IPTC-19706-Abstract

Downloaded from http://onepetro.org/IPTCONF/proceedings-pdf/20IPTC/2-20IPTC/D023S171R002/1188294/iptc-19706-abstract.pdf by Universidad Nacional De Colombia user on 11 September 2023

A New Technique to Quantify the Productivity of Complex Wells Using
Artificial Intelligence Tools

Amjed Hassan, Mohamed Mahmoud, Abdulaziz Al-Majed, and Abdulazeez Abdulraheem, King Fahd University of
Petroleum & Minerals

Copyright 2020, International Petroleum Technology Conference

This paper was prepared for presentation at the International Petroleum Technology Conference held in Dhahran, Saudi Arabia, 13 – 15 January 2020.

This paper was selected for presentation by an IPTC Programme Committee following review of information contained in an abstract submitted by the author(s).
Contents of the paper, as presented, have not been reviewed by the International Petroleum Technology Conference and are subject to correction by the author(s). The
material, as presented, does not necessarily reflect any position of the International Petroleum Technology Conference, its officers, or members. Papers presented at
IPTC are subject to publication review by Sponsor Society Committees of IPTC. Electronic reproduction, distribution, or storage of any part of this paper for commercial
purposes without the written consent of the International Petroleum Technology Conference is prohibited. Permission to reproduce in print is restricted to an abstract of
not more than 300 words; illustrations may not be copied. The abstract must contain conspicuous acknowledgment of where and by whom the paper was presented.
Write Librarian, IPTC, P.O. Box 833836, Richardson, TX 75083-3836, U.S.A., fax +1-972-952-9435.

Abstract
Nonconventional wells (NCWs) are applied to increase the well deliverability and access the difficult
formations. The nonconventional wells have been used to refer for the advanced wells such as highly
deviated, horizontal, fishbones or multilateral wells. These wells offer a great potential to maximize the
hydrocarbon recovery, however, it is difficult to predict their performance. In the literature, numerous
mathematical models were developed to predict the well-productivity. However, the available models have
been developed by employing one or more simplifying assumption(s), which may lead to over or under
estimate the hydrocarbon production. This paper presents an effective technique to estimate the productivity
for nonconventional wells.
In this work, artificial intelligence (AI) technique was utilized to determine the well-productivity for
wide range of conditions. The developed models can determine the well performance without introducing
the complexity associated with the numerical approaches. Artificial neural network was utilized to estimate
the hydrocarbon production for two types of nonconventional wells; fishbone multilateral and hydraulically
fractured horizontal wells. Reliable models are presented to quantify the performance of nonconventional
wells producing from heterogeneous and anisotropic formations. The developed models evaluate the
importance of reservoir properties and well configuration on the well deliverability. Total of 850 data sets
were utilized to construct the intelligence models and to validate the prediction performance. Moreover,
mathematical equations were extracted utilizing the optimized ANN models. The extracted correlations
showed acceptable prediction errors, the absolute error around 7.4% in average.
The novelty of this work is that effective models are proposed to quantify the productivity of
nonconventional wells. The proposed models can be utilized to refine commercial software to narrow down
the deviations between the actual measurements and simulation outputs. Also, this work can contribute to
enhance our understanding of the oil-field management by improving the prediction of well deliverability.
Consequently, this study can help in optimizing the well planning for complex wells such as hydraulically
fractured horizontal and fishbone multilateral wells.
2 IPTC-19706-Abstract

Key Words: nonconventional wells (NCWs), artificial intelligence (AI), well productivity, predictive
models

Introduction
Nonconventional (NCWs) or advanced wells are the highly deviated, horizontal or multilateral wells

Downloaded from http://onepetro.org/IPTCONF/proceedings-pdf/20IPTC/2-20IPTC/D023S171R002/1188294/iptc-19706-abstract.pdf by Universidad Nacional De Colombia user on 11 September 2023

(Bosworth et al., 1998). They are considered as a new production technology that can be implemented to
enhance the hydrocarbon production from unconventional resources such as shale or tight gas reservoirs
(Furui et al., 2003). The drilling of nonconventional wells has become standard practice during the past
decade. A single NCW may be more cost-effective than multiple vertical wells in terms of overall drilling
and completion costs (Yu et al., 2009). In addition, nonconventional wells can operate at low drawdown,
and hence reduce the water coning in many cases (Guangyu et al., 2012). NCWs are well suited for
the efficient exploitation of complex reservoirs since they act to increase drainage area and are capable
of reaching attic hydrocarbon reserves or reservoir compartments. Consequently, by drilling these wells,
capital expenditures and operating costs can be reduced (Filho et al., 2015). These appealing advantages,
which lead to more efficient reservoir management, are driving oil and gas producers to reconsider fields
which previously had marginal economics, such as mature, tight, thin or heavy oil reservoirs. Compared to
conventional wells, these wells provide for the same or better reservoir exposure but with fewer wells, hence
improving production and injection strategies. With these advantages, slot utilization can be optimized for
offshore developments (Karakas and Ayan, 1991;). Figure 1 shows the difference between conventional and
unconventional wells (Jessica, 2015; Filho et al., 2015).

Figure 1—Conventional and unconventional wells for producing hydrocarbon from underground reservoirs.

Predicting the well productivity is an essential factor in designing and completing the production well, as
well as selecting the artificial lift and stimulation processes (Guo et al., 2008). Several techniques have been
reported to estimate the well performance for unconventional wells. Different correlations and analytical
models were reported to determine the inflow performance relationship (IPR) (Borisov, 1984; Economides,
IPTC-19706-Abstract 3

1994; Furui et al., 2003; Yildiz, 2005). The most popular equations are Fetkovitch's and Vogel's correlations
(Furui et al., 2003; Ahmed et al., 2016). Recently, numerical simulators have been utilized to estimate
the well productivity, which resulted in significant reduction for the estimation error. Several reservoir
models were evaluated to simulate dual porosity system, triple porosity system, isotropic and anisotropic
permeability conditions (Ding et al., 2012; Filho et al., 2015). Moreover, computational fluid dynamics

Downloaded from http://onepetro.org/IPTCONF/proceedings-pdf/20IPTC/2-20IPTC/D023S171R002/1188294/iptc-19706-abstract.pdf by Universidad Nacional De Colombia user on 11 September 2023

(CFD) analysis has been utilized to model the fishbones performance in depleted reservoirs under water
flooding operations, fishbones multilateral wells showed a productivity improvement of 25% in comparison
with the conventional horizontal wells (Freyer and Shaoul 2011).
Artificial intelligence (AI) technique showed a great performance for prediction purposes. AI methods
such as artificial neural networks (ANN) fuzzy logic system, and support vector machine are extensively
used in the petroleum industry (Alajmi et al., 2015; Alarifi et al., 2015; Chen et al., 2015; Hassan et al., 2017;
Abdalla et al., 2018). For example, Al-Mashhad et al., (2016) estimated the productivity of multilateral wells
utilizing artificial neural networks (ANN). They presented an ANN model to determine the oil production
rate for multilateral wells based on the reservoir and well parameters. They compared the developed model
with analytical models and correlations. The ANN model over performed other models, strong matching
between actual and predicted flow rates was achieved, with an overall average absolute percentage error
of 7.9%.
Nonconventional wells offer a great potential to maximize the hydrocarbon recovery, however, it is
difficult to predict their performance. the available models have been developed by employing one or
more simplifying assumption(s), which may lead to over or under optimistic the predictions. This paper
presents an effective technique to estimate the productivity for nonconventional wells. Reliable models
were developed using artificial neural network, the developed models can quantify the performance of
nonconventional wells producing from heterogeneous and anisotropic formations. Also, the developed
models can be used to determine the well performance without introducing the complexity associated with
the numerical approaches.

Data Acquisition and Statistical Analysis

In this work, the used data were generated by a commercial well software, more than 850 runs were
performed. Actual data were used to build the simulation models, several reservoir conditions were used
as well as different well completion scenarios were investigated. The simulation results were inspected
by a team of production engineers, then, the most practical results were used for developing the artificial
intelligence models. The used data contains the profiles of flowing bottom hole pressures (Pwf) and well
production rate (Q). Also, the well geometry such as distances between laterals, length of each lateral and
number of fractures were included in the used data sets. Randomization function was applied to group the
data into two categories; training and testing sets. The ANN models were trained using 70% of the whole
data, then, the developed models were tested using the reset of the data which are 30% of the data. The testing
data were unseen by the model and used only to validate the model reliability. Table 1 and 2 summarize the
statistical parameters for the hydraulically fractured horizontal and fishbone multilateral wells, respectively.
The minimum, maximum, standard deviation and other statistical parameters are listed. For the hydraulically
fractured horizontal well, the main inputs are the dimensionless pressure (PD), number of fractures (n),
fracture conductivity (CFD) and permeability ratio (Kv/Kh), while the primary inputs for the fishbone well are
the lateral length, number of laterals, distance between laterals, permeability ratio and flowing bottomhole
pressure. Furthermore, the relative importance between the input parameters and the target out was studied
using the correlation coefficient approach. Figures 2 and 3 show the relationship between the input and
output for hydraulically fractured horizontal and fishbone multilateral wells, respectively. Increasing the
value of correlation coefficients indicates the higher importance of the particular input. For both cases,
the flowing bottomhole pressure showed the highest impact on the well production rate. The correlation
4 IPTC-19706-Abstract

coefficient analysis indicates that the permeability ratio has higher influence for the case of fishbone well
compared to the case of hydraulically fractured horizontal.

Table 1—Statistical parameters for the case of hydraulically fractured horizontal well.

Parameter PD n CfD Kv/Kh QD

Downloaded from http://onepetro.org/IPTCONF/proceedings-pdf/20IPTC/2-20IPTC/D023S171R002/1188294/iptc-19706-abstract.pdf by Universidad Nacional De Colombia user on 11 September 2023

Minimum 0.003 1.000 0.034 0.001 0.047

Maximum 0.743 10.000 11.866 1.000 1.000

Mean 0.248 8.343 3.094 0.124 0.667

Range 0.740 9.000 11.832 0.999 0.953

Variation 0.054 7.829 4.762 0.031 0.094

Standard Deviation 0.233 2.798 2.182 0.176 0.306

Skewness 0.631 -1.466 2.198 4.619 -0.536

Kurtosis 2.039 3.686 10.455 23.191 1.878

Coefficient
93.757 33.537 70.533 142.764 45.878
of variation

Table 2—Statistical parameters for the case of fishbone multilateral well.

Parameter Kh/kv No. of laterals Length Distance Pwf Q

Minimum 1 2 700 1300 14.7 0

Maximum 1000 14 3100 5200 4800 197903.226

Mean 61 6.667 2759.523 2723.809 2359.558 81860.474

Range 999 12 2400 3900 4785.3 197903.226

Variation 44637.13 6.247 480387.023 469391. 2407890 2372909235

Standard
211.275 2.499 693.099 685.121 1551.738 48712.516
Deviation

Skewness 4.192 1.412 -1.9159 2.0689 0.09535 -0.118

Kurtosis 18.73 5.358 5.3081 9.503 1.7184 2.216

Coefficient
346.352 37.491 25.116 25.153 65.763 59.507
of variation
IPTC-19706-Abstract 5

Downloaded from http://onepetro.org/IPTCONF/proceedings-pdf/20IPTC/2-20IPTC/D023S171R002/1188294/iptc-19706-abstract.pdf by Universidad Nacional De Colombia user on 11 September 2023

Figure 2—The relative importance of production rate with input
parameters used for case of the hydraulically fractured horizontal well.

Figure 3—The relative importance of production rate with input parameters used to train the ANN model, for the fishbone well.

Results and Discussion

Artificial neural network (ANN) was used to develop a predictive model for determining the productivity
of hydraulically fractured horizontal and fishbone multilateral wells. The optimum predictive model was
defined based on the prediction error and the match between the actual and predicted values. Average
absolute percentage error (AAPE) was used to represent the prediction error, and correlation coefficient
(R-value) was used to assess the match between the actual and predicted values. Thereafter, the best ANN
structure was defined in term of number of hidden layers and number of neurons per each layer.

Hydraulically Fractured Horizontal Well

The best ANN model for predicting the productivity of hydraulically fractured horizontal well is consist of
one hidden layer with 4 neurons per each layer. The correlation coefficient (R-value) is 0.995 and the average
error (AAPE) is 6.82%, while for the unseen data (testing data) the R-value and AAPE are 0.993 and 8.39%,
6 IPTC-19706-Abstract

respectively. The values of correlation coefficient and average error indicates the good performance of the
ANN model in determining the production rate for case of hydraulically fractured horizontal well. Figure
4 illustrates the performance of neural network model for predicating the productivity of hydraulically
fractured horizontal well. In general, the error profile for the validation data (green curve) is higher than
that of the training data (blue curve) while indicates that no model memorization was occurred for this ANN

Downloaded from http://onepetro.org/IPTCONF/proceedings-pdf/20IPTC/2-20IPTC/D023S171R002/1188294/iptc-19706-abstract.pdf by Universidad Nacional De Colombia user on 11 September 2023

model. The best epoch number was found to be 6 and the mean squared error (MSE) is around 0.00132.
Figure 5 and 6 show the predicted and actual flow rate, for the hydraulically fractured horizontal well, for
training and testing data sets, respectively.

Figure 4—Performance of ANN model for predicating the productivity of hydraulically fractured
horizontal well. The best epoch number is 6 with mean squared error (MSE) of 0.00132.

Figure 5—a cross plot between the actual and predicted flow rate for the hydraulically fractured
horizontal well. The average absolute error is 6.82% and the R-value is 0.995 training data.
IPTC-19706-Abstract 7

Downloaded from http://onepetro.org/IPTCONF/proceedings-pdf/20IPTC/2-20IPTC/D023S171R002/1188294/iptc-19706-abstract.pdf by Universidad Nacional De Colombia user on 11 September 2023

Figure 6—The actual and predicted flow rates for the hydraulically fractured horizontal
well. For the testing data, the average absolute error and the R-value are 8.39% and 0.993.

Fishbone Multilateral Well

The productivity of fishbone well was determined using artificial neural network. The well geometry and
the reservoir parameters were used to estimate the production rate. The input parameters are the flowing
bottomhole pressure, the lateral specification and the permeability ratio. The best ANN model to determine
the fishbone production is consist of one hidden layer and 20 neurons per layer. Figure 7 shows the
performance of the developed ANN model; the best validation performance is 0.0036 at epoch of 4. Also,
the error profiles for the training and validation data sets confirm that no memorization issues are associated
with this model, since the validation error is higher than the training error. Moreover, the predicted flow
rates are plotted against the actual flow rate for the training and testing data as shown in Figures 8 and 9,
respectively. For training data set, the average error (AAPE) is 11.63% and the R-value is 0.987. While, the
AAPE and the R-value are 6.36% and 0.995, respectively, for the unseen data.

Figure 7—Error profiles for the training and testing data during the predication of the
fishbone productivity. The best epoch number is 4 with mean squared error (MSE) of 0.0036.
8 IPTC-19706-Abstract

Downloaded from http://onepetro.org/IPTCONF/proceedings-pdf/20IPTC/2-20IPTC/D023S171R002/1188294/iptc-19706-abstract.pdf by Universidad Nacional De Colombia user on 11 September 2023

Figure 8—Cross plot between the actual and predicted flow rate for the fishbone multilateral
well. The average absolute error is 11.63% and the R-value is 0.987 training data.

Figure 9—Cross plot between the actual and predicted flow rate for the fishbone multilateral
well. For the testing data, the average absolute error and the R-value are 6.36% and 0.995.

Comparison Analysis
Figure 10 shows the predicted and actual flow rate for fishbone and hydraulically fractured horizontal wells.
The flow rate for both wells showed a good aligned around the 45° line indicating the effective prediction
performance for the developed ANN models. Also, it was observed than the match between the actual and
predicted values become better to higher flow rates. Furthermore, the relationship between the prediction
performance and the flowing bottomhole pressure was studied. Figure 11 shows the error profiles against
IPTC-19706-Abstract 9

the dimensionless pressure. Increasing the flowing pressure can lead to increase the prediction error for both
wells. However, at same pressure, higher error was observed for the prediction of hydraulically fractured
horizontal well compared to the fishbone well.

Downloaded from http://onepetro.org/IPTCONF/proceedings-pdf/20IPTC/2-20IPTC/D023S171R002/1188294/iptc-19706-abstract.pdf by Universidad Nacional De Colombia user on 11 September 2023

Figure 10—Cross plot for the actual and the predicted flow rate for the
fishbone (FB) and the hydraulically fractured horizontal (HZHF) well.

Figure 11—Average percentage error against the dimensionless pressure for the fishbone and
hydraulically fractured horizontal wells, Higher error was observed at higher flowing pressure.
10 IPTC-19706-Abstract

Empirical Correlations
In order to convert the ANN model from black box into a white box, empirical correlations were extracted
from the optimized ANN models. The extracted correlations can provide a direct method for determining
the well productivity. The weights (w) and biases (b) of the neural network model were utilized to derive
the empirical correlations. For the hydraulically fractured horizontal well, the empirical correlation is given

Downloaded from http://onepetro.org/IPTCONF/proceedings-pdf/20IPTC/2-20IPTC/D023S171R002/1188294/iptc-19706-abstract.pdf by Universidad Nacional De Colombia user on 11 September 2023

as following;

(1)

(2)

For the fishbone multilateral well, the empirical equation is given as;

(3)

Where, QD is the dimensionless flow rate, PD is the dimensionless pressure, n is the number of fractures,
CfD is the dimensionless fracture conductivity, L is the lateral length and Kv/Kh is the permeability ratio.
The values of weights and biases of hidden and output layers are summarized in Table 3 and 4 for the
hydraulically fractured horizontal and fishbone multilateral wells, respectively.

Table 3—The values of weights and biases for hydraulically fractured horizontal well.

Weights for the Hidden Layer (W1) Weights for

Neuron Bias for the Bias for the
the Output
Index PD n CFD Kv/Kh Hidden layer (b1) Output Layer (b2)
Layer (W2)

1 -1.1713 0.2589 -0.3738 1.9617 -0.8833 -1.5890

2 -0.7215 -0.7507 -0.2223 -0.2491 0.5667 1.5052

0.8742
3 -0.9324 0.4620 0.1368 0.1467 0.4938 -0.6357

4 0.2172 0.3873 1.0893 -0.0781 0.8527 -1.3861

Table 4—The values of weights and biases for the fishbone multilateral well.

Weights for the Bias for

Neuron Hidden Layer (W1) Weights for the Bias for the
the Output
Index Output Layer (W2) Hidden layer (b1)
Kh/Kv Length Pwf Layer (b2)

1 -3.84692 0.617902 -2.26283 -2.819227146 0.752135

2 3.358502 -2.56259 -1.34471 -2.498195347 0.232057

3 3.162647 -3.3314 1.433747 -0.682675154 0.430348

4 2.595679 -3.26074 -1.83961 0.666775968 -0.9063

5 -2.19077 2.3777 1.716382 -2.423948008 0.130544 -0.28498

6 -1.74031 2.608322 2.778165 -0.581621184 0.281862

7 1.455491 -2.75341 -2.49005 0.699240526 -0.74851

8 -1.01596 1.755128 1.831094 -2.721731367 -0.23775

9 -0.51291 2.085212 1.655426 -2.701708506 -0.15973

IPTC-19706-Abstract 11

Weights for the Bias for

Neuron Hidden Layer (W1) Weights for the Bias for the
the Output
Index Output Layer (W2) Hidden layer (b1)
Kh/Kv Length Pwf Layer (b2)

10 -0.30873 3.380575 -1.66117 0.602113511 0.173508

11 0.169321 -1.10784 -3.44826 -1.33129177 0.285198

Downloaded from http://onepetro.org/IPTCONF/proceedings-pdf/20IPTC/2-20IPTC/D023S171R002/1188294/iptc-19706-abstract.pdf by Universidad Nacional De Colombia user on 11 September 2023

12 -0.35496 -1.95086 -2.1071 2.340221069 -0.05304

13 1.08924 2.348532 1.9611 -2.136881713 0.191233

14 1.407857 0.420195 2.554844 2.696650854 0.15787

15 -1.74964 -1.27965 -0.31507 3.224532039 -0.16893

16 -2.24378 -1.25899 1.524934 -3.236788256 -0.11517

17 -2.61158 -2.64587 -2.30505 1.377837678 -0.07059

18 3.316892 3.350453 0.264872 -1.109735463 -0.12635

19 3.298386 1.357587 -3.4066 -0.837658734 0.641118

20 3.717023 0.598516 -3.12083 1.403728747 0.227681

Conclusions
This paper presents effective models to quantify the productivity of complex wells using artificial
intelligence technique. The production rates for hydraulically fractured horizontal well and fishbone
multilateral well were determined using artificial neural network (ANN). The reservoir properties and the
well configurations were used to estimate the well performances. The developed models can determine
the well production without introducing the complexity associated with the numerical approaches. Average
absolute percentage error (AAPE) and correlation coefficient were used to select the best ANN models.
The developed models can determine the flow rate for hydraulically fractured horizontal and fishbone
multilateral wells with average errors of 8.39% and 6.36%, respectively, and correlation coefficients higher
than 0.99 for both wells. Moreover, empirical correlations were extracted from the optimized ANN models.
The extracted correlations can provide a direct and simple approach to calculate the well productivity.
The proposed equations can be inserted into the commercial software to allow better prediction for the
productivity of complex well such as hydraulically fractured horizontal and fishbone multilateral wells.

Acknowledgement
Authors would like to acknowledge College of Petroleum and Geosciences (CPG), at King Fahd University
of Petroleum and Minerals (KFUPM) for the technical supports and permission to publish this paper.

References
Abdalla, M., Hassan, A., Abdulraheem, A., Elkatatny, S. and Mohamed, A., 2018, January. New Technique to Evaluate the
Performance of Hydraulically Fractured Horizontal Wells. In SPE/IADC Middle East Drilling Technology Conference
and Exhibition. Society of Petroleum Engineers.
Ahmed, M. E., Alnuaim, S. and Abdulazeem, A. New Algorithm to Quantify Productivity of Fishbone Type Multilateral
Gas Well. SPE-181888-MS, presented at the SPE Annual Technical Conference and Exhibition held in Dubai, UAE,
2016, 26-28 September.
AlAjmi, M. D., Alarifi, S. A., Mahsoon, A. H. Improving Multiphase Choke Performance Prediction and Well Production
Test Validation Using Artificial Intelligence: A New Milestone. SPE-173394-MS, presented at the SPE Digital Energy
Conference and Exhibition, held in The Woodlands, Texas, USA, 2015, 3-5 March.
Alarifi, S. A., AlNuaim, S., Abdulraheem, A. Productivity Index Prediction for Oil Horizontal Wells Using Different
Artificial Intelligence Techniques. SPE-172729-MS, presented at the SPE Middle East Oil & Gas Show and
Conference, held in Manama, Bahrain, 2015, 8-11 March.
12 IPTC-19706-Abstract

Al-Mashhad A. S., Al-Arifi S. A., Al-Kadem M. S., Al-Dabbous M. S., Buhulaigah A. Multilateral Wells Evaluation
Utilizing Artificial Intelligence. SPE-183508-MS, presented at the Abu Dhabi International Petroleum Exhibition and
Conference held in Abu Dhabi, UAE, 2016, 7–10 November.
Borisov, Ju. P. Oil Production using Horizontal and multiple deviation wells. J. strauss, Trans. And S.D Joshi, Ed., Phillips
Petroleum Co. Bartlesville, 1984.
Bosworth, X., El-Sayed, H.S., Ismail, G., Ohmer, H., Stracke, M., West, C., Retnanto, A. Key Issues in Multilateral

Downloaded from http://onepetro.org/IPTCONF/proceedings-pdf/20IPTC/2-20IPTC/D023S171R002/1188294/iptc-19706-abstract.pdf by Universidad Nacional De Colombia user on 11 September 2023

Technology. Oilfield Review, 1998, 10(4): 14–28.
Chen F., Duan Y., Zhang J., Wang k., Wang W. Application of neural network and fuzzy mathematic theory in evaluating
the adaptability of inflow control device in horizontal well. Journal of Petroleum Science and Engineering 134,2015,
131–142.
Ding, Z., Liu, Y., Gong, Y., and Xu, N. A new technique: Fishbone well injection. Petroleum Science and Technology,
2012, 30 (23): 2488–2493. http://dx.doi.org/10.1080/10916466.2010.518196.
Economides, M.J., Hill, A.D., and Economides, C. Petroleum Production Systems. Prentice Hall PTR, New Jersey, 1994.
Filho, J.C. Yifei Xu, and Sepehrnoori, K. Modeling Fishbones Using the Embedded Discrete Fracture Model Formulation:
Sensitivity Analysis and History Matching. SPE-175124-MS presented at the SPE Annual Technical Conference and
Exhibition, held in Houston, Texas, USA, 2015, 28–30 September.
Freyer, R. and Shaoul, J. R. Laterals stimulation method. In Brasil Offshore Conference and Exhibition, Macae, Brazil.
Society of Petroleum Engineers. SPE-143381-MS, 2011. http://dx.doi.org/10.2118/143381-MS.
Furui, K., Zhu, D., Hill, A. D. A Comprehensive Model of Horizontal Well Completion Performance. Paper SPE 84401
presented at the SPE Annual Technical Conference and Exhibition, Denver, Colorado, 2003, 5-8 October.
Guangyu X., Guo F., Cheng S., Sun Y., Yu J., Wang G. Fishbone Well Drilling and Completion Technology in Ultra-Thin
Reservoir. Paper IADC/SPE 155958 presented at the IADC/SPE Asia Pacific Drilling Technology Conference and
Exhibition held in Tianjin, China, 2012, 9–11 July.
Guo, B., Sun, K. and Ghalambor. Well Productivity Hand Book. Gulf Publishing Company, Houston, Texas. 2008,
226–230.
Hassan, A., Abdulraheem, A., Elkatatny, S. and Ahmed, M., 2017, October. New approach to quantify productivity of
fishbone multilateral well. In SPE Annual Technical Conference and Exhibition. Society of Petroleum Engineers.
Jessica, L., 2015, Conventional Vs. Unconventional oil wells, https://www.croftsystems.net/oil-gas-blog/conventional-
vs.-unconventional (access on 31 October 2019)
Karakas, M. and Ayan, C., 1991, January. Productivity and coning behavior of phased horizontal completions. In SPE
Annual Technical Conference and Exhibition. Society of Petroleum Engineers.
Yildiz, T. Multilateral Horizontal Well Productivity. Paper SPE 94223 presented at SPE Europec/EAGE Annual
Conference held in Madrid, Spain, 2005, 13-16 June.
Yu Xiance, Boyun Guo, Chi Ai, Zhidan Bu. A comparison between multi-fractured horizontal and fishbone wells for
development of low-permeability fields. Paper SPE 120579 presented at Asia Pacific Oil and Gas Conference and
Exhibition, held in Jakarta, Indonesia, 2009, 4-6 August.