Support vector machine in volcanic reservoir forecast: East slope in Xujiaweizi depression

In Xujiaweizi depression of northern Songliao Basin, the development of volcanic reservoir dominated largely gas accumulation. However, an accurate description for volcanic distribution is always difficult for geologists, because of its complex lithology, lateral heterogeneity and poor comparison between wells. With regard to this problem, we present the model of support vector machine as a solution. By the analyses of the combination of seismic attributes, this model can be used to indicate volcanic reservoir. The thickness of volcanic rocks and its distribution, which are predicted through using this method, can reflect its sedimentation model and maintain the lateral resolution of seismic as well as the overall trend. In addition, the thickness of volcanic rocks at drilled wells is highly consistent with those of well logs.