A coal seam gas content prediction method based on pso-bp model and seismic attribute parameters

Abstract

The present invention discloses a coal seam gas content prediction method based on PSO-BP model and seismic attribute parameters. From the cluster analysis and optimization of attributes, to the construction of the PSO-BP prediction model, finally, the coal seam gas content is predicted by the PSO-BP prediction model trained on the well data. Different from the technical process of single seismic attribute prediction, the invention strives to excavate the seismic attribute response information of coal seam gas content from multiple angles; Compared with the traditional linear prediction model, the model can effectively characterize this nonlinear mapping relationship, the technology is more advanced, the prediction accuracy and reliability can be guaranteed, and the prediction speed is greatly improved. Therefore, the present invention has more advantages in information mining, technical process and prediction accuracy compared with the traditional coalbed methane gas content prediction technology.

Description

technical field [0001] The invention relates to the field of coalbed methane 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] Most of the prediction methods for coalbed gas content or coalbed methane (gas) enriched areas are based on a single pre-stack seismic attribute or post-stack seismic attribute, and the types of seismic attribute parameters lack diversity, and in the prediction process, the above methods mostly use linear prediction models. It is difficult to guarantee the prediction accuracy and effect, and the universality of the technological process is limited; in actual situations, the gas content of coal seams is affected and controlled by various geological conditions and factors, and there is an extremely complex and fuzzy relationship with seismic attribute parameters. It is difficult to meet the needs of precise explor...

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 coal seams is affected and controlled by various geological conditions and factors, and there is an extremely complex and fuzzy relationship with seismic attribute parameters. It is difficult to meet the needs of accurate exploration and development of coalbed methane by using the traditional single seismic attribute and linear model technology. In view of this situation, a method based on PSO-BP model and seismic attribute parameters is proposed. coal seam gas content prediction method

Images