In general, we wish to interpret the most broadband data possible. However, broadband data do not always provide the best insight for seismic attribute analysis. Obviously, spectral bands contaminated by noise should be eliminated. However, tuning gives rise to spectral bands with higher signal-to-noise ratios. To quantify geologic discontinuities in different scales, we combined spectral decomposition and coherence. Using spectral decomposition, the spectral amplitudes corresponding to a given scale geologic discontinuity, as well as some subtle features, which would otherwise be buried within the broadband seismic response, can be extracted. We applied this workflow to a 3D land data volume acquired over the Tarim Basin, Northwest China, where karst forms the principle reservoirs. We found that channels are better illuminated around 18 Hz, while subtle discontinuities were better delineated around 25 Hz.