In shale gas formations, imbibition is significant since the tight pore structure causes a strong capillary suction pressure. After hydraulic fracturing, imbibition during the period of shut-in affects the water recovery of flowback. Although there have been many studies investigating imbibition in shale formations, few papers have studied the relationship between gas production and shut-in time under the influence of imbibition. This paper developed a numerical model to investigate the effect of imbibition on gas production to optimize the shut-in time after hydraulic fracturing. This numerical model is a 2-D two-phase (gas and water) imbibition model for simulating an imbibed fluid flow and its effect on permeability, flowback, and water recovery. The experimental and field data from the Woodford shale formation were matched by the model to properly configure and calibrate the model parameters. The experimental data consisted of the relationship between the imbibed fluid volume and permeability change, the relative permeability, and the capillary pressure for the Woodford shale samples. The Woodford field data included the gas production and flowback volume. The modeling results indicate that imbibition can be a beneficial factor for gas production, since it can increase rock permeability. However, the gas production would be reduced when excessive fluid is imbibed by the shale matrix. Therefore, the shut-in time after hydraulic fracturing, when the imbibition happens in shale, could be optimized to maximize the gas production.

In today’s oil industry, companies frequently flare the produced natural gas from oil wells. The flaring activities are extensive in some regions including North Dakota. Besides company-reported data, which are compiled by the North Dakota Industrial Commission, flaring statistics such as count and volume can be estimated via Visible Infrared Imaging Radiometer Suite nighttime observations. Following data gathering and preprocessing, Bayesian machine learning implemented with Markov chain Monte Carlo methods is performed to tackle two tasks: flaring time series analysis and distribution approximation. They help further understanding of the flaring profiles and reporting qualities, which are important for decision/policy making. First, although fraught with measurement and estimation errors, the time series provide insights into flaring approaches and characteristics. Gaussian processes are successful in inferring the latent flaring trends. Second, distribution approximation is achieved by unsupervised learning. The negative binomial and Gaussian mixture models are utilized to describe the distributions of field flare count and volume, respectively. Finally, a nearest-neighbor-based approach for company level flared volume allocation is developed. Potential discrepancies are spotted between the company reported and the remotely sensed flaring profiles.

We present TADI (Tool-Augmented Drilling Intelligence), an agentic AI system that transforms drilling operational data into evidence-based analytical intelligence. Applied to the Equinor Volve Field dataset, TADI integrates 1,759 daily drilling reports, selected WITSML real-time objects, 15,634 production records, formation tops, and perforations into a dual-store architecture: DuckDB for structured queries over 12 tables with 65,447 rows, and ChromaDB for semantic search over 36,709 embedded documents. Twelve domain-specialized tools, orchestrated by a large language model via iterative function calling, support multi-step evidence gathering that cross-references structured drilling measurements with daily report narratives. The system parses all 1,759 DDR XML files with zero errors, handles three incompatible well naming conventions, and is backed by 95 automated tests plus a 130-question stress-question taxonomy spanning six operational categories. We formalize the agent's behavior as a sequential tool-selection problem and propose the Evidence Grounding Score (EGS) as a simple grounding-compliance proxy based on measurements, attributed DDR quotations, and required answer sections. The complete 6,084-line, framework-free implementation is reproducible given the public Volve download and an API key, and the case studies and qualitative ablation analysis suggest that domain-specialized tool design, rather than model scale alone, is the primary driver of analytical quality in technical operations.

We present PetroAgents, a multi-agent, multi-modal large-language-model framework for petroleum-engineering reasoning on the Equinor Volve open dataset. The target architecture mirrors an integrated asset team: discipline-specific evidence surfaces, cross-examination, a Council Synthesiser, distributional well-action proposals, and risk review. Read as an agent-design pattern map, the architecture is organised around the seven cognitive functions of a language agent, with the per-discipline evidence lock as its governance layer; four functions are implemented and evaluated in this submission and three are specified as design. The current quantitative evidence is narrower by design. We specify Volve Bench, a six-task Volve benchmark suite spanning DRILL-NPT root-cause attribution, formation top picking, six-month production forecasting, stuck-pipe early warning, multi-modal Discovery-Report QA, and per-wellbore lifecycle forensic analysis over 26 wellbores, 1,759 daily drilling reports, 56 million WITSML rows, 602 LAS files, 5.7 million horizon points, and a decade of production. This submission reports two landed evidence slices: a three-seed DRILL-NPT study on stratified samples drawn from a 1,750-example pool, and a 12-question DISCOVERY-QA smoke test on three rendered pages of the 194-page Hugin Discovery Report. Every reported LLM call goes through a local OpenAI-compatible gateway using locally-hosted open weights (GPT-OSS-120B, Qwen3.6-35B, Gemma-4-31B, MiniMax-M2.7, Qwen3-VL-235B-FP8); no paid frontier API is invoked. On DRILL-NPT, the four-family vote attains macro-F1 0.464 ± 0.012 on the broad all-wellbore sample and 0.442 ± 0.019 on the WITSML-applicable subset. The Drilling+HSE+Council path lifts WITSML-applicable macro-F1 by +0.048 over the single-LLM baseline, but the paired test is not significant at three seeds (p = 0.22), so we report it as directional evidence rather than a settled win. A same-subset evidence-redaction ablation shows that exposing state_detail and proprietary_code lifts B1 from 0.355 to 0.431 macro-F1, quantifying how much of DRILL-NPT is label-code leakage rather than prose reasoning. On DISCOVERY-QA, Qwen3-VL reading rendered page images reaches a 0.958 keyword-hit score versus 0.792 for GPT-OSS-120B reading pdftotext, a bounded +16.7 percentage-point lift concentrated on figure annotations and OCR-damaged numerics.

For the drilling engineer, an instrumented drillstring is a resource-constrained, communication-starved, safety-critical edge node: it must estimate its own state, schedule its own work, and survive faults while the surface is too far and the telemetry too narrow to intervene in time. The Apollo Guidance Computer (AGC) met a structurally similar predicament in 1969 under documented and severe constraints, and we argue that its systems-engineering playbook, not its algorithms, is an underused reference architecture for drilling automation. We make four mappings precise and bound each. Apollo’s priority-scheduled, fault-tolerant executive, the design that turned the first 1202 program alarm into a survivable event, is the right structure for protecting a safety-critical drilling-automation task under overload; a reproducible model shows that priority with deliberate work-shedding holds a safety-critical deadline that a priority-blind scheduler misses. Apollo flew a numerically stable square root (Potter–Battin) Kalman filter in fixed point; on an ill-conditioned survey problem we show that this factored form stays positive semidefinite where the conventional and even the Joseph-stabilized covariance updates fail, and we reframe the standard wellbore position-uncertainty model as the propagation half of that estimator. Apollo’s fixed-point, snapshot-telemetry edge discipline matches a downhole tool that has less surface bandwidth than a 1969 spacecraft. Finally, Apollo’s verb-noun interface, in which the machine proposes and the human commits, is a precedent for the driller’s supervisory console. We delimit the analogy at the point where the subsurface denies an absolute position fix and state the breaking points as a research agenda.

Nowadays hydraulic fracturing is becoming the most popular practice for low permeability reservoirs. While in some cases fractured wells show superior productivity than non-fractured wells, in other cases the effective fracture length which is used to channel gas and oil from reservoir to wellbore, is much shorter than the propped fracture length, thus leading to a lower-than-expected production rate. The main reason is the unsatisfactory well cleanup following the fracturing treatment. In this work the research is focused on capillary pressure’s role in post-fracturing well cleanup. Capillary pressure is inversely proportional to relative permeability to hydrocarbon fluids. Looking at the LaPlace-Young equation, capillary pressure is determined by interfacial tension, contact angle and pore throat radius. Each of the three components is examined first in respect to its role in well cleanup, after which methods of reducing capillary pressure are investigated. Methods of lowering interfacial tension, alteration of contact angle and controlling of effective pore radius are come up with.