摘要：The main reservoir space and seepage channel of volcanic reservoir are fractures and dissolution holes.The heterogeneity of the reservoir makes the logging interpretation more complex than that of clastic and carbonate reservoirs.In view of the difficulties faced by the well logging interpretation of volcanic reservoirs,this paper use the point-by-point detection method of pattern discrimination in the identification and prediction of volcanic reservoir fracture.Combined with the logging,seismicand production performance data of the actual area,the well fracture imaging is drawn,and the relationship between fracture development and curve characteristics is studied.The research results shows that the pattern discrimination point by point detection method is used to identify and predict fractures.Compared with the conventional method of seismic prediction,the accuracy has been greatly improved.The prediction results are in line with the law of volcanic fracture development.The comparison of interpretation results and imaging data shows that the prediction accuracy is more than 78%.The pattern recognition method breaks through the problem of difficult prediction of micro fractures.The result of single well fracture identification is acted on,and combined with seismic technology,the prediction of large fracture zone is carried out from micro to macro,which greatly improve the prediction accuracy,and also provide a reference for the identification and prediction of volcanic rock fractures in other similar geological environments.
