瞬时谱数据的谱加权自适应带通滤波融合

Spectra-weighted adaptive band-pass filtering fusion of instantaneous spectral data

为了快速提取地震谱分解数据中的储层特征信息,本文提出一种将瞬时峰值振幅和峰值频率属性数据进行融合的方法,它采用随频率自适应调节滤波带宽的高斯基函数,可反映时频域地震信号在低频端具有很高的频率分辨率,高频端具有较低的频率分辨率的特征;并以峰值振幅属性作为权重,将两种谱分解属性数据映射为颜色融合数据。实际资料的应用表明,该法可反映瞬时谱主振幅随频率的变化,刻画储层的空间展布、几何形态、相对厚度和含流体情况等,快速提取谱分解数据中的有效地质信息,提高解释的效率。

In order to quickly extract reservoir characteristics from seismic spectral decomposition data,we present a data fusion method to map features in both peak amplitude and peak frequency attributes,which uses frequency-dependent adaptive bandwidth-varied filter of Gaussian basis function.Such basis function can reflect the inherent characteristics of seismic signal in time-frequency domain,i.e.higher frequency resolution at lower frequency and lower frequency resolution at higher frequency.Then we choose the peak amplitude as the weighting,and map the two spectral decomposition attributes into one true color fusion volume.The field example demonstrates that it can delineate reservoir spatial distribution,its geometry,its relative thickness and its petroliferous feature.It is feasible to quickly extract geologic feature of interests and improve the efficiency in interpretation.