New Data-Driven Method for In Situ Coalbed Methane Content Evolution: A BP Neural Network Prediction Model Optimized by Grey Relation Theory and Particle Swarm

In situ coalbed methane (CBM) content accurate evolution is critical to target area optimization and long-term CBM production. In this study, we first proposed a new data-driven method, an improved BP neural network model optimized by grey relational analysis (GRA) and particle swarm optimization (PSO) algorithm for in situ CBM content prediction. The results show that the GRA method is useful to determine the feature input parameters for the BP neural network model which speeds up operation and reduces the influence of redundant parameters simultaneously. Meanwhile, the PSO algorithm with asynchronous learning factors is applied successfully to optimize the weights and thresholds of the BP neural network to increase modeling accuracy. To prove the prediction accuracy, the proposed model was trained and validated using field measured data from 36 CBM wells in Zhengzhuang block in the southern Qinshui Basin. The proposed modeling method yielded reliable results, outperforming traditional prediction models in terms of prediction accuracy (3.71% relative error only). Moreover, the proposed model is thought to be useful for high accuracy prediction of in situ CBM content in heterogeneous reservoirs under complicated geological structure conditions since it has higher robustness and stronger generalization.