixed daily gas rate of 4000 m³/d is recommended. This work provides theoretical support for optimizing commingled development of superimposed tight gas and deep CBM reservoirs. Full article

Upper-loss and lower-kick (UL–LK) events may occur in ultra-deep fractured carbonate formations when gas enters from a lower high-pressure zone while drilling fluid is lost to an upper low-pressure fracture. Because both flows can continue after shut-in, the wellbore remains incompletely closed. This study develops a transient wellbore-formation pressure model based on phase mass conservation and global volume balance, and introduces an effective gas–liquid partition coefficient to represent phase separation at the fracture inlet. The model shows that circulation loss limits bottomhole-pressure recovery, allowing gas influx to persist after shut-in. Relative to kick-only conditions, UL–LK conditions have a lower initial shut-in casing pressure (SICP) but a steeper subsequent buildup. A smaller partition coefficient, corresponding to preferential liquid loss, leaves more free gas in the wellbore and further increases the SICP buildup rate. A surface-pressure-based screening method was developed from contrasting SICP and shut-in drillpipe pressure (SIDPP) responses. When applied to five field cases, the method correctly identified three UL–LK cases and two kick-only cases. Its outcomes for five field cases agreed with the field interpretations. This framework supports post-shut-in pressure prediction and rapid screening without dedicated downhole measurements. Full article

Severe fracturing-fluid retention and low post-fracturing flowback efficiency are common in the Lianggaoshan shale reservoirs of the Sichuan Basin. Liquid loading may also occur during late production. To address these problems, this study investigates a synergistic flowback technology that combines natural fracturing-fluid flowback with CO₂ gas lift. First, based on the complex fracture network characteristics of the Lianggaoshan shale reservoir, the interaction mechanisms between hydraulic fractures and natural fractures were investigated. An energy model for fracturing-fluid flowback under natural flowback conditions was established, revealing that reservoir gas expansion energy, hydromechanical energy, and rock elastic energy are the primary driving forces for fracturing-fluid flowback. Furthermore, considering fracture closure behavior, fluid leakoff, and wellbore flow dynamics, a calculation model for the natural flowback of fracturing fluid was developed, and a staged pressure-controlled flowback strategy was proposed. Subsequently, to address the decline in liquid unloading capacity caused by formation-energy depletion during the late stage of natural flowback, a gas-lift-assisted flowback multiphase flow model for the wellbore was established. The effects of the gas injection pressure, gas injection rate, and wellhead pressure on liquid unloading efficiency were systematically investigated. The results indicate that the liquid unloading rate increases with an increasing gas injection pressure and gas injection rate; however, a pronounced diminishing marginal effect is observed. For the Well H1 reference case, the central recommended gas injection pressure was 12 MPa, the gas injection rate was 8 × 10⁴–10 × 10⁴ m³/d, and the wellhead backpressure was maintained below 0.5 MPa. Furthermore, the CO₂-assisted flowback mechanisms were evaluated by distinguishing between the effects explicitly represented in the model and the potential reservoir-scale physicochemical effects. The reduction in wellbore mixture density and bottomhole flowing pressure was simulated directly, whereas CO₂–oil mass transfer, viscosity reduction, mineral dissolution, and changes in water-blocking behavior were interpreted with reference to published experimental studies. Based on these mechanisms, a three-stage synergistic optimized flowback scheme, consisting of “CO₂ soaking–natural flowback–CO₂ gas lift,” was established. A sequence of stagewise quasi-steady PIPESIM calculations was subsequently performed over the 30-day operating schedule. Under the adopted simulation conditions, the recommended soaking period is 5–7 days. The operation should be switched to gas lift when the wellhead pressure falls below 1.5 MPa or when daily liquid production declines continuously by more than 20%. Under the synergistic scheme, the 30-day cumulative flowback volume was predicted to reach 3492 m³. This value was substantially higher than those obtained by conventional natural flowback and standalone gas-lift processes. Moreover, the flowback curve exhibits a distinct “secondary surge” characteristic. These findings provide a theoretical basis and technical support for efficient fracturing-fluid flowback and stable long-term production in the Lianggaoshan Formation. They may also be applicable to other shale oil reservoirs with low porosity and ultra-low permeability. Full article

Carbon dioxide replacement represents a promising hydrate development strategy that effectively balances production efficiency and environmental considerations. However, its production efficiency is lower than that of the depressurization strategy. This limitation can be effectively alleviated by coupling carbon dioxide replacement with inhibitor injection. The design and optimization of the temperature–pressure operating window constrain its effective implementation. In the present work, the phase equilibrium conditions of carbon dioxide hydrate and methane hydrate were experimentally investigated. It was found that the experimental values obtained in this study are in excellent agreement with those calculated by the CSMHyd program. The average absolute relative deviations (AARD) for the experimental versus calculated results are 5.77% for methane hydrate and 2.66% for carbon dioxide hydrate. Then, the methodology for determining the recommended temperature–pressure combinations used in the carbon dioxide replacement strategy was proposed, and the size of region in which these combinations occur was quantified. The investigation results found that there are significant differences in the size of the recommended region for different sea areas, and inhibitor injection reduces the size of this recommended region. Injection of 3.0 wt% NaCl solution reduces the size of recommended region from 10.968 K·MPa to 8.366 K·MPa for pure methane hydrate, and a similar trend is also observed for natural gas hydrates. Based on the experimental results, the carbon sequestration potential of natural gas hydrate development using the carbon dioxide replacement strategy on core size was analyzed. The final simulation results show that 9.05 mol of carbon dioxide hydrate was obtained in the reaction vessel, which achieves effective CO₂ sequestration. The investigation in this work provides theoretical support for dual goals of carbon sequestration and efficient gas production from gas hydrates. Full article

To address the complex pressure-response mechanisms and difficulties in quantitatively characterizing dynamic reservoir properties during CO₂ geological storage in tight oil reservoirs, this work develops a dual-region composite seepage model coupling reservoir heterogeneity and CO₂-induced fluid property variation. The reservoir is divided into a near-well CO₂-stimulated zone and a far-field unstimulated zone. Combining the Laplace transform and the Stehfest368 numerical inversion method, we derive the analytical solutions of the bottom-hole pressure (BHP) and its derivative, and we establish a complete transient BHP monitoring and parameter inversion framework. The pressure-derivative curves are divided into five typical flow stages: wellbore storage, skin transition, inner-region radial flow, inter-region transition and outer-region radial flow. The key parameters, including wellbore storage coefficient, skin factor, mobility ratio, storativity ratio and CO₂ swept radius, can be accurately inverted via the BHP data analysis, which quantitatively characterizes flow capacity evolution, stimulated region scale and fluid flow patterns after CO₂ injection. The field application on two production wells in H138 block verifies the reliability of the proposed method. Further numerical simulation validation, measurement error sensitivity analysis and cross-verification of reservoir parameters are supplemented to prove the robustness and the applicability of the model. This study provides solid theoretical and technical support for on-site pressure monitoring, storage performance evaluation and operation optimization of CO₂ geological storage in tight reservoirs, and it also offers a reference for long-term storage security and storage capacity assessment. Full article

Pump start-up and shutdown, flow-rate adjustment, and tripping operations during drilling can induce bottomhole pressure fluctuations. These fluctuations may alter fracture aperture and change the development of lost-circulation pathways. To investigate the dynamic evolution of fracture aperture under fluctuating pressure, a thermo-hydro-mechanical (THM) coupled numerical model was established using ABAQUS. Bottomhole pressure fluctuations were induced by applying periodic perturbations to the inlet flow rate. The effects of fluctuation amplitude, fluctuation duration, and drilling-fluid temperature were then analyzed. The results indicate that fracture aperture exhibits a transient response before reaching a stable state. The fluctuation amplitude has a significant effect on the maximum transient fracture aperture. When the fluctuation amplitude increases to 30%, the maximum fracture aperture increases by 44%. In contrast, the fracture that has already formed may undergo reclosure during the low-pressure stage. The fluctuation duration mainly affects the persistence of the fracture opening and reclosure process, but has a relatively weak effect on the maximum fracture aperture. A decrease in drilling-fluid temperature promotes fracture opening and tip propagation. When the formation temperature is 100 °C, low-temperature drilling fluid increases the maximum fracture aperture by 3.06% and the fracture length by 13.89% compared with the isothermal reference case. These findings indicate that fracture aperture under fluctuating pressure cannot be characterized only by its stabilized value. The maximum transient fracture aperture, minimum fracture aperture, and temperature-induced changes in fracture morphology should also be considered. This study provides a numerical insight into the transient response of fracture aperture to bottomhole pressure fluctuations and drilling-fluid temperature during drilling in stress-sensitive fractured formations. Full article

Reliable wellbore cleaning remains difficult in deviated, horizontal, extended-reach, deep, and ultra-deep wells because the downhole distribution and mechanical state of cuttings beds cannot usually be observed directly. This review examines cuttings-bed dynamics, multiscale modeling, compressible multiphase constraints, and field-validation pathways for drill cuttings transport and wellbore cleaning. Bibliometric mapping of 625 Web of Science records was combined with critical assessment of 204 technically screened studies and 56 engineering-oriented OnePetro records. Bed height, cuttings concentration, pressure response, equivalent circulating density/bottomhole-pressure (ECD/BHP) margin, solids residence time, and packoff tendency are identified as bridge variables linking particle-scale behavior with operational risk. Recent studies strengthen wet-bed erosion and friction characterization, non-spherical and geometry-resolved CFD–DEM, hybrid prediction, compressible pressure–solids coupling, and field observability. Study-level comparison shows that ML approaches differ markedly in data provenance, validation design, physical integration, uncertainty reporting, and transfer evidence. An uncertainty-aware, field-calibratable workflow is proposed that links synchronized measurements, complementary models, latent-state estimates with prediction intervals, section-specific probabilistic thresholds, operational response, and post-action verification. Quantitative benchmark criteria are defined for particle realism, wet-bed mechanics, tool-induced flow, compressible transport, transient field models, and advisory outputs. Full article

Refracturing is an important stimulation technique for improving the productivity of mature shale gas wells. However, for low-productivity horizontal wells, the controlling effects of production history and pre-refracturing energy replenishment on fracture re-initiation and repropagation remain insufficiently quantified. This study focuses on mature wells in the H Block of the Fuling shale gas field. The Jiaoshiba area in the Fuling shale gas field, located on the eastern margin of the Sichuan Basin, is characterized by organic-rich marine shales of the Wufeng–Longmaxi Formation, where gas enrichment is jointly controlled by the Jiaoshiba anticline, fault distribution, and favorable preservation conditions. A three-dimensional geological model was constructed using seismic interpretation, well logging, core analysis, ant-tracking fracture attributes, and field fracturing data. A one-way coupled finite-element workflow was then applied to simulate the evolution of pore pressure and in situ stress during primary production, water-injection energy replenishment, and refracturing. The model was calibrated against historical bottomhole flowing pressure data, with a pressure-response matching accuracy greater than 85%. The results show that a lower initial production (4 × 10⁴ m³/d) allocation can mitigate reservoir pressure depletion and maintain a more favorable stress environment for fracture branching during refracturing. Compared with refracturing after 10 or 20 years of production, refracturing after 5 years produced a stronger post-treatment response in the simulated cases. For water-injection energy replenishment, an injection rate of 700 m³/d restored reservoir pressure and regulated the local stress field more effectively than 500 m³/d, whereas increasing the rate to 1000 m³/d provided only limited additional pressure recovery. Overall, under the simulated reservoir conditions, a technically favorable parameter combination for the target well is an initial production allocation of 4 × 10⁴ m³/d, refracturing after approximately 5 years of production, and one year of pre-refracturing water-injection energy replenishment at about 700 m³/d. These findings provide a reference for refracturing timing and pre-treatment energy-replenishment design in depleted shale gas reservoirs. Full article

The Chang 8 tight oil reservoir in the Xifeng area of the Ordos Basin is characterized by poor reservoir properties, making conventional water flooding ineffective for efficient reservoir development. CO₂ flooding is therefore considered an important approach for enhancing oil recovery in tight reservoirs. However, suitable development strategies for direct CO₂ injection in undeveloped reservoir areas remain insufficiently understood. In this study, compositional numerical simulation combined with a single-factor sensitivity analysis was employed to investigate the effects of key parameters, including well pattern configuration, fracturing parameters, injection–production strategy, and gas injection modes. The results indicate that an inverted nine-spot well pattern with vertical well injection and vertical well production, a well spacing of 500 m, and a row spacing of 200 m can achieve relatively favorable areal and vertical sweep performance. A fracture half-length of 80 m, fracture widths of 0.003–0.005 m, and fracturing treatment before initial production help balance early-stage productivity and gas channeling control. Maintaining an injection rate of 0.03–0.04 PV/a, an oil production rate of 2–3 m³/d, and a bottomhole flowing pressure of 13–14 MPa is beneficial for maintaining reservoir energy and stabilizing displacement-front propagation. Based on neighboring field development experience, switching from continuous CO₂ injection to water–alternating–gas (WAG) injection during the mid-development stage can improve mobility control and enlarge the CO₂ swept volume. Under the current geological model and simulation conditions, the recommended development strategy predicts a recovery factor of 35.43% over a 30-year production period. The results provide reasonable parameter ranges and an engineering reference for direct CO₂ flooding development in the Chang 8 tight oil reservoir and similar reservoirs. Full article

Fractured–vuggy carbonate reservoirs are characterized by highly discrete storage structures, and the number, spatial distribution, and volume of cavities strongly affect well-test responses and reservoir development decisions. This study develops a PEBI-grid finite-volume implementation of a wave–seepage-coupled model for pressure-transient interpretation in reservoirs containing irregular cavities. The objective is not to introduce a new general-purpose finite-volume method but to embed irregular cavities as special control volumes into a locally orthogonal PEBI grid so that the cavity volume, geometry, and well–cavity distance can be represented explicitly in bottom-hole pressure calculations. The model is formulated as a thickness-averaged two-dimensional system in which the fracture–matrix region is treated as an equivalent seepage continuum, and each cavity is assigned a spatially uniform pressure governed by a wave–seepage exchange relation. For the limiting case of zero cavity volume, the numerical bottom-hole pressure agrees closely with the analytical solution and the material-balance estimate. A further cylindrical-cavity benchmark against an analytical wave–seepage solution gives a pressure-drawdown relative L2 error of 4.38%, where the relative L2 error denotes the Euclidean norm of the pressure error vector normalized by that of the reference solution, providing additional validation of the cavity-coupled formulation. Sensitivity analysis shows that increasing the cavity volume delays the characteristic extrema of the pressure derivative and strengthens the contrast between the minimum and maximum, whereas increasing the well–cavity distance mainly shifts the onset of the cavity-dominated response and weakens its amplitude. A field pressure-buildup case from the Fuyuan oilfield is interpreted using the proposed workflow. The matched model indicates a pentagonal cavity with a volume of 169,770 m³, a well–cavity distance of 158.4 m, a permeability of 5.535 md, and an initial reservoir pressure of 86.66 MPa. The results demonstrate that the proposed PEBI-FVM wave–seepage-coupled model can support practical well-test interpretation of irregular cavities, while its reliability depends on the validity of the equivalent-continuum and uniform-cavity-pressure assumptions. Full article

Well control during drilling requires continuous assessment of bottom-hole pressure (BHP) relative to the pressure window bounded by formation and fracture pressures. This study presents a reduced-order, physics-guided digital-twin framework for well-control decision support, kick and loss risk assessment, and hybrid BHP prediction. The framework is intended as a computational decision-support prototype rather than a fully deployed, real-time, field-validated digital twin. It combines pressure-window calculations, dimensionless risk indices, bounded machine-learning correction, scenario-based event simulation, an interactive engineering dashboard, and 3D safety-envelope visualization. The machine-learning layer was trained on a predominantly augmented drilling dataset containing 909 cases, including nine field-related baseline records and 900 synthetically generated cases, and was used as a constrained correction mechanism rather than a replacement for the physics-based model. On the held-out test set, the BHP regression model achieved R² = 0.987, MAE = 108.6 psi, and RMSE = 215.7 psi, while the well-control status classifier achieved an accuracy of 98.35%. Scenario simulations reproduced representative kick-prone and loss-prone conditions and tracked the evolution of BHP, the Pressure Safety Index, the Kick Risk Index, and the Loss Risk Index. The results show that the proposed workflow can identify underbalanced states, quantify pressure margins, evaluate mud-weight sensitivity, and support visual interpretation of well-control risk. Further field validation, real-time data integration, uncertainty quantification, and robustness testing are required before operational deployment. Full article