This study discusses and compares, from a practical point of view, three different approaches for permeability determination from logs. These are empirical, statistical, and the recently introduced "virtual measurement" methods. They respectively make use of empirically determined models, multiple variable regression, and artificial neural networks. All three methods are applied to well log data from a heterogeneous formation and the results are compared with core permeability, which is considered to be the standard.In this first part of the paper we present only the model development phase in which we are testing the capability of each method to match the presented data. Based on this, the best two methods are to be analyzed in tenns of prediction performance in the second part of this paper.
Permeability is one of the most important characteristics of hydrocarbon bearing formations. An accurate knowledge of permeability gives petroleum engineers a tool for efficiently managing the production process of a field. It is also one of the most important pieces of information in the design and management of enhanced recovery operations. Formation permeability is often measured in the laboratory from cores or evaluated from well test data. Core analysis and well test data, however, are only available from a few wells in afield. On the other hand, almost all wells are logged.
In this study an artificial neural network has been designed that is able to predict the permeability of the formations using the data provided by geophysical well logs with good accuracy. Artificial neural network, a biologically inspired computing method, with its ability to learn, self-adjust, and be trained provide a powerful tool to solve problems that involve pattern recognition.
Using well logs to predict permeability has been attempted in the past. The problems with previous approaches were mainly two fold, namely, the number of variables used (only one variable-porosity), and using regression analysis as the main tool for correlations. The approach introduced in this paper is an attempt to overcome these short comings. This is done, first, by using many variables from well logs that may provide information about the permeability. Second, by recognizing the existence of possible patterns between these variables and formation permeability using artificial neural networks. Neuralnets are analog, inherently parallel and distributive systems. These characteristics, which will be discussed in the paper, are the main characteristics that enable artificial neural networks to be successful in predicting the permeability in rocks using well log information.
Introduction
Acquiring knowledge on formation permeability has remained one of the fundamental challenges to petroleum engineers.
We discuss and compare three different approaches for permeability determination from logs from a practical point of view. The three methods, empirical, statistical, and the recently introduced "virtual measurement," make use of empirically determined models, multiple variable regression, and artificial neural networks, respectively. We apply all three methods to well log data from a heterogeneous formation and compare the results with core permeability, which is considered to be the standard. Our comparison focuses on the predictive power of each method.
TX 75083-3836, U.S.A., fax 01-972-952-9435.
AbstractCoalbed Methane (CBM) currently accounts for nearly 8 percent of U.S. annual gas production and approximately 12 percent of estimated total U.S. natural gas reserves. Coalbed methane proven reserves in the United States have increased from 3.7 Tcf in 1989 to 18.5 Tcf in 2002. This number is expected to increase even further as more resources are discovered and a better understanding of the existing resources is achieved. Appalachian Basin accounts about 10 percent of U.S. CBM resources. However, CBM production is very limited in the Appalachian Basin. The contribution of CBM to overall mix of natural gas sources in U.S. is expected to increase for next two decades. However, this cannot be achieved without substantial increase in CBM production in the Appalachian Basin. The problems causing the lag in development of CBM in the Appalachian Basin need to be overcome for CBM to reach its true potential in the U.S. energy equation.Gas production from CBM reservoirs is governed by complex interaction of single-phase gas diffusion through micro-pore system (primary porosity) and two-phase gas and water flow through cleat system (secondary porosity) that are coupled through desorption process. In order to effectively evaluate CBM resources, it necessary to utilize reservoir models that incorporate the unique flow and storage characteristics of CBM reservoirs. These models are often complicated to use, expensive, and time consuming. The typical gas producers in the Appalachian Basin suffer from the lack of scientific, userfriendly tools that can assist them in development of CBM resources. Therefore, it is necessary to develop tools that make it possible for typical (small to medium size) producers to seriously consider this important resource.This study presents a set of production type curves that would help the producers to predict the production from their CBM wells. As a consequence, the producers would be able to make better, more informed decisions regarding the CBM resources in the region. A reservoir model that incorporates the unique flow and storage characteristics of Coalbed Methane reservoirs was employed in this study to develop the type curves. The type curves provide a reliable tool to predict the production performance of CBM reservoirs both during dewatering and stable gas production phases. The application and issues concerning the production performance of CBM reservoirs are also discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.