Analysis of Data From the Barnett Shale Using Conventional Statistical and Virtual Intelligence Techniques

2011 ◽  
Vol 14 (05) ◽  
pp. 544-556 ◽  
Author(s):  
Obadare O. Awoleke ◽  
Robert H. Lane
Keyword(s):  
Neural Network ◽  
Horizontal Wells ◽  
Recovery Factor ◽  
Barnett Shale ◽  
Production Data ◽  
Water Production ◽  
Vertical Wells ◽  
Self Organizing Maps ◽  
Data Set ◽  
Horizontal And Vertical Wells

Summary A Barnett shale water-production data set from approximately 11,000 completions was analyzed using conventional statistical techniques. Additionally, a water/hydrocarbon ratio and first-derivative diagnostic-plot technique developed elsewhere for conventional reservoirs was extended to analyze Barnett shale water-production mechanisms. To determine hidden structure in well and production data, self-organizing maps and the k-means algorithm were used to identify clusters in data. A competitive-learning-based network was used to predict the potential for continuous water production from a new well, and a feed-forward neural network was used to predict average water production for wells drilled in Denton and Parker Counties, Texas, of the Barnett shale. Using conventional techniques, we concluded that for wells of the same completion type, location is more important than time of completion or hydraulic-fracturing strategy. Liquid loading has potential to affect vertical more than horizontal wells. Different features were observed in the spreadsheet diagnostic plots for wells in the Barnett shale, and we made a subjective interpretation of these features. We find that 15% of the horizontal and vertical wells drilled in Denton County have a load-water-recovery factor greater than unity. Also, 15 and 35% of the horizontal and vertical wells drilled, respectively, in Parker County have a load-recovery factor greater than unity.The use of both self-organizing maps and the k-means algorithm showed that the data set is divided into two main clusters. The physical properties of these clusters are unknown but interpreted to represent wells with high water throughput and those with low water throughput. Expected misclassification error for the competitive-learning-based tool was approximately 10% for a data set containing both vertical and horizontal wells. The average prediction error for the neural-network tool varied between 10 and 26%, depending on well type and location.Results from this work can be used to mitigate risk of water problems in new Barnett shale wells and predict water issues in other shale plays. Engineers are provided a tool to predict potential for water production in new wells. The method used to develop this tool can be used to solve similar challenges in new and existing shale plays.

Machine Learning: Automated Knowledge Acquisition Based on Unsupervised Neural Network and Expert System Paradigms

2005 ◽  
Vol 9 (6) ◽  
pp. 693-697 ◽  
Author(s):  
Nazar Elfadil ◽  
Keyword(s):  
Neural Network ◽  
Expert System ◽  
Knowledge Acquisition ◽  
Training Data ◽  
Neural Network Models ◽  
Self Organizing Maps ◽  
Data Set ◽  
Unsupervised Neural Network ◽  
Automated Knowledge ◽  
Self Organizing

Self-organizing maps are unsupervised neural network models that lend themselves to the cluster analysis of high-dimensional input data. Interpreting a trained map is difficult because features responsible for specific cluster assignment are not evident from resulting map representation. This paper presents an approach to automated knowledge acquisition using Kohonen's self-organizing maps and k-means clustering. To demonstrate the architecture and validation, a data set representing animal world has been used as the training data set. The verification of the produced knowledge base is done by using conventional expert system.

scholarly journals PS1-STRM: neural network source classification and photometric redshift catalogue for PS1 3π DR1

2020 ◽  
Vol 500 (2) ◽  
pp. 1633-1644
Author(s):  
Róbert Beck ◽  
István Szapudi ◽  
Heather Flewelling ◽  
Conrad Holmberg ◽  
Eugene Magnier ◽  
...  
Keyword(s):  
Neural Network ◽  
Broad Band ◽  
Monte Carlo Sampling ◽  
Training Data ◽  
Space Telescopes ◽  
Absolute Deviation ◽  
Self Organizing Maps ◽  
Validation Data ◽  
Data Set ◽  
Photometric Redshift

ABSTRACT The Pan-STARRS1 (PS1) 3π survey is a comprehensive optical imaging survey of three quarters of the sky in the grizy broad-band photometric filters. We present the methodology used in assembling the source classification and photometric redshift (photo-z) catalogue for PS1 3π Data Release 1, titled Pan-STARRS1 Source Types and Redshifts with Machine learning (PS1-STRM). For both main data products, we use neural network architectures, trained on a compilation of public spectroscopic measurements that has been cross-matched with PS1 sources. We quantify the parameter space coverage of our training data set, and flag extrapolation using self-organizing maps. We perform a Monte Carlo sampling of the photometry to estimate photo-z uncertainty. The final catalogue contains 2902 054 648 objects. On our validation data set, for non-extrapolated sources, we achieve an overall classification accuracy of $98.1{{\ \rm per\ cent}}$ for galaxies, $97.8{{\ \rm per\ cent}}$ for stars, and $96.6{{\ \rm per\ cent}}$ for quasars. Regarding the galaxy photo-z estimation, we attain an overall bias of 〈Δznorm〉 = 0.0005, a standard deviation of σ(Δznorm) = 0.0322, a median absolute deviation of MAD(Δznorm) = 0.0161, and an outlier fraction of $P\left(|\Delta z_{\mathrm{norm}}|\gt 0.15\right)=1.89{{\ \rm per\ cent}}$. The catalogue will be made available as a high-level science product via the Mikulski Archive for Space Telescopes.

Map Matching Using De-Noise Interpolation Kohonen Self-Organizing Maps

2011 ◽  
Vol 460-461 ◽  
pp. 680-686 ◽  
Author(s):  
Zhan Wei Du ◽  
Yong Jian Yang ◽  
Yong Xiong Sun ◽  
Chi Jun Zhang
Keyword(s):  
Neural Network ◽  
Large Error ◽  
Original Position ◽  
Map Matching ◽  
Self Organizing Maps ◽  
Data Set ◽  
Position Information ◽  
True Value ◽  
Match Accuracy ◽  
Self Organizing

In this work, we have proposed a de-noise interpolation Kohonen Self-Organizing Maps(DNIKSOM) -based method for the Map matching(MM). It has been seen that there are some problems in the MM, such as large error range of the original position information, low match accuracy and so on. Therefore, in MM problem to achieve high accuracy, it is necessary to consider the topography of roads and the requirement for match accuracy lying within the original position information in the matching process. In the present study, Kohonen Self-Organizing Maps(KSOM) in the field of pattern recognition possesses good performance. Now to get more valuable position information, A kind of de-noise algorithm for Kohonen neural network is proposed to meet the case that neural network may not be trained sufficiently with consideration for the topography of roads. And a kind of Lagrange interpolation algorithm is also proposed to meet the requirements for matching accuracy. These processes make the amended position information closer to the true value. In this application to a city’s MM, we investigate DNIKSOM’s ,KSOM’s and Centroid localization algorithm’s location performance on a original position data set. Finally, the comparison of experimental results shows that DNIKSOM has better location performance than others.

Application of Multi-Lateral Wells for Production and Enhanced Oil Recovery – Case Studies From Canada

2021 ◽  
Author(s):  
Eric Delamaide
Keyword(s):  
Oil Recovery ◽  
Western Canada ◽  
Water Production ◽  
Vertical Wells ◽  
Public Data ◽  
Heavy Oil Reservoirs ◽  
Complex Architectures ◽  
Horizontal And Vertical Wells ◽  
Cumulative Production ◽  
Tertiary Recovery

Abstract The use of multi-lateral wells started in the mid-1990s in particular in Canada, and they have since been used in many countries. However, few papers on multi-lateral wells focus on their production performances, thus what could be expected from such wells in terms of production and recovery factor is not clear and this paper will attempt to address that gap. Taking advantage of public data, the production performances of various multi-lateral wells in Western Canada have been studied. In the cases reviewed in this paper, these wells always target a single formation; they have been used in a variety of fields and reservoirs, mostly for primary production but also for polymer flooding in some cases. Multiple examples will be provided, mostly in heavy oil reservoirs, and production performances will be compared to nearby horizontal and vertical wells whenever possible. From the more classical dual and tri-lateral to more complex architectures with 7 or 8 laterals, and the more exotic, with laterals drilled from laterals, the paper will present the architecture and performances of these complex wells and of some fields that have been developed almost exclusively with multi-lateral wells. Interestingly, multi-lateral wells have not been used much for secondary or tertiary recovery, probably due to the difficulty of controlling water production after breakthrough. However, field results suggest that this may not be such a difficult proposition. One of the most remarkable wells producing a 1,250 cp oil under polymer flood has achieved a cumulative production of over 3MM bbl, which puts it among the top producers in Canada. Although multi-lateral wells have been in use for over 25 years, very few papers have been devoted to the description of their production performances. This paper will bring some clarity on these aspects. It is hoped that this paper will encourage operators to reconsider the use of multi-lateral wells in their fields.

Maximizing Condensate Recovery With Proven Cost Simulation for a Giant UAE Field: Base Study to Estimate Productivity between Horizontal and Vertical Wells

2021 ◽  
Author(s):  
Maxim Sudarev ◽  
Mariam Al Hosani ◽  
Ahmed Mohamed Al Bairaq ◽  
Ihab Nabil Mohamed ◽  
Zainah Salem Al Agbari ◽  
...  
Keyword(s):  
Horizontal Wells ◽  
Gas Production ◽  
Vertical Wells ◽  
Hydrodynamic Simulation ◽  
Field Assessment ◽  
Base Study ◽  
Horizontal And Vertical Wells ◽  
High Production ◽  
Production Demand

Abstract Implementing the horizontalization scheme was developed for number of wells in order to increase the Gas and Condensate production, which will achieve sustainable and profitable Gas Supply. It worth to highlight that most of these wells are being subjected to N2 and lean gas breakthroughs. By adopting a comparison methodology, the horizontal wells showed better performance in terms of HC production and CGR performance. The number of breakthrough in horizontal wells is less or delayed in term of time. High production demand was promoting this project to take place, where the current situation was not supporting due to N2 and lean gas breakthrough, which is affecting the quality of the gas sales. It was challenging to balance between high production demand, N2, and lean gas breakthrough. Initially, optimizing the production allowable was considered to maximize the production from high CGR wells and minimize the production from low CGR wells. The sidetrack scheme is important to penetrate the un-swept area and to maintain the geometry/distances between wells to prevent early breakthrough and minimize the interference. All results from surveillance and hydrodynamic simulation were integrated for final field assessment impact. This work has resulted in positive expected outcome with few millions additional condensate recovery and extended gas production plateau. According the outcomes analysis the implementation plan was designed.

A Holistic Study on Performance Evaluation of Horizontal Wells and its Implications on Tight Spacing Drilling Strategy in Mauddud Reservoir

2021 ◽  
Author(s):  
Lakshi Konwar ◽  
Bader Alhammadi ◽  
Ebrahim Alawainati ◽  
Ajithkumar Panicker
Keyword(s):  
Performance Evaluation ◽  
Future Development ◽  
Horizontal Well ◽  
Horizontal Wells ◽  
Productivity Index ◽  
Water Production ◽  
Vertical Wells ◽  
Productivity Improvement ◽  
Well Productivity ◽  
Improvement Factor

Abstract The objective of this paper is to present the comparative results of comprehensive analysis of horizontal well productivity and completion performance with vertical wells drilled and completed within same time window in the Mauddud reservoir in the Bahrain Oil Field. The study also focuses on performance evaluation of horizontal wells drilled in different areas of the field. Key reservoir risks and uncertainties associated with horizontal wells are identified, and contingency and mitigation plans are devised to address them. Besides controlling gas production, the benefits of using cemented horizontal wells over vertical wells are highlighted based on performance of recently completed workovers and economic evaluation. Reservoir and well performance are analyzed using a variety of analytical techniques such as well productivity index (PI), productivity improvement factor (PIF), normalized productivity improvement factor (PIFn), well productivity coefficient (Cwp), in conjunction with a statistical distribution function to reflect the average and most likely values. In addition, average oil/gas/water production, cumulative production, reserves, and estimated ultimate recovery (EUR) are compared for both vertical and horizontal wells using decline curve analysis. Furthermore, economics are evaluated for tight spacing drilling with vertical wells, as well as horizontal cemented wells, to optimize future development of Mauddud reservoir. Based on the evaluation, it is inferred that the average horizontal well outperforms a vertical well in terms of production rate, PI, PIF, reserves, and EUR in the field except in waterflood areas. Based on average cumulative oil, reserves and EUR, and well productivity coefficient, overall performance of horizontal wells are better in the GI area in comparison their counterparts in the North/South areas of the Mauddud reservoir, where the dominant mechanism is strong water drive. High gas and water production in horizontal wells are attributed to open-hole completions of the wells and the possibility of poor cementing. A trial has been completed recently in a few horizontal wells using cased-hole cemented completion with selected perforations, resulting in improved oil rates and the drastic reduction of gas to oil ratio. Furthermore, two new cased-hole cemented horizontal wells are planned in 2021 as a trial. A detailed cost-benefit analysis using a net present value concept is performed, leading to a rethink of future development strategies with a mix of both vertical as well as horizontal wells in the GI area. Using the dimensionless correlations and distribution functions, the productivity and PIF of new horizontal wells to be drilled in any area can be predicted during early prognosis given the values of average reservoir permeability, well length, and fluid properties. This study can be used as a benchmark for the development of a thin oil column with a large and expanding gas cap under crestal gas injection using both vertical and horizontal wells.

Evaluation of Inflow Performance of Multiple Horizontal Wells in Closed Systems

1999 ◽  
Vol 122 (1) ◽  
pp. 8-13 ◽  
Author(s):  
Suwan Umnuayponwiwat ◽  
Erdal Ozkan
Keyword(s):  
Horizontal Well ◽  
Transient Flow ◽  
Horizontal Wells ◽  
Vertical Wells ◽  
Well Pattern ◽  
Horizontal And Vertical Wells ◽  
Closed Systems ◽  
Inflow Performance

This work presents a model to investigate the inflow performance relationships (IPR) of horizontal and vertical wells in a multi-well pattern. The model can be used to compute the overall and individual well performances. It is shown that stabilized IPRs may not be sufficient for the evaluation of horizontal well performances due to prolonged transient flow periods. The results presented in this paper clearly indicate that inflow performance of wells in a multi-well pattern is a dynamic concept; and, especially in the prediction of future performances, dynamic rather than static IPR models should be used. [S0195-0738(00)00801-3]

Data Analysis of Barnett Shale Completions

SPE Journal ◽  
2008 ◽  
Vol 13 (03) ◽  
pp. 366-374 ◽  
Author(s):  
William V. Grieser ◽  
Robert F. Shelley ◽  
Bill J. Johnson ◽  
Eugene O. Fielder ◽  
James R. Heinze ◽  
...  
Keyword(s):  
Organic Matter ◽  
Thermal Transformation ◽  
Lower Boundary ◽  
High Water ◽  
Core Area ◽  
Barnett Shale ◽  
Water Production ◽  
Data Set ◽  
The Core ◽  
Stimulation Of

Summary The north Texas Barnett shale illustrates the successful commercialization of an unconventional reservoir. However, it took 17 years to evolve from pumping crosslinked gel (XLG) carrying more than 1 million lbm of proppant per job to sand waterfracs (SWFs) consisting of large volumes of water with friction reducer and small quantities of sand. This transition to SWF stimulation opened the door for widespread development that has advanced the Newark East (Barnett shale) to the largest producing gas field in Texas. This paper investigates Barnett completion strategy from 1993 to 2002. The 393-well data set includes completion, reservoir, and production data. Unique data-evaluation tools and techniques were used to investigate various completion and reservoir parameters to determine their effects on production (Shelley and Stephenson 2000; Zangl and Hannerer 2003). We found that production results show a broad scattering when crossplotted with various completion and reservoir inputs. This result is not uncommon when analyzing field data. However, general trends were identified through comparisons of large numbers of wells. These trends were confirmed through the use of more-advanced data-mining techniques, which included self-organizing mapping (SOM) of data. The results show that SWF-type stimulation of the Barnett outperformed to varying degrees XLG treatments for the five reservoir types used in this evaluation. Geology The Barnett is a Mississippian marine shelf deposit. The Barnett shale ranges in thickness from 200 ft in the southwest region to 1,000 ft in the northeast near the Munster arch. The formation is described as a black, organic-rich (total organic content 4.5%) shale composed of fine-grained, nonsiliciclastic rocks with extremely low permeability (0.00007 to 0.005 md). The organic matter in the shale was first reported to contain 60 scf/ton but could be as high as 200 scf/ton (Montgomery et al. 2005). The Barnett is described as a "spent oil-prone source rock with porosity and permeability developed with thermal transformation of its organic matter from liquid to gas with resulting maturation-induced microfractures" (Jarvie et al. 2004). While the Barnett is classified as shale, it is complex and not homogeneous. In the core area (Denton and Wise counties), the Barnett is composed of two producing intervals notated as the upper and lower Barnett. These intervals are separated by the Forestburg lime, which varies in thickness from 20 ft to more than 150 ft. When production from the lower and upper Barnett is commingled, the lower Barnett contribution is 75-80% of the total. This value has been verified from production logs and from measuring production when isolating the intervals and producing them individually. The lower boundary (Viola/Simpson) pinches out west of the core area. The Ellenberger is a known water source, so stimulation of the lower Barnett without the Viola/Simpson can lead to high water production. Another potential for water production is the Viola, which in some areas has high water-production potential. Historical Completion Practices The first stimulation completion of the Barnett used nitrogen gas as the injection fluid. In early Barnett development, a concern about the high clay content in the shale led to precautions when using water-based fluids. An average mineral analysis from samples collected in Wise County, Texas, is given in Table 1. Early completion fluids tended to be foamed or gas-assisted. Our data set begins approximately 4 years before the first SWF was attempted. Reasons for this transition were predominately driven by economics. SWFs provided the operator with a substantial savings in stimulation costs; however, the ability to place high concentrations of proppant was eliminated. SWF began in 1997-98, and the assumption was that the Barnett would respond to a sand concentration of less than a monolayer and yield commercial production (Grieser et al. 2003). The lower Barnett was the only interval completed during the early development of the Barnett field using XLG-type treatments. The upper Barnett interval was added to the completion when the SWF era began. The addition of upper and lower net pay in the wells treated with SWF is the reason for the extra thickness. The cost savings that were realized with the evolution to the SWF enabled the additional expenditure for completing the upper Barnett. Stimulation treatment averages and production outcome are given in Table 2 for XLG fracs and SWF.

Integrated characterization of hydraulic fracture treatments in the Barnett Shale: The Stocker geophysical experiment

2014 ◽  
Vol 2 (2) ◽  
pp. T111-T127 ◽  
Author(s):  
Baishali Roy ◽  
Bruce Hart ◽  
Anastasia Mironova ◽  
Changxi Zhou ◽  
Ulrich Zimmer
Keyword(s):  
Hydraulic Fracture ◽  
Horizontal Wells ◽  
Time Lapse ◽  
Seismic Facies ◽  
Barnett Shale ◽  
Hydraulic Fractures ◽  
Fracture Networks ◽  
Data Set ◽  
Stochastic Inversion ◽  
Wireline Logs

We integrated several independent geophysical and geologic methods to examine the effects of stratigraphic and structural heterogeneities on the growth of hydraulic fracture networks from two horizontal wells in the Barnett Shale, Fort Worth Basin, Texas. Our data set included time-lapse 3D seismic surveys, microseismic data, wireline logs, and distributed temperature sensing (DTS) data. We first created a local stratigraphic framework using wireline logs. In our area, the lower Barnett Shale consists of siliceous mudstones (the primary reservoir) intercalated with carbonate submarine fan deposits. The latter are low porosity (i.e., nonreservoir) and, if thick enough are potential baffles to the growth of hydraulic fractures. We used stochastic inversion to define the 3D distribution of fan lobes with much better resolution than could be obtained using deterministic inversion and obtained a geologically reasonable lithology prediction. The lowest of the fan lobes partially overlies the two horizontal wells, and its limits could be defined using wireline logs, the stochastic inversion, and seismic attributes (e.g., coherence, seismic facies classification). As suggested by the distribution of microseismic events, the extent of this lobe (locally up to 80 ft/24-m-thick) had a significant impact on the growth of the hydraulic fracture networks. The DTS data showed that high production correlates to dense microseismic activity in this area. Our time-lapse seismic analyses suggested that velocity changes induced by the hydraulic injections are detectable, although (largely because of logistical problems) the data were inadequately sampled to quantitatively define these changes. Alone, none of the analyses described herein provided an adequate understanding of the subsurface. However, once integrated, our multidisciplinary work provided a coherent, if still largely qualitative, understanding of the relationships between the geology and the growth of hydraulic fracture networks and some of the geophysical and engineering methods that can be used to define those links.

scholarly journals The The Optimum Reservoir Performance of Nahr Umr/Ratawi Oil Field

2020 ◽  
Vol 26 (2) ◽  
pp. 42-56
Author(s):  
Mohammed Rashad Jemeel ◽  
Samahr A. Lazium ◽  
Sameera Hamdullah
Keyword(s):  
Production Rate ◽  
Horizontal Wells ◽  
Oil Field ◽  
Production Data ◽  
Well Test ◽  
Vertical Wells ◽  
Production Rates ◽  
Optimum Performance ◽  
Reservoir Performance ◽  
Test Pressure

Reservoir study has been developed in order to get a full interesting of the Nahr Umr formation in Ratawi oil field. Oil in place has been calculated for Nahr Umr which was 2981.37 MM BBL. Several runs have been performed to get matching between measured and calculated of oil production data and well test pressure. In order to get the optimum performance of Nahr Umr many strategies have been proposed in this study where vertical and horizontal wells were involved in addition to different production rates. The reservoir was first assumed to be developed with vertical wells only using production rate of (80000–125000) STB/day. The reservoir is also proposed to produce using horizontal wells besides vertical wells with production rate of (80000-150000) STB/day. The best strategy was by adding 33 new vertical wells and 5 horizontal wells beside the 11 existing wells where the results show oil plateau of 9 years and 7 months and recovery factor of 3.4%.

Sign in / Sign up

Export Citation Format

Share Document