Full text loading...
-
Random Noise Attenuation in Reflection Seismic Data Using Adaptive Neuro-fuzzy Interference System (ANFIS)
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, 78th EAGE Conference and Exhibition 2016, May 2016, Volume 2016, p.1 - 5
Abstract
This research introduces a method for background random noise attenuation in seismic data giving priority to the preservation of coherent seismic events and automation of algorithm. Since statistical characteristics of random noise are different than those of coherent events, in the proposed method, after defining a few statistical features, fuzzy C-Mean clustering was carried out on some randomly selected data samples from the seismic section. Then, the resulting membership functions along with the output of the adaptive Wiener filter were used so that automatic training of ANFIS could take place. Then, the acquired weights of the ANFIS were generalized to the whole data set based on the calculation of the statistical features. The proposed method was applied on both synthetic and real data sets and the results were compared to those of the conventional methods. The research findings revealed that the method was of a considerably higher performance in random noise attenuation as well as preserving the coherent events.