Research on the prediction method of coalbed methane production based on GA-BP

As clean energy, coalbed methane is a hot spot and focus of research and development at home and abroad. For the prediction of coalbed methane production, the existing methods have a poor prediction effect. In this paper, random forest (RF) is used to sort the importance of the characteristics affecting CBM production, eight main controlling factors are selected, and a CBM production prediction model is established based on the Genetic Algorithm-Optimized BP Neural Network (GA-BP). The GA-BP model predicted the yield with an accuracy of 87.2%, which provides a good method reference for the CBM production forecast.