Adaptive attenuation of aliased ground roll using the shearlet transform Seyed Abolfazl Hosseini a , Abdolrahim Javaherian a,b, ⁎, Hossien Hassani c , Siyavash Torabi d , Maryam Sadri e a Department of Petroleum Engineering, Amirkabir University of Technology, 424 Hafez Ave., Tehran, Iran b Institute of Geophysics, University of Tehran, North Amirabad Ave., Tehran, Iran c Department of Mining and Metallurgical Engineering, Amirkabir University of Technology, 424 Hafez Ave., Tehran, Iran d Dana Geophysics Company, No. 140, Dana Group Building, Dastgerdi (Zafar) St., Sahriati St., Tehran, Iran e Department of Geophysics, Exploration Directorate of National Iranian Oil Company, Sheikh Bahaei Sq., Seoul St., Tehran, Iran abstract article info Article history: Received 18 March 2014 Accepted 25 November 2014 Available online 2 December 2014 Keywords: Shearlet transform Subimage Aliased ground roll Adaptive ground roll attenuation Attenuation of ground roll is an essential step in seismic data processing. Spatial aliasing of the ground roll may cause the overlap of the ground roll with reflections in the f–k domain. The shearlet transform is a directional and multidimensional transform that separates the events with different dips and generates subimages in different scales and directions. In this study, the shearlet transform was used adaptively to attenuate aliased and non- aliased ground roll. After defining a filtering zone, an input shot record is divided into segments. Each segment overlaps adjacent segments. To apply the shearlet transform on each segment, the subimages containing aliased and non-aliased ground roll, the locations of these events on each subimage are selected adaptively. Based on these locations, mute is applied on the selected subimages. The filtered segments are merged together, using the Hanning function, after applying the inverse shearlet transform. This adaptive process of ground roll attenu- ation was tested on synthetic data, and field shot records from west of Iran. Analysis of the results using the f–k spectra revealed that the non-aliased and most of the aliased ground roll were attenuated using the proposed adaptive attenuation procedure. Also, we applied this method on shot records of a 2D land survey, and the data sets before and after ground roll attenuation were stacked and compared. The stacked section after ground roll attenuation contained less linear ground roll noise and more continuous reflections in comparison with the stacked section before the ground roll attenuation. The proposed method has some drawbacks such as more run time in comparison with traditional methods such as f–k filtering and reduced performance when the dip and frequency content of aliased ground roll are the same as those of the reflections. © 2013 Elsevier B.V. All rights reserved. 1. Introduction Ground roll is one of the main types of coherent noise in land seismic data. Since it has stronger amplitudes and higher level of energy com- pared to reflections, it may mask them. Different methods have been in- troduced to attenuate this type of noise. Frequency–wavenumber (f–k) filtering is one of the methods of ground roll attenuation. In the f–k domain, ground roll and reflections are separated regarding their dips. Spatial aliasing of the signal and/or noise usually creates problems in seismic data processing. The simplest solutions to overcome this prob- lem are high-cut filtering, spatial anti-alias filtering, and trace interpola- tion. Applying high-cut filter or spatial anti-alias filter results in losing some data. Different authors discuss trace interpolation. Based on the fact that missing traces spaced equally can be interpolated by a set of linear equations, Spitz (1991) proposed an interpolation method in the f–x domain. Huard et al. (1996) extended Spitz's method to the f–xy domain. Porsani (1999) introduced the half-step f–x method, mak- ing trace interpolation significantly more efficient and easier for implementation. Wang (2002) extended the f–x method to f–xy do- main and applied full-step and fractional-step predictions for interpola- tion. Naghizadeh and Sacchi (2009) introduced an adaptive f–x interpolation method that performs quite well in the presence of con- flicting dips with aliasing. Naghizadeh and Innanen (2011) proposed a fast and efficient method for interpolation of nonstationary seismic data. Liu and Fomel (2011) presented a new approach to interpolate aliased seismic data based on adaptive prediction error filtering (PEF) and regularized nonstationary autoregression that includes a fast itera- tion convergence. Yang et al. (2012) used curvelet-based projection onto convex sets (POCS) interpolation algorithm as a base for interpola- tion of nonuniformly sampled seismic data. In addition to the above procedures, some methods have been intro- duced for aliased ground roll attenuation. Brown and Clapp (2000) at- tenuated ground roll by modeling and separation of the ground roll in Journal of Applied Geophysics 112 (2015) 190–205 ⁎ Corresponding author at: Department of Petroleum Engineering, Amirkabir University of Technology, Tehran, Iran. Tel.: +98 2164545131; fax: +98 21 64543528. E-mail addresses: javaherian@aut.ac.ir, javaheri@ut.ac.ir (A. Javaherian). http://dx.doi.org/10.1016/j.jappgeo.2014.11.018 0926-9851/© 2013 Elsevier B.V. All rights reserved. Contents lists available at ScienceDirect Journal of Applied Geophysics journal homepage: www.elsevier.com/locate/jappgeo