Browsing by Author "Mihoubi, A."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Application of feedback connection artificial neural network to seismic data filtering
    (Elsevier, 2008) Djarfour, Noureddine; Aïfa, Tahar; Baddari, K.; Mihoubi, A.; Ferahtia, J.
    The Elman artificial neural network (ANN) (feedback connection) was used for seismic data filtering. The recurrent connection that characterizes this network offers the advantage of storing values from the previous time step to be used in the current time step. The proposed structure has the advantage of training simplicity by a back-propagation algorithm (steepest descent). Several trials were addressed on synthetic (with 10% and 50% of random and Gaussian noise) and real seismic data using respectively 10 to 30 neurons and a minimum of 60 neurons in the hidden layer. Both an iteration number up to 4000 and arrest criteria were used to obtain satisfactory performances. Application of such networks on real data shows that the filtered seismic section was efficient. Adequate cross-validation test is done to ensure the performance of network on new data sets
  • No Thumbnail Available
    Item
    Characterization of a reservoir in a south Algerian prospect using the instantaneous seismic attributes: efficiency and reliability of the instantaneous frequency parameter using the joint time-frequency analysis
    (2003) Aitouche, Moh-Amokrane; Djeddi, M.; Mihoubi, A.
    Present day, exploration for oil and gas requires a combined effort based on the successful integration of the most part of geophysical methods for optimizing the location of data acquisition, identifying and evaluating the productive potential of unexplored regions or extending existing productive traps. Exploration seismology has been focussed on imaging the structural features of the Earth's subsurface. This approach is now commonplace in most seismic evaluation project due to the ability of this technique under favorable hypothesis to predict reservoirs properties (depth, lateral extension, discrimination between reservoir fluids ... ). However, after the fantastic software improvement, new robust processing tools (principally in signal processing techniques) have been developed for extracting indirect information provided by structure imaging. These new tools can significantly increase the probability of success associated with a given project. In this context, the success of direct hydrocarbons detection is primary due to the identification oflarge negative amplitudes known as bright spot which can define a necessary but not sufficient condition for identifying oil and gas pitfalls. Robust methods in volve computed and correlated sesimic attributes such as the instantaneous ones (intantaneous phase, instantaneous frequency, instantaneous amplitude, inversion polarity ... ) have enjoyed in many cases considerable suc cess for characterizing potential hydrocarbon traps. In the present work, we have precisely used a set of instantaneous attributes to characterize a reservoir located in a permit of the South Algerian Sahara.However, we take the following question: how about the efficiency and the reliability of each instantaneous seismic attribute ? To do this, the instantaneous frequency parameter has been selected because it provides a power indicator of the variations in the energy distribution of the sei smic signal, principally in a noisy environment. More recently, adapted signal processing tools are performed; one can cite the joint time-frequency analysis and its corollaries the Wigner-Ville Distribution, the Wigner bispectrum and the Pseudo-Wigner-Ville representation which are simultaneously tested in the present work on a noisy hyperbolic swept frequency signal