Abstract
Due to many reasons, in many occasions, reservoir engineers should analyze the reservoirs with small sets of measurements; this problem is known as the small sample size problem. Because of small sample size problem, modeling techniques commonly fail to accurately extract the true relationships between the inputs and the outputs used for reservoir properties prediction or modeling. In this paper, small sample size problem is addressed for modeling carbonate reservoirs by the active learning method (ALM). In this paper, noise injection technique, which is a popular solution to small sample size problem, is employed to recover the impact of separating the validation and test sets from the entire sample set in the process of ALM. The proposed method is used to model hydraulic flow units (HFUs) . HFUs are defined as correlatable and mappable zones within a reservoir which control fluid flow. This study presents quantitative formulation between flow units and well logs data in one of the heterogeneous carbonate reservoir in Persian Gulf. The results for R and nMSE are equal to 85 % and 0.0042 which reflect the ability of the proposed method when facing with sample size problem.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bahrpeyma F, Golchin B, Cranganu C (2013) Fast fuzzy modeling method to estimate missing logs in hydrocarbon reservoirs. J Pet Sci Eng 112:310–321
David RL, Gregory JM (1999) Evaluating the use of goodness-of-fit measures in hydrologic and hydroclimatic model validation. Water Resour Res 35(1):233–241
Ebanks W (1987) Flow unit concept-integrated approach to reservoir description for engineering projects. AAPG Meet Abstr 1(5):521–522
Ghiasi-Freez J, Kadkhodaie-Ilkhchi A, Ziaii M (2012) Improving the accuracy of flow units prediction through two committee machines, South Pars Gas Field, Persian Gulf Basin, Iran. Comput Geosci 46:10–23
Jude OA, Altunbay M, Tiab D, Kersey DG, Keelan DK (1993) Enhanced reservoir description: using core and log data to identify hydraulic (flow) units and predict permeability in uncored intervals/wells. In: 68th annual technical conference and exhibition, Houston
Kadkhodaie-Ilkhchi A, Amini A (2009) A fuzzy logic approach to estimating hydraulic flow units from well log data: a case study from the Ahwazoil field, South Iran. J Pet Geol 32(1):67–78
Liu YS, Janusz AZ (2008) Optimized approximation algorithm in neural networks without overfitting. IEEE Trans Neural Netw 19:983–995
Piotrowski AP, Napiorkowski JJ (2013) A comparison of methods to avoid overfitting in neural networks training in the case of catchment runoff modelling. J Hydrol 476:97–111
Raudys S (2003) Experts’ boasting in trainable fusion rules. IEEE Trans Pattern Anal Mach Intell 25:1178–1182
Raudys S (2006) Trainable fusion rules. II. Small sample-size effects. Neural Netw 19:1517–1527
Rifai S, Glorot X, Bengio Y, Vincent P (2011) Adding noise to the input of a model trained with a regularized objective. Technical report dept. IRO, Universite de Montreal. Montreal (QC), H3C 3J7, Canada
Rynkiewicz J (2012) General bound of overfitting for MLP regression models. Neurocomputing 90:106–110
Saeed Bagheri S, Honda N (1997) A new method for establishment and saving fuzzy membership functions. In: 13th fuzzy symposium, Toyama, Japan 1997, pp 91–94
Saeed Bagheri S, Honda N (1999) Recursive fuzzy modeling based on fuzzy interpolation. J Adv Comput Intell 3:114–125
Schittenkopf C, Deco G, Brauer W (1997) Two strategies to avoid overfitting in feedforward networks. Neural Netw 10:505–516
Shouraki SB (2000) A novel fuzzy approach to modeling and control and its hardware implementation based on brain functionality and specification. The University of Electro-Communication, Chofu-Tokyo
Skurichina M, Raudys S, Duin RPW (2000) K-nearest neighbors directed noise injection in multilayer perceptron training. IEEE Trans Neural Netw 11:504–511
Yulei Jiang RMZ, Lorenzo LP, Karen D (2009) A study of the effect of noise injection on the training of artificial neural networks. In: Proceedings of international joint conference on neural networks, Atlanta, Georgia, USA
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Bahrpeyma, F., Cranganu, C., Golchin, B. (2015). Improving the Accuracy of Active Learning Method via Noise Injection for Estimating Hydraulic Flow Units: An Example from a Heterogeneous Carbonate Reservoir. In: Cranganu, C., Luchian, H., Breaban, M. (eds) Artificial Intelligent Approaches in Petroleum Geosciences. Springer, Cham. https://doi.org/10.1007/978-3-319-16531-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-16531-8_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16530-1
Online ISBN: 978-3-319-16531-8
eBook Packages: EnergyEnergy (R0)