Application of feedback connection artificial neural network to seismic data filtering

Abstract

International audienceThe 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

Strategy for automated analysis of passive microseismic data based on S-transform, Otsu’s thresholding, and higher order statistics

“…This way, the filter designed has two components that are applied on the real and imaginary parts of the signal in the time-frequency domain. The result is inverse S-transformed, Canales, 1984Gulunay, 1986 Artificial neural networks Essenreiter, 1999Djarfour et al, 2008Fuzzy methods Hashemi et al, 2008 Figure 2. Event-detection algorithm flowchart.…”

Acoustic impedance inversion by feedback artificial neural network

“…An output error is calculated from the difference between the actual output and the desired output. The resulting error is then propagated through the network and weights are adjusted accordingly (Renders, 1995;Djarfour et al, 2008).…”

“…For this reason it has been applied in many fields of Science and Engineering such as classification, approximation, pattern recognition, signal processing, prediction, feature extraction, etc. Recent application of ANN in geophysics involves the use of ANN to the seismic inversion (Calderón-Macías et al, 2000), seismic data filtering (Djarfour et al, 2008), magnetotelluric time-series analysis (Manoj and Nagarajan, 2003), deconvolution and source wavelet estimation (Wang and Mendel, 1992) and for many other problems.…”

Seismic random noise attenuation using artificial neural network and wavelet packet analysis

“…In reflection seismology, however, except for the cases relating to the interpretation and classification of seismic attributes, it seems that soft computations and artificial intelligence are not widely used in processing of seismic data. To exemplify some applications of artificial intelligence in seismic data processing, one can refer to Zhang et al (2010) who used a neural network with a modified version of back propagation architecture in which the error function had been altered so as to attenuate the random noise in a shot record; Djarfour et al (2008) who attenuated the noise in synthetic and real shot records using neural network; and Lin et al (2014) who recently applied fuzzy clustering along with their main algorithm, which was based on time-frequency peak filtering, to attenuate random noise. This paper seeks to enhance resolution of the seismic reflection data by attenuating background random noise, utilizing wavelet packet analysis WPA and the high potential of artificial neural network (ANN) in model discrimination.…”