Coal seam gas content prediction method based on PSO-BP model and seismic attribute parameters

Abstract

The invention discloses a coal seam gas content prediction method based on a PSO-BP model and seismic attribute parameters. The coal seam gas content prediction method comprises the specific technological process of: extracting pre-stack seismic attributes and post-stack seismic attributes, calculating and primarily selecting correlation coefficients of the seismic attributes, performing clustering analysis and optimization on the seismic attributes, constructing the PSO-BP prediction model, and finally predicting the coal seam gas content by means of the PSO-BP prediction model trained by using well data. The coal seam gas content prediction method is different from a single seismic attribute prediction technology, and strives to mine seismic attribute response information of the coal seam gas content from multiple angles; meanwhile, since the coal seam gas content is influenced and controlled by various geological conditions and geological factors, the PSO-BP prediction model can effectively represent the nonlinear mapping relation compared with a traditional linear prediction model, the technical process is more advanced, the prediction precision and reliability can be guaranteed, and the prediction speed is greatly accelerated. Therefore, compared with a traditional coalbed methane gas content prediction process, the coal seam gas content prediction method has more advantages in information mining, technical process and prediction precision.

Description

technical field [0001] The invention relates to the field of coalbed gas seismic exploration and reservoir evaluation, in particular to a coalbed gas content prediction method based on a PSO-BP model and seismic attribute parameters. Background technique [0002] The prediction methods of coalbed methane content or coalbed methane (gas) enriched area are mostly based on a single pre-stack seismic attribute or post-stack seismic attribute. The types of seismic attribute parameters lack diversity, and most of the appeal methods use linear prediction models in the prediction process. The prediction accuracy and effect are difficult to guarantee, and the universality of the process flow is limited; in reality, the gas content of the coal seam is affected and controlled by various geological conditions and factors, and there is an extremely complex and fuzzy relationship with the seismic attribute parameters. The non-linear mapping relationship of the traditional single seismic a...

AI Technical Summary

Problems solved by technology

[0002] The prediction methods of coalbed methane content or coalbed methane (gas) enriched area are mostly based on a single pre-stack seismic attribute or post-stack seismic attribute. The types of seismic attribute parameters lack diversity, and most of the appeal methods use linear prediction models in the prediction process. The prediction accuracy and effect are difficult to guarantee, and the universality of the process flow is limited; in actual situations, the gas content of co

Images