Search

Petrophysical properties including volume of shale, porosity and water saturation are significance parameters for petroleum companies in evaluating the reservoirs and determining the hydrocarbon zones. These can be achieved through conventional petrophysical calculations from the well logs data such as gamma ray, sonic, neutron, density and deep resistivity. The well logging operations of the targeted limestone Mishrif reservoirs in Ns-X Well, Nasiriya Oilfield, south of Iraq could not be done due to some problems related to the well condition. The gamma ray log was the only recorded log through the cased borehole. Therefore, evaluating the reservoirs and estimating the perforation zones has not performed and the drilled well was abandoned. This paper presents a solution to estimate the missing openhole logs of Mishrif Formation including sonic, neutron, density and deep resistivity using supervised Artificial Neural Network (ANN) in Petrel software (2016.2). Furthermore, the original gamma-ray log along with the predicted logs data from ANN models were processed, and the petrophysical properties including volume of shale, effective porosity and water saturation were calculated to determine the hydrocarbon zones. The ANN Mishrif Formation models recorded coefficient of determination (R²) of 0.65, 0.77, 0.82, and 0.04 between the predicted and the tested logs data with total correlations of 0.67, 0.91, 0.84 and 0.57 for sonic, neutron, density, and resistivity logs respectively. The best possible hydrocarbon-bearing zone ranges from the depth of about 1980-2030 m in the mB1unit. The ANN provides a good accuracy and data matching in clean and non-heterogeneous formations compared to those with higher heterogeneity that contain more than one type of lithology. The Ns-X Well can, therefore, be linked to the development plans of the Nasiriya Field instead of neglect it. [ABSTRACT FROM AUTHOR]

This work focuses on the problem of constructing accurate prediction models using an adaptive neuro-fuzzy inference system (ANFIS) from data that are scarce and poorly scaled. Many real-world problems have limited data to work with and yet require models with high prediction accuracy. Due to the fuzzy nature of many data sets, it is appropriate to construct prediction models using fuzzy inference systems (FIS), rather than traditional artificial neural network (ANN) models. However, the scarcity of the data raises serious concerns when attempting to construct models of this type. In this paper, we address the problem of constructing accurate prediction models using ANFIS in circumstances where capturing large amounts of data is difficult. We propose a new approach, using robust data expansion methods to enhance the data carefully. This approach provides the learning algorithm with enough representative data to allow all of the parameters (premise and consequent) to be optimised. We compare and contrast the effectiveness in reducing prediction error for three specific expansion models using radial basis function (RBF) kernels. When expanding data, for which the underlying smoothness properties are not known, there is often a danger of over-smoothing. This is usually noticeable at turning points and can occur when fitting the data using polynomials or cubic splines for example. To avoid over-smoothing, we introduce a modified multiquadric approach that allows smooth, near-interpolation while maintaining the desirable shape-preserving properties of the data. The proposed method is explained through two case studies — the first to predict gasoline consumption for the oil/fuel industry in Iraq and the second for predicting natural gas consumption in Iran. This is the first study that uses adjustable, shape-preserving re-sampling methods for optimising ANFIS models in low data environments. • ANFIS networks capture complexities not easily found using traditional ANNs. • Model complexity versus data sample size is a significant practical problem. • Data augmentation methods can be constructed using robust continuous models. • Multiquadric RBFs can be easily tuned to provide robust, accurate data expansion. • Complex models can be built with confidence using reliable data expansion. [ABSTRACT FROM AUTHOR]