Abstract: A method, an apparatus, a computer storage medium and a computer device for geological characteristic constraint-based reservoir parameter prediction are provided. The method includes: selecting dominant seismic attributes according to the relevance between different types of seismic attributes of a target stratum and reservoir parameters (S100); on the basis of the dominant seismic attributes, classifying seismic waveforms of the target stratum by a preset waveform classification network model and according to waveform features, so as to obtain a waveform classification result (S200); taking the waveform classification result as a constraint, and constructing different deep neural network models corresponding to different geological characteristics (S300); fusing different trained deep neural network models into a set of spatially varying neural network prediction model (S500); and predicting the reservoir parameters of the target stratum.

Abstract: Disclosed are an automatic focus identification method and a system for a Karst cave reservoir. According to the method, velocity replacement is performed based on a pre-stack time migration velocity model to obtain a plurality of replacement migration velocity volumes; pre-stack time migration is performed based on the plurality of replacement migration velocity volumes to obtain a plurality of post-stack seismic data volumes; a three dimensional cube window is selected based on a seismic response characteristic of the Karst cave reservoir; sparse statistical data of a seismic trace or sparse statistical data of a seismic trace attribute of each of the post-stack seismic data volumes in the three dimensional cube window are obtained respectively; and an optimized migration velocity and an optimized seismic trace are obtained through optimization determination.

Abstract: Disclosed are an automatic focus identification method and a system for a Karst cave reservoir. According to the method, velocity replacement is performed based on a pre-stack time migration velocity model to obtain a plurality of replacement migration velocity volumes; pre-stack time migration is performed based on the plurality of replacement migration velocity volumes to obtain a plurality of post-stack seismic data volumes; a three dimensional cube window is selected based on a seismic response characteristic of the Karst cave reservoir; sparse statistical data of a seismic trace or sparse statistical data of a seismic trace attribute of each of the post-stack seismic data volumes in the three dimensional cube window are obtained respectively; and an optimized migration velocity and an optimized seismic trace are obtained through optimization determination.