An understanding of statistical concepts is important to many aspects of petroleum engineering, but especially reservoir modeling and simulation. The discussion below focuses on a range of statistical concepts that engineers may find valuable to understand. The focus here is classical statistics, but differences in the application for geostatistics are included. A quantitative approach requires more than a headlong rush into the data, armed with a computer.
Many approaches to estimating permeability exist. Recognizing the importance of rock type, various petrophysical (grain size, surface area, and pore size) models have been developed. This page explores techniques for applying well logs and other data to the problem of predicting permeability [k or log(k)] in uncored wells. If the rock formation of interest has a fairly uniform grain composition and a common diagenetic history, then log(k)-Φ patterns are simple, straightforward statistical prediction techniques can be used, and reservoir zonation is not required. However, if a field encompasses several lithologies, perhaps with varying diagenetic imprints resulting from varying mineral composition and fluid flow histories, then the log(k)-Φ patterns are scattered, and reservoir zonation is required before predictive techniques can be applied.
Pore pressure prediction plays a critical role in the ability to predict areas of high overpressure and fracture behavior for the exploitation of unconventional plays, which are both correlated with production. Shales in these plays have variable clay content and complex multi-mineral fractions that require a detailed petrophysical assessment reinforced with rock physics modelling as needed. For example, changes in total organic content have a similar elastic response to changes in porosity. Therefore, any pressure-stress property model for unconventional plays must be supported by petrophysically conditioned elastic logs and accurate multi-mineral volume sets calibrated to core data.
A supervised deep neural network approach is introduced as an alternative innovative tool for petrophysical, pore pressure and geomechanics analysis enabling the use of all the previously collected and interpreted data to devise solutions which simultaneously integrate wide ranging well bore and wireline logs. We implement three neural networks, all with similar structure, as each of these networks had a different objective and the outputs from one were the inputs for the other.
The first network was trained to predict petrophysical volume logs (shale, sand, dolomite, calcite, kerogen and also porosity) simultaneously from compressional velocity (Vp), Gamma ray, density (rho), resistivity and Neutron logs. The second neural network, cascaded from the first, was then designed to match the manually predicted pore pressure. The inputs were Vp and shear velocity (Vs), Rho, resistivity, Neutron logs as well as the results of the first network. The third network focused on predicting various properties of interest, in this case pore pressure, minimum horizontal stress (Shmin), maximum horizontal stress (SHmax), and volume of kerogen, based on only Vp, Vs, and Rho logs which is an example building a neural network capable of predicting key rock properties directly from seismic inversion results to produce meaningful 3D interpretations.
The volumetric pore pressure model was also positively correlated to cumulative production values from blind long horizontal wells. The results show a promising outlook for the application of deep learning in integrated studies such as those shown in this paper.
Martini, Brigette (Corescan Inc.) | Bellian, Jerome (Whiting Petroleum Corporation) | Katz, David (Encana Corporation) | Fonteneau, Lionel (Corescan Pty Ltd) | Carey, Ronell (Corescan Pty Ltd) | Guisinger, Mary (Whiting Petroleum Corporation) | Nordeng, Stephan H. (University of North Dakota)
Hyperspectral core imaging studies of the Bakken-Three Forks formations over the past four years has revealed non-destructive, high resolution, spatially relevant insight into mineralogy, both primary and diagenetically altered that can be applied to reservoir characterization. While ‘big’ data like co-acquired hyperspectral imagery, digital photography and laser profiles can be challenging to analyze, synthesize, scale, visualize and store, their value in providing mineralogical information, structural variables and visual context at scales that lie between (and ultimately link) nano and reservoir-scale measurements of the Bakken-Three Forks system, is unique.
Simultaneous, co-acquired hyperspectral core imaging data (at 500 μm spatial resolution), digital color photography (at 50 μm spatial resolution) and laser profiles (at 20 μm spatial and 7 μm vertical resolution), were acquired over 24 wells for a total of 2,870 ft. of core, seven wells of which targeted the Bakken-Three Forks formations. These Bakken-Three Forks data (~5.5 TB) represent roughly 175,000,000 pixels of spatially referenced mineralogical data. Measurements were performed at a mobile Corescan HCI-3 laboratory based in Denver, CO, while spectral and spatial analysis of the data was completed using proprietary in-house spectral software, offsite in Perth, WA, Australia. Synthesis of the spectral-based mineral maps and laser-based structural data, with ancillary data (including Qemscan, XRD and various downhole geophysical surveys) were completed in several software and modelling platforms.
The resulting spatial context of this hyperspectral imaging-based mineralogy and assemblages are particularly compelling, both in small scale micro-distribution as well as borehole scale mineralogical distributions related to both primary lithology and secondary alteration. These studies also present some of the first successful measurement and derivation of lithology from hyperspectral data. Relationships between hyperspectral-derived mineralogy and oil concentrations are presented as are separately derived structural variables. The relationship between hyperspectral-based mineralogy to micro-scale reservoir characteristics (including those derived from Qemscan) were studied, as were relationships to larger-scale downhole geophysical data (resulting in compelling correlations between variables of resistivity and hyperspectral-mineralogy). Finally, basic Net-to-Gross calculations were completed using the hyperspectral imaging data, thereby extending the use of such data from geological characterizations through to resource estimations.
The high-fidelity mineralogical maps afforded by hyperspectral core imaging have not only provided new geological insight into the Bakken-Three Forks formations, but ultimately provide improved well completion designs in those formations, as well as a framework for applying the technology to other important unconventional reservoir formations in exploration and development. The semi-automated nature of the technology also ushers in the ability to consistently and accurately log mineralogy from multiple wells and fields globally, allowing for advanced comparative analysis.
Klie, Hector (DeepCast.ai) | Klie, Arturo (DeepCast.ai) | Rodriguez, Adolfo (OpenSim Technology) | Monteagudo, Jorge (OpenSim Technology) | Primera, Alejandro (Primera Resources) | Quesada, Maria (Primera Resources)
The Vaca Muerta formation in Argentina is emerging as one of the most promising resources of shale oil/gas plays in the world. At the current well drilling pace, challenges in streamlining data acquisition, production analysis and forecasting for executing timely and reliable reserves and resource estimations will be an overarching theme in the forthcoming years. In this work, we demonstrate that field operation decision cycles can be improved by establishing a workflow that automatically integrates the gathering of reservoir and production data with fast forecasting AI models.
We created a data platform that regularly extracts geological, drilling, completion and production data from multiple open data sources in Argentina. Data cleansing and consolidation are done via the integration of fast cross-platform database services and natural language processing algorithms. A set of AI algorithms adapted to best capture engineering judgment are employed for identifying multiple flow regimes and selecting the most suitable decline curve models to perform production forecasting and EUR estimation. Based on conceptual models generated from minimum available data, a coupled flow-geomechanics simulator is used to forecast production in other field areas where no well information is available. New data is assimilated as it becomes available improving the reliability of the fast forecasting algorithm.
In a matter of minutes, we are able to achieve high forecasting accuracy and reserves estimation in the Vaca Muerta formation for over eight hundred wells. This workflow can be executed on a regular basis or as soon as new data becomes available. A moderate number of high-fidelity simulations based on coupled flow and geomechanics allows for inferring production scenarios where there is an absence of data capturing space and time. With this approach, engineers and managers are able to quickly examine a feasible set of viable in-fill scenarios. The autonomous integration of data and proper combination of AI approaches with high-resolution physics-based models enable opportunities to reduce operational costs and improving production efficiencies.
The integration of physics-based simulations with AI as a cost/effective workflow on a business relevant shale formation such as Vaca Muerta seems to be lacking in current literature. With the proposed solution, engineers should be able to focus more on business strategy rather than on manually performing time-consuming data wrangling and modeling tasks.
Mechanical rock properties have a complex impact on long, horizontal wells’ stimulations. Through multi-variate analysis of mechanical data, petrophysical facies modeling can provide a predictive and actionable categorization. For the greatest value, petrophysical facies must be calibrated to measured stimulation responses. Calibrating the model to these responses is complicated for two reasons: 1) the difference in resolution between measured mechanical data and multi-hundred-foot treatment stages and 2) the disconnect between the petrophysicist manipulating the log data and the engineer reviewing the treatments. This workflow presents an open-source software solution for importing and upscaling mechanical facies logs to an analytical interface. The completion engineer uses the interface to calibrate petrophysical facies to treatment stage data.
To build the mechanical facies model, mechanical rock property data is measured while drilling the lateral well. Mechanical data includes Young's Modulus and vertically-transverse isotropic (VTI) anisotropy. From these measured properties, the petrophysicist empirically interprets unconfined compressive strength (UCS) and shale volume, respectively. A type of cluster analysis algorithm, common in petrophysical facies workflows, is used to build a facies model from UCS and shale volume.
This workflow 1) takes the mechanical facies model from the petrophysical software, 2) up-scales the half-foot data to the treatment stage resolution, 3) calculates a stress-shadowing effect based on treatment stage order, and 4) brings stage-by-stage facies into a statistical software package for the engineer.
Using the statistical software, the engineer has an interactive template to identify relationships between the facies and stage-by-stage treatment responses. The template allows the engineer to filter stages based on abnormal treating responses associated with non-geologic operational issues and make other calibration adjustments. The engineer selects a treatment parameter that is pertinent to observed challenges and is regionally focused (e.g. tortuosity, injectivity, etc.). Scalars applied to the facies are then calibrated to achieve a best fit between the modeled and actual parameters. Once a best fit is achieved, the engineer will have insight into which facies are dominating the treatment responses. Then, the engineer can apply these insights to future completions to increase treatment efficiency and effectiveness.
This workflow provides a simple way for the completions engineer to calibrate lateral mechanical logs to stage the well by grouping regions of the lateral that should treat similarly and isolating or flagging regions that could be troublesome. Calibrated models have been successfully developed in the Permian and Williston Basins. In this demonstration of the concept, we will show a prediction of frac gradient (FG) in the Williston Basin.
This study introduces a methodology for estimating uncertainty in production of new shale wells. The methodology combines geostatistical modeling and machine learning and accounts for geological uncertainty. Our approach improves uncertainty quantification by merging local and global trends.
A functional random forest regression model is trained, connecting completion parameters and geological parameters with production profiles. The geological parameters are simulated on a two-dimensional areal grid using Sequential Gaussian Simulation with information from pilot wells. Production profiles are generated for each cell in the simulation grid based on optimal completion and simulated geological parameters. These machine learning-based realizations account for the global trends. We account for local effects by using cokriging to merge total production from nearby wells with the production from machine learning-based realizations.
We test the methodology on a dataset from the Eagle Ford formation. The result of the study is a map of the play highlighting the most probable production (P50) for different areas and associated risk (P90–P10). The resulting map allows us to rank locations for new wells for drilling. The proposed methodology provides a first estimate, and a more detailed data investigation is required to sanction a new well in a particular location.
The size of the individual seismic surveys has increased over the last decade, along with the generation of megamerge and even larger, what some operators call “gigamerge” surveys. The number of useful attribute volumes has also increased, such that interpreters may need to integrate terabytes of data. During the past several years, various machine learning methods including unsupervised, supervised and deep learning have been developed to better cope with such large amounts of information. In this study we apply several unsupervised machine learning methods to a seismic data volume from the Barents Sea, on which we had previously interpreted shallow high-amplitude anomalies using traditional interactive interpretation workflows. Specifically, we apply k-means, principal component analysis, self-organizing mapping and generative topographic mapping to a suite of attributes and compare them to previously generated P-impedance, porosity and Vclay displays, and find that self-organized mapping and the generative topographic mapping provide additional information of interpretation interest.
In the late 1980s, seismic facies analysis was carried out on 2D seismic data by visually examining the seismic waveforms that can be characterized by their amplitude, frequency and phase expression. Such information would be posted on maps and contoured to generate facies maps. As seismic data volumes increased in size with the adoption of 3D seismic data in the early 1990s, interpreters found that 3D seismic attributes highlighted patterns that facilitated the human recognition of geologic features on time and horizon slices, thereby both accelerating and further quantifying the interpretation. More recently, computer-assisted seismic facies classification techniques have evolved. Such methods or workflows examine seismic data or their derived geometric, spectral, or geomechanical attributes and assign each voxel to one of a finite number of classes, each of which is assumed to represent seismic facies. Such seismic facies may or may not represent geologic facies or petrophysical rock types. In this workflow, well log data, completion data, or production data are then used to determine if a given seismic facies is unique and should be lumped (or “clustered”) with other similar facies determined from attributes with similar attribute expression.
Butler, Shane (University of North Dakota Energy & Environmental Research Center) | Azenkeng, Alexander (University of North Dakota Energy & Environmental Research Center) | Mibeck, Blaise (University of North Dakota Energy & Environmental Research Center) | Kurz, Bethany (University of North Dakota Energy & Environmental Research Center) | Eylands, Kurt (University of North Dakota Energy & Environmental Research Center)
Advanced characterization of the Bakken Formation, an unconventional oil and gas play of the Williston Basin, was performed via newly developed analytical tools of microscopic investigation in concert with standard laboratory methods. Characterization of an unconventional formation to understand the composition and distribution of framework grains, organic matter (OM), clay minerals, and porosity is difficult because of the extremely lithified nature of the lithofacies within the formation and the small grain and particle sizes. In this study, corroborative methods aimed to define micro- and nanoscale fabrics that impact parameters such as maturity, recovery, clay content, micropore networks, and CO2 interactions for either storage or enhanced oil recovery (EOR). Lateral and vertical variations in the rock fabric across multiple wellsites were observed on a micro- to nanometer scale with innovative analytical technologies.
Detailed morphologies and chemical compositions of ion-milled samples were obtained with field emission scanning electron microscopy (FESEM) coupled with energy-dispersive spectroscopy (EDS). Furthermore, a new software suite, Advanced Mineral Identification and Characterization System (AMICS), was used to classify and quantify mineralogy, OM, and porosity from the FESEM images. For validation purposes, x-ray diffraction was used to obtain bulk mineral and clay mineral data and x-ray fluorescence to obtain bulk chemical compositions of the samples. Advanced image analysis was performed on high-resolution FESEM images as another corroborative approach to characterize key features of interest within the lithofacies. Each sample consisted of high-resolution FESEM backscattered electron (BSE) images taken at multiple magnifications to maximize particle morphology in the fine-grained rock of the unconventional reservoir.
The data highlighted trends related to factors that impact CO2 transport and sorption in unconventional reservoirs. Segmented BSE images from the FESEM using program parameters that included texture, gray scale, and other morphological properties made it possible to estimate OM, clays, and porosity for each sample. The compositional analysis, including matrix porosity, OM porosity, and mineralogical composition maps, provided context for the potential of organic-rich and tight rock formations as CO2- based EOR targets or CO2 storage targets.
Advanced image analysis techniques were applied to better understand and quantify factors that could affect CO2 storage in the Bakken Formation, with an ultimate goal of improved method development to estimate CO2 storage potential of unconventional reservoirs. Discernible differences in fabric, mineral, and elemental content in comparable lithofacies across wellsites provided insight into the nature of the Bakken Formation, which could serve as a proxy for other tight rock, organic-rich reservoirs that could be potential targets for both CO2-based EOR and CO2 storage.
Applications, Significance, and Novelty: The proposed methodology may be widely applied, since it relies on available standard well and completion data. This method can be used on (i) legacy projects where offset pressure data was recorded; (ii) post job analysis of recent completions, and (iii) near real-time analysis of current completions.