Efficient Use of Data Analytics in Optimization of Hydraulic Fracturing in Unconventional Reservoirs

Temizel, Cenk; Purwar, Suryansh; Abdullayev, Azer; Urrutia, Karelis; Tiwari, Aditya

doi:10.2118/177549-ms

Cited by 7 publications

(6 citation statements)

References 36 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…with the increase in number of stages. As the number of fracture stages increases, the efficiency of incremental stages decreases in the Bakken shale Formation [25]. Beyond a certain number, therefore, the incremental cost would exceed the incremental benefits.…”

Section: Estimated Ultimate Recovery Of Wells (Eur) Usually Increasesmentioning

confidence: 99%

Optimal Spacing of the Wolfcamp in the Delaware Basin

Alzahabi¹

2021

GJES

View full text Add to dashboard Cite

Proper well spacing for horizontal wells is one of the missing pieces for the Delaware Basin development in the Wolfcamp Formation. In the Wolfcamp formation in the Delaware Basin, well spacing varies with formation characteristics (rock and fluid) across the Basin. Finding the spacing intervals between horizontal wells right is crucial to maximizing productivity and estimated ultimate recovery (EUR) while avoiding detrimental frac hits and cross-well pressure and fluid interference during stimulation and production.Along with the various parameters affecting development, well patterns and completion methodologies are having the highest impact. Both parameters show a significant impact on the drainage area of wells and may in turn affect optimal spacing between the wells. The model outcomes are expected to improve recovery efficiency, oil production, and minimize detrimental frac hits and cross-well pressure and fluid interference during stimulation and production. A pool of private production and spacing data were analyzed in conjunction with data analytics. This step led to a newly developed model to optimize well spacing.• Fluid Bbls = the amount of fluid pumped downhole to initiate fracture and place proppant.• Fluid Gal/Cluster = the amount of fluid pumped per cluster.

show abstract

Section: Estimated Ultimate Recovery Of Wells (Eur) Usually Increasesmentioning

confidence: 99%

Optimal Spacing of the Wolfcamp in the Delaware Basin

Alzahabi¹

2021

GJES

View full text Add to dashboard Cite

show abstract

“…Source Cumulative oil production 6/18 month just after the job [24] 12 months cumulative oil production [25] Average monthly oil production after the job [19] NPV [26] Comparison to modelling [28] Delta of averaged Q oil [29] Pikes in liquid production for 1, 3 and 12 months [30] Break even point (job cost equal to total revenue after the job) [32] • In [26], a procedure was presented to optimize the fracture treatment parameters such as fracture length, volume of proppant and fluids, pump rates, etc. Cost sensitivity study upon well and fracture parameters vs NPV as a maximization criteria is used.…”

Section: Metricsmentioning

confidence: 99%

“…• Statistically representative set of synthetic data served as an input for machine learning algorithm in [28]. The study analyzed the impact of each input parameter to the simulation results like cumulative gas production for contingent resources like shale gaz simulation model.…”

Section: Metricsmentioning

confidence: 99%

“…The performance of the data-driven models is validated by comparing the results to a numerical model, including size, number, location, phasing angle of perforations, fluid and proppant type, rock strength, porosity, and permeability on the fracture design optimization using various fracture models. Data-driven predictive models (surrogate models, see [38]) are generated by using ANN and SVM algorithms [28].…”

Section: For Frac Design Optimizationmentioning

confidence: 99%

“…Metrics Source Cumulative oil production 6/18 month just after the job [24] 12 months cumulative oil production [25] Average monthly oil production after the job [19] NPV [26] Comparison to modelling [28] Delta of averaged Q oil [29] Pikes in liquid production for 1, 3 and 12 months [30] Break even point (job cost equal to total revenue after the job) [32] Table 1: Success metrics of HF job…”

Section: Problem Statementmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning on field data for hydraulic fracturing design optimization

Mutalova¹,

Morozov²,

Осипцов³

et al. 2019

Preprint

View full text Add to dashboard Cite

Growing amount of fracturing stimulation jobs in the recent two decades resulted in a significant amount of measured data available for construction of predictive models via machine learning (ML). Simultaneous evolution of machine learning has made it possible to apply algorithms on the hydraulic fracture database. A typical multistage fracturing job on a near-horizontal well today involves a significant number of stages. The post-fracturing production analysis (e.g., from production logging tools) reveals evidence that different stages produce very non-uniformly, and up to 30% may not be producing at all due to a combination of geomechanics and fracturing design factors. Hence, there is a significant room for fracturing design optimization, and the wealthy of field data combined with ML techniques opens a new road for solving this optimization problem. However, ML algorithms are only applicable when there is a comprehensive, well structured digital database. This paper summarizes the efforts into the creation of a digital database of field data from several thousands of multistage hydraulic fracturing jobs on near-horizontal wells from several different oilfields in Western Siberia, Russia. In terms of the number of points (fracturing jobs), the present database is a rare case of an outstandingly representative dataset of thousands of cases, compared to typical databases available in the literature, comprising tens or hundreds of pints at best. The focus is made on data gathering from various sources, data preprocessing and development of the architecture of a database as well as solving fracture design optimization via ML. We work with the database composed from reservoir properties, fracturing designs and production data. Both forward problem (prediction of production rate from fracturing design parameters) and inverse problem (selecting an optimum set of frac design parameters to maximize production) are considered. A recommendation system is designed for advising a DESC engineer on an optimized fracturing design.

show abstract

Optimizing Unconventional Completions - An Integrated Approach

Fulks

Hughes

Geldmacher

2016

Day 1 Mon, November 07, 2016

View full text Add to dashboard Cite

North American unconventional well completion design has evolved dramatically since 2013 in an effort to keep pace with the productivity gains realized in horizontal drilling. Several trends have emerged during the current industry downturn. Among these trends are a focus on core acreage with higher yield potential, the use of longer laterals, a movement towards higher proppant loading (pounds per linear foot), an increased reliance on plug and perf techniques, and decreased stage length and perforation cluster spacing (increased perf density). As a result associated improvements in well initial production (IP) rates and estimated ultimate recoveries (EUR's) have been highlighted in oil & gas operator's quarterly shareholder's reports during 2015 and early 2016. Unconventional multi-stage completion designs have also quickly evolved along a path paralleling these trends. Horizontal well IP rates and EUR's have also been enhanced through the adoption of integrated completion designs. Recently introduced geo-engineered completions rely on cross-functional expertise and software to integrate petrophysical, geomechanical, drilling, and production data into a completion design. In cases where geo-engineered designs were used, wells showed improvements in EUR's over those associated with increased lateral lengths, proppant loading and stage counts. In one recent case using a geo-engineered design it was demonstrated that fewer stages and clusters achieved higher production than offset wells while injecting less proppant and fluid; thus achieving lower completion cost. The use of engineered workflows in tight or unconventional reservoirs is not new. Multiple case histories have been published in recent literature illustrating the use of stress variability/contrast or mechanical specific energy (MSE) to generate brittleness or other fraccability indices to group stages with similar rock characteristics. In contrast to engineered designs, newer geo-engineered designs integrate multiple inputs (attributes) to determine basin and formation-specific weighted algorithms that correlate to stage and cluster production contribution improvement. The geo-engineered approach has proven repeatable and can be accomplished even when key wireline or LWD data is not available. This paper will document how geo-engineered completion designs evolved from engineered workflows. Multiple inputs (e.g. production, wireline/LWD/mud logs, core analyses, and big data from national and state data bases) can be combined to determine stage length and perforation cluster positioning. Case studies will demonstrate that geo-engineered horizontal completion designs deliver superior well production results when compared to geometric, high-intensity plug & perf designs.

show abstract

Efficient Use of Data Analytics in Optimization of Hydraulic Fracturing in Unconventional Reservoirs

Cited by 7 publications

References 36 publications

Optimal Spacing of the Wolfcamp in the Delaware Basin

Optimal Spacing of the Wolfcamp in the Delaware Basin

Machine learning on field data for hydraulic fracturing design optimization

Optimizing Unconventional Completions - An Integrated Approach

Contact Info

Product

Resources

About