Permeability Prediction Using Hydraulic Flow Units And Hybrid Soft Computing Systems R. Soto B.; R. Soto B. ECOPETROL-ICP Search for other works by this author on: This Site Google Scholar J.C. Garcia; J.C. Garcia ECOPETROL-ICP Search for other works by this author on: This Site Google Scholar F. Torres; F. Torres American Geoexploration Search for other works by this author on: This Site Google Scholar G.S. Perez G.S. Perez American Geoexploration Search for other works by this author on: This Site Google Scholar Paper presented at the SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, September 2001. Paper Number: SPE-71455-MS https://doi.org/10.2118/71455-MS Published: September 30 2001 Cite View This Citation Add to Citation Manager Share Icon Share Twitter LinkedIn Get Permissions Search Site Citation Soto B., R., Garcia, J.C., Torres, F., and G.S. Perez. "Permeability Prediction Using Hydraulic Flow Units And Hybrid Soft Computing Systems." Paper presented at the SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, September 2001. doi: https://doi.org/10.2118/71455-MS Download citation file: Ris (Zotero) Reference Manager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex Search nav search search input Search input auto suggest search filter All ContentAll ProceedingsSociety of Petroleum Engineers (SPE)SPE Annual Technical Conference and Exhibition Search Advanced Search AbstractIn the last years, the concept of hydraulic flow units (HFU) has been used in the petroleum industry to improve prediction of permeability in uncored interval/wells. This concept is strongly related to the flow zone indicator (FZI) which is a function of the reservoir quality index (RQI). Both measures are based on porosity and permeability of cores. It is assumed that samples with similar FZI values belong to the same HFU. Thus the FZI, along with other significant variables such as porosity, can be used directly to estimate the permeability in a zone; however, the FZI has to be estimated first. In this paper, a novel method based on hybrid soft computing techniques is used for permeability predictions. The technique is known as adaptive network-based fuzzy inference systems or ANFIS, and is based on adaptive neural networks and fuzzy inference systems (FIS). The final inference on FZI is made by a FIS but the parameters of this FIS will be estimated through a learning procedure based on input data; such procedure is typically used in neural network training. The technique is applied in 3 steps:Identification of the dominant variables in rock type behavior,Development of an ANFIS which best suits the real model, using the dominant variables as input and the FZI as output.Estimation of permeability from FZI and porosity values.These steps are applied on a sample case and the results show that hybrid soft computing techniques offer powerful tools for further improving permeability predictions.IntroductionPermeability (a measure of fluid conductivity in porous media) is a critical parameter in models for reservoir characterization, reserve estimation and production forecast. Estimation of permeability in a heterogeneous reservoir is a very complex task; a poorly estimated permeability will make the model inaccurate and unreliable, thus, affecting the degree of success of many oil and gas operations based on such models.Big efforts have been made by many researchers in order to establish a complex mathematical function which relates permeability to other reservoir characteristics1,2. These studies have helped understanding the factors controlling permeability but have not provided an accurate estimation of permeability. The internal processes inside a reservoir correspond to complex physical phenomena where many factors are interacting. Definition of an exact expression for each one of these factors as a function of others is an impossible task. The best that can be done is approximate methods which somehow give a hint about the permeability distribution in the reservoir.One of the first practices was finding correlations between permeability and other reservoir characteristics such as porosity, or well logs. Samples extracted from cored wells were used in laboratory to find values of permeability and porosity; likewise, logs were taken in the same wells. Correlations were obtained from permeability vs. porosity plots or from functional transformation on the well logs, wherever enough information existed. These correlations were extrapolated to wells where little or no information was available. In order for this method to work, a high amount of reservoir representative samples were required, something expensive to achieve. Besides, when heterogeneity of well is high, these correlations become unreliable3.Another traditional method was the development of simple transfer functions, which try to match permeability values adjusting the function parameters. In many cases, these equations have a poor performance and oversimplify the natural complexity of reservoir data. Statistical multivariate techniques arise as a better choice, providing a potential solution through regression analysis. These technique offers appealing solutions; however, its main drawback is the need to exhaustively identify all the factors affecting permeability, and then, establish a linear or non-linear model which best represent interactions among such factors. Keywords: spe 71455, porosity, core data, permeability prediction, anfis, upstream oil & gas, fuzzy inference system, information, fzi, reservoir Subjects: Information Management and Systems, Artificial intelligence This content is only available via PDF. 2001. Society of Petroleum Engineers You can access this article if you purchase or spend a download.