R. Gholami; A. Moradzadeh
Abstract
Reservoir permeability is a critical parameter for characterization of the hydrocarbon reservoirs. In fact, determination of permeability is a crucial task in reserve estimation, production and development. Traditional methods for permeability prediction are well log and core data analysis which are ...
Read More
Reservoir permeability is a critical parameter for characterization of the hydrocarbon reservoirs. In fact, determination of permeability is a crucial task in reserve estimation, production and development. Traditional methods for permeability prediction are well log and core data analysis which are very expensive and time-consuming. Well log data is an alternative approach for prediction of permeability because they are usually available for all of the wells. Hence, attempts have been made to utilize well log data to predict permeability. However, because of complicate and non-linear relationship of well log and core permeability data, usual statistical and artificial methods are not completely able to provide meaningful results. In this regard, recent works on artificial intelligence have led to the introduction of a robust method generally called support vector machine (SVM). The term “SVM” is divided into two subcategories: support vector classifier (SVC) and support vector regression (SVR). The aim of this paper is to use SVR for predicting the permeability of three gas wells in South Pars filed, Iran. The results show that the overall correlation coefficient (R) between predicted and measured permeability of SVR is 0.97 compared to 0.71 of a developed general regression neural network. In addition, the strength and efficiency of SVR was proved by less time-consuming and better root mean square error in training and testing dataset.
A. R. Arab-Amiri; A. Moradzadeh; N. Fathianpour; B. Siemon
Abstract
Helicopter-borne frequency-domain electromagnetic (HEM) surveys are used extensively for mineral and groundwater
exploration and a number of environmental investigations. To have a meaningful interpretation of the measured multi-
frequency HEM data, in addition to the resistivity maps which are ...
Read More
Helicopter-borne frequency-domain electromagnetic (HEM) surveys are used extensively for mineral and groundwater
exploration and a number of environmental investigations. To have a meaningful interpretation of the measured multi-
frequency HEM data, in addition to the resistivity maps which are provided in each frequency or for some particular
depth levels, it is a necessity to have a suitable modeling technique to produce resistivity cross-section along some
specific profiles. This paper aims to: (1) develop a new inversion method to handle HEM data; (2) compare its results
with the well known Amplitude, Niblett-Bostick (NB), and Siemon inversion methods. The basic formulation of this
new inversion routine was provided based on the Zonge spatial filtering procedure to cure static shift effect on the
magnetotelluric (MT) apparent resistivity curves. When the relevant formulas and the required algorithm for the inverse
modeling of HEM data were provided, they were then coded in Matlab software environment. This new inversion
program, named as SUTHEM, was used to invert some sets of one and two dimensional (1D and 2D) model synthetic
data which were contaminated by random noise. It was also applied to invert one set of real field data acquired in the
NW part of Iran by the DIGHEM system. The obtained results of this method and their comparison with those of the
aforementioned methods indicate that SUTHEM is able to produce the results like those produced by the commercial
Siemon routine. In addition, the new inversion method is superior to the Amplitude and the NB methods particularly in
inversion of the noisy data.
