Hydraulic fracturing pumping data is recorded in the field at one-second intervals. Engineers spend hours identifying events such as Instantaneous Shut-in Pressure (ISIP) in the time-series data that is generated. The ISIP flag is placed at the end of the stage pumping time, immediately after shut-in and before the pressure starts to drop. This is estimated by placing a straight line on the early pressure decline and locating the point in time where the pressure rate is zero. Manual selection of this flag is time-consuming, prone to error, and inconsistent due to differing interpretation methods across the industry. The purpose of this study is to demonstrate an automated process to identify accurate and consistent ISIP events in a high-frequency time-series data set using machine learning algorithms.
This study is based on the analysis of metered high-frequency fracturing treatment data from wells landed in different formations across North America coupled with supervised machine learning algorithms. The pumping data includes treating pressure and slurry rate for 870 stages from the Wolfcamp, Bone Spring, Granite Wash, Barnett, Meramec, Niobrara, Codell, Bakken, Three Forks, Haynesville, Bossier, Caney, and Marcellus formations, for a total of over 7 million rows of data per channel. Eighty percent of the data is used to train the model, seven percent is used for validation, and the remaining thirteen percent forms the test set used for the final evaluation. To allow the algorithm to run leaner, the dataset was pre-processed using smoothing techniques, and the rate of change of the main data channels were added. The selected algorithm, an artificial neural network (ANN), was trained to recognize and isolate the necessary data from the treating plot that will be used to predict the ISIP. Once the data is isolated, a filter is used to extract the portion of the data to be used. A second machine learning algorithm, linear regression, is then applied to the portion of extracted data to predict the ISIP value when the slurry rate is equal to zero.
Classification techniques were used to generate an accurate suggestion of the reduced dataset needed to recognize the ISIP event in a high-frequency treating plot. The neural network achieved a classification accuracy (on the training and validation sets) of approximately 98 percent when isolating the target region. The subsequent ISIP predictions from the linear regression on the test set had an average accuracy of +/- 50 psi when compared to the manually picked values. Considering that the typical range for ISIP values is between 2,500 psi and 9,000 psi, 50 psi represents a 0.5% to 2% error. A limitation of this method is that it requires periodic re-training with new field data to improve the prediction robustness and to maintain high accuracy.
Automatically labeling relevant regions of high-frequency hydraulic fracturing treatment plots using classification techniques can lead to simple and effective procedures for identifying events of interest. Accurate flag selection makes processing large volumes of fracture treatment data viable and significantly reduces the time spent reviewing field data for quality control. The method will also allow rapid reprocessing of historical data. The benefits of using simple (and accurate) models include ease of deployment, ease of debugging, and extremely fast prediction and re-training (updating the model).
Tight oil production has increased dramatically and contributed to 61% of total US oil production in 2018. However, recovery factors for primary depletion with multistage fractured wells are low, typically less than 10%. Gas huff-n-puff emerges as a promising technique to push the recovery factor beyond 10% in tight oil reservoirs, based on laboratory studies, simulation and field pilot tests. A CO2 huff-n-puff pilot was implemented in the Midland Basin, and data collected demonstrated significant incremental oil recovery, but with higher than expected water-cut rise.
To understand the excessive water production, a compositional model was built. Eight pseudo-components were used to match the PVT lab results of a typical oil sample in the Wolfcamp shale. A lab scale model was established in our simulator to match the results of gas huff-n-puff experiments in cores, where key parameters were identified and tuned. A half-stage model consisting of five fractures was built, where stress-dependent permeability was represented by compaction tables. Then a sensitivity analysis was conducted to understand the roles of different mechanisms behind the abnormal high water-cut phenomenon on this scale. Our simulation results have shown that initial water saturation, IFT-dependent relative permeability, reactivation of water-bearing layers, and re-opening of unpropped hydraulic fractures may all affect water-cut after gas injection. Among them, re-opening of unpropped hydraulic fractures was the most critical one.
Data from a pilot test imply substantial water production after gas injection, which may impede oil production, but the underlying mechanisms are poorly understood. A numerical model is developed to study possible mechanisms for high water-cut pilot results. This study also intends to quantify the impact of high water cut on cyclic gas injection.
The current scheme for developing shale reservoirs necessitates special considerations while estimating the reserve. While reservoir characteristics lead to an extended infinite acting flow regime, completion schemes could result in a series of linear flows. Therefore, the initial linear flow does not have to be followed by a boundary-dominated flow. Overlooking this observation leads to unphysical Arps’ exponents and overestimations of the Estimated Ultimate Recovery (EUR). We are proposing a workflow to overcome these challenges and honor the inherited uncertainty while using the classic
The combination of extended-length horizontal drilling and high volume hydraulic fracturing has led to previously unimaginable production increases, yet the recovery potential of unconventional oil and gas resources remains largely unrealized. Recovery factors for unconventional oil and gas wells are typically reported at < 20% in gas shale reservoirs and < 10% in the oil plays.
Neutrally buoyant ultra-lightweight proppants have been demonstrated to effectively provide production from fracture area that is otherwise unpropped and thus, non-contributive with conventional sand/slickwater hydraulic fracturing processes. Production simulations illustrate that treatment designs incorporating neutrally buoyant ULW proppant treatment designs tailored for contemporary unconventional well stimulations deliver cumulative production increases of 30% to over 50% compared to the typical large volume sand/slickwater treatments. Unfortunately, production simulation results may not sufficiently lessen risk uncertainties for operators planning high-cost multi-stage horizontal stimulations. Therefore, several field trial projects using the neutrally buoyant ULW proppant in extended-length horizontal unconventional wells are currently in progress to validate the production simulations.
Since the initial 4-stage fracturing stimulation incorporating neutrally buoyant ultra-lightweight proppant in 2007, deployment has occurred in fracture stimulating hundreds of oil and gas wells spanning multiple basins and reservoirs. Most of the wells are vertical or relatively short lateral wells common to asset development practices predating the unconventional shale completions mania, but many were targeted at the same unconventional reservoirs as the current multi-stage horizontal completions. Several published case histories have documented the production enhancement benefits afforded by the legacy ULW proppant wells, but questions remained as to how those lessons might be correlated to provide engineers confidence in the current production simulations.
Well completion and production information was mined from the various accessible databases for the neutrally buoyant ULW proppant wells. The scope of the legacy data compiled for analysis was limited to the reservoirs common to the current field trials and production simulations, ie. unconventional oil and gas shale reservoirs. Production performance contributions of neutrally buoyant ULW proppant in past applications were compared with the production uplift observed in applications and/or simulated application of neutrally buoyant ultra-lightweight proppant fracturing treatments in current multi-stage horizontal reservoirs.
The lessons learned from this investigation provide the practicing engineer the means to confidently assess production simulation data for multi-stage horizontal unconventional completions incorporating neutrally buoyant ulw proppant in the treatment designs.
Production and proved reserves in the Permian Basin’s Wolfcamp Shale and Bone Spring Formation are reaching new heights, and a new assessment from the US Geological Survey indicates the industry is just scratching the subsurface when it comes to what may be technically recoverable. Major oil discoveries by Armstrong Oil & Gas and ConocoPhillips have compelled the US Department of the Interior to reassess its estimate of undiscovered, technically recoverable resources in parts of Alaska. The list of the biggest gas plays in the US is being revised as the US Geological Survey creates new estimates based on additional drilling results and available rock samples. New at Number 2 is the Mancos Shale on the Western Slope of the Rockies with 66 Tcf in recoverable reserves.
Noble’s first row of wells in its massive Mustang project is helping increase the operator’s DJ Basin output, and similar results are soon expected in the Delaware Basin. Production and proved reserves in the Permian Basin’s Wolfcamp Shale and Bone Spring Formation are reaching new heights, and a new assessment from the US Geological Survey indicates the industry is just scratching the subsurface when it comes to what may be technically recoverable. The SPE Liquids-Rich Basin Conference in Midland, Texas, merged topics that have dominated recent industry discussions: technologies centered on big data, interwell communication, and Permian Basin production. WPX Energy COO Clay Gaspar discusses his company’s timely transformation into a Permian player and the challenges that lie ahead in the basin. The Irving, Texas-based supermajor plans to cash in on its expanded foothold in the Permian Basin, aided by a big reduction in the US corporate tax rate.
The strategy supports the Maximise Economic Recovery from UK Oil & Gas Strategy and Vision 2035, whose goal is to achieve £140 billion additional gross revenue from UKCS production by that time. The Caribbean nation hopes the auction will lead to at least two exploration projects in a region that has become increasingly attractive thanks to new discoveries and investments made in neighboring countries. Operator Talos Energy now believes Zama’s gross recoverable resource lies in the upper half of its pre-appraisal estimate of 400–800 million BOE. The consortium is working toward a 2020 final investment decision on the project. The explorer has so far encountered 400 ft of reservoir pay zone in an area where it has three other producing fields.
The shale sector is studying the results of a 23-well experiment in the southeastern corner of New Mexico to learn what the wider implications might be. Researchers from the Federal Reserve Bank of Dallas quantified the economic impact of the US shale revolution for the first half of this decade. The green light for Santos Energy’s drilling program in the McArthur Basin comes after a moratorium on hydraulic fracturing in the Northern Territory was lifted in 2018. Findings from Kayrros suggest the average Permian well is both less productive and more expensive than reflected in public data. Permian Basin operators and service companies met to discuss completions diagnostics, flowback strategies, water management, and artificial lift strategies.
Researchers from the Federal Reserve Bank of Dallas quantified the economic impact of the US shale revolution for the first half of this decade. Times are still financially tough for many shale operators: Sanchez Energy and Halcón Resources become the latest to file for Chapter 11 protection. Share prices have plunged for seemingly every major US shale producer, with Concho, Pioneer, and Continental among those receiving the worst of the market’s fury. Have investors completely lost faith in the industry? And are shale executives any more optimistic?