Browsing by Author "Aliouane, Leila"

Filter results by typing the first few letters
Now showing 1 - 20 of 60
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Aeoromagnetic data analysis using the 2D continuous wavelet transform
    (2011) Aliouane, Leila; Ouadfeul, Sid-Ali; Boudella, Amar
  • No Thumbnail Available
    Item
    Aeromagnetic data analysis using the 2D directional continuous wavelet transform (DCWT)
    (Springer, 2013) Ouadfeul, Sid-Ali; Hamoudi, Mohamed; Aliouane, Leila; Eladj, Said
  • No Thumbnail Available
    Item
    Application of local optimisation with Steepest Ascent Algorithm for the residual static corrections in a southern Algeria geophysical survey
    (2022) Bansir, Fateh; Eladj, S.; Harrouchi, Lakhdar; Doghmane, M. Z.; Aliouane, Leila
    Static corrections in the seismic data processing sequence are one of the most sensitive steps in seismic exploration undertaken in areas with complex topography and geology. Using the stack energy as an objective function for the inversion problem, static corrections can be performed without using the cross-correlation of all traces of a Common Depth Point (CDP) with all other CDP traces. This step is a time-consuming operation and requires huge computer memory capacities. The pre-calculation step of the crosscorrelation table can provide greater processing efficiency in practice; by either a local optimisation algorithm such as Steepest Ascent applied to the traces, or a global search method such as genetic algorithms. The sudden change of the topography and the signal/ noise (S/N) ratio decrease can cause failure in residual static (RS) corrections operations; consequently, it may lead to poor quality of the seismic section. In this study, we firstly created a synthetic seismic section (synthetic stack), which describes a geological model. Then, the Steepest Ascent Algorithm (SAA) method is used to estimate RS corrections and evaluate its performance, in order that the encountered problems in the field will be overcome. The generated synthetic stack, with a two-layer tabular geological model, has been disturbed by introducing wrong static corrections and random noise. Thus, the model became a noised stack with low S/N ratio and poor synthetic horizons continuity. After 110 iterations, the SAA estimated the appropriate corrections and eliminated disturbances introduced earlier. Moreover, it improves the quality of the stack and the continuity of synthetic horizons. Therefore, we have applied this algorithm using the same methodology for calculating the RS corrections of real data of seismic prospection in southern Algeria; the input data has poor quality caused by near-surface anomalies. We found that our proposed methodology has improved the RS corrections in comparison to currently used conventional methods in the seismic processing in Algerian industr
  • No Thumbnail Available
    Item
    Artificial Intelligence Technique in earth sciences for porosity prediction in shaly petroleum reservoir from geophysical well-logs data. Application to Hassi R'mel field, Algeria
    (MEACSE Publication, 2024) Aliouane, Leila; Ouadfeul, Sid-ali
    Machine learning techniques are becoming very popular in earth sciences, mainly in petroleum exploration and exploitation. Reservoir characterization using geophysical well-logs data analysis is commonly conducted and plays a central role in formation evaluation in petroleum domain. The most petrophysical parameters that describe the reservoir are the porosity, the permeability and the water saturation where the porosity is the main key. Using conventional methods, the estimation of the porosity is very difficult, mainly in shaly reservoirs where the presence of clay affects considerably, the porosity and the permeability. For that, we propose to accurately predict the porosity from geophysical recordings crossed the formation of wells using machine learning methods such as multi-layer neural network. The input layer are constituted by the petrophysical well-logs data and the output layer presented by one neuron corresponding to the predicted porosity. The training step of neural network machine (NNM) is processed using core data (CORPOR) by minimizing the root mean square error using Radial Basis Function algorithm (RBF). Once trained, the model is then applied to the target wells to predict porosity (PORRBF). The predicted porosity match the core values with good accuracy. This approach provides significantly a robust computation method and reduces dependency on prior domain knowledge
  • No Thumbnail Available
    Item
    Automatic fault tracking from 3D seismic data using the 2D Continuous Wavelet Transform combined with a Convolutional Neural Network
    (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale, 2024) Ouadfeul, Sid Ali; Aliouane, Leila
    The aim of this work is to propose a new technique for automatic fault tracking from 3D seismic data using the 2D Continuous Wavelet Transform (CWT) method combined with artificial intelligence. Time slices of the variance attribute, derived from the 3D seismic data and chosen by the user, are analysed using the 2D CWT with the 2D Mexican Hat as an analysing wavelet, and the maxima of the modulus of the 2D CWT are mapped for the full range of scales. The ensemble of mapped maxima for the set of time slices is filtered using a Convolutional Neural Network machine. Machine training is performed with a supervised mode using the manually tracked faults as a desired output. Application to real data shows the efficiency and robustness of the proposed method, which can greatly help seismic interpreters in avoiding manual fault tracking, a difficult and time-consuming task.
  • No Thumbnail Available
    Item
    Automatic lithofacies segmentation from well-logs data. A comparative study between the Self-Organizing Map (SOM) and Walsh transform
    (2013) Aliouane, Leila; Ouadfeul, Sid-Ali; Rabhi, Abdessalem; Rouina, Fouzi; Benaissa, Zahia; Boudella, Amar
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    AVO Seismic data inversion using global simultaneous technique
    (2012) Eladj, Said; Ouadfeul, Sid-Ali; Aliouane, Leila; Djarfour, N.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    A comparative study of some Artificial Neural Network models for lithofacies classification from well-logs data
    (2012) Aliouane, Leila; Ouadfeul, Sid-Ali; Djarfour, Nouredine; Boudella, Amar
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Contribution of the seismic anisotropy in the understanding of tight sand reservoirs with an example from the Algerian Sahara
    (Society of Exploration Geophysicists, 2015) Ouadfeul, Sid-Ali; Aliouane, Leila
  • No Thumbnail Available
    Item
    Daily geomagnetic field prediction of intermagnet observatories data using the multilayer perceptron neural network
    (Springer, 2014) Ouadfeul, Sid-Ali; Tourtchine, Victor; Aliouane, Leila
  • No Thumbnail Available
    Item
    Edges detection from aeromagnetic data using the wavelet transform
    (2013) Ouadfeul, Sid-Ali; Aliouane, Leila
  • No Thumbnail Available
    Item
    Fractal analysis based on the continuous wavelet transform and lithofacies classification from well-logs data using the self-organizing map neural network
    (Springer-Verlag, 2013) Aliouane, Leila; Ouadfeul, S.; Boudella, A.
    The main goal of this paper is to show that the fractal analysis based on the continuous wavelet transform is not able to improve lithofacies classification using the self-organizing map (SOM) neural network model from well-logs data. The proposed idea consists to inject many inputs in SOM neural network machines and to choose the best map. These inputs are: data set 1: the five raw well-logs data which are: the gamma ray, density, neutron porosity, photoelectric absorption coefficient and sonic well-log; data set 2: the estimated Hölder exponents using the continuous wavelet transform of the data set 1; data set 3: data set 1 and the three radioactive elements concentrations; data set 4: the estimated Hölder exponents of the data set 1 and the Hölder exponents of the radioactive elements concentrations; data set 5: the estimated Hölder exponents of the data set 1 and the three radioactive elements concentrations logs. Application of the proposed idea at two boreholes located in the Algerian Sahara shows that the Hölder exponents estimated with the continuous wavelet transform as an input of the SOM neural network are not able to give geological details. However, the raw well-logs as an input give more details and precision especially when they are enhanced with the natural gamma ray spectrometry data
  • No Thumbnail Available
    Item
    Fractal behavior of total organic carbon in shale-gas reservoirs with an example from the Barnett Shale, Texas, USA
    (Society of Exploration Geophysicists, 2015) Ouadfeul, Sid-Ali; Aliouane, Leila
    The behavior of fractal analysis using the continuous wavelet transform in shale-gas reservoirs is studied based on estimation of the so-called Hölder exponent by analyzing a total-organiccarbon (TOC) well log using the continuous wavelet transform; the Morlet is the analyzing wavelet. Application to the TOC well-log data of a horizontal well drilled in the Fort Worth Basin, Texas, USA, where the main objective is the lower Barnett Shale, clearly shows no special behavior of the Hölder exponents for known sweet spots. This process can be applied to other well-log data of shale-gas reservoirs to compare results and generalize a rule about the fractal behavior in shale-gas reservoirs
  • No Thumbnail Available
    Item
    Fuzzy clustering algorithm for Lithofacies classification of Ordovician unconventional Tight-sand reservoir from well-logs data (Algerian Sahara)
    (2019) Cherana, Amina; Aliouane, Leila; Doghmane, Mohamed Zinelabidine; Ouadfeul, Sid-Ali
    In this paper we present an approach based on a fuzzy clustering algorithm applied for lithofacies classification in an unconventional tight-sand reservoir from well-logs data. In some cases, these kinds of reservoirs are ra-dioactive due to the presence of non clayey radioactive minerals. However, conventional methods can give bad results. For that, artificial intelligence such as Fuzzy logic, can be suitable to solve the problem. Fuzzy clustering is an unsupervised machine learning technique where a given set of data is classified into groups. Hence, fuzzy logic is a more general logic then classical logic because it does not ignore uncertainties and accepts the implicit consideration of the inherited error associated with any physical measurement. This techniquet has been applied to real data of one well in an unconventional tight-sand reservoir in the Algerian Sahara. Predicted results are compared to lithofacies obtained from conventional methods and spectral mineralogical well-logs data Keywords: Well-log, Unconventional Tight reservoir, Lithofacies, Fuzzy logic, Clustering
  • No Thumbnail Available
    Item
    Geothermal Energy in Algeria and the Contribution of Geophysics
    (MDPI, 2023) Aliouane, Leila; Ouadfeul, Sid-Ali
    Geothermal energy is one of the cleanest, most accessible and cheapest alternative energies in the whole world. It is a renewable energy designating an inexhaustible source at a human scale that can be renewed (energy culture). Geothermal energy comes from the disintegration of radioactive elements present in rocks and the Earth’s core. These generate heat flow to the surface. This heat increases with depth on average by 30 ◦C/km [1]. In Algeria, this gradient varies from 25 ◦C/km in the north to 60 ◦C/km in the south [2]. In 2006, Madlnés published a world map showing the geothermal potential on all continental plates. North Africa has geothermal potential, which explains why many geothermal studies have been carried out in the north of Algeria (Figure 1). Figure 2 shows the geothermal areas in Algeria where the reservoir rocks are the Jurassic limestone in the north and Albian sandstone in the south. This renewable energy is used in multiple areas: fish farming, greenhouse heating or district heat networks, balneotherapy, and electricity production. Currently, only a tiny fraction of the world’s geothermal resources are used. Certain technological improvements and a better recognition of the true value of geothermal energy could lead to a strong development of this clean and reliable energy for the majority of the countries of the world. Algeria, which has about 200 thermal springs, has the possibility of being among the leaders in this field. In this presentation, we cite the characteristics of geothermal energy, the Algerian thermal springs and the possibilities of their uses according to the temperatures using the Lindal diagram, as well as the role of geophysics or the Earth’s physics in the exploration of geothermal sources before drilling where most of the techniques are the same as those used in petroleum exploration and reservoir characterization exploiting new technological development such as artificial intelligence from seismic and well-logs data [3].
  • No Thumbnail Available
    Item
    Heterogeneities analysis using the generalized fractal dimension and continuous wavelet transform
    (2012) Ouadfeul, Sid-Ali; Aliouane, Leila; Boudella, Amar