DOI: 10.11799/ce202506020
Prediction of CH4 displacement rate in CO2-injected coal using BP neural network
JIA Dongxu
Abstract：To accurately predict the CH4 displacement rate in coal seams after CO2 injection,samples of anthracite were selected as the research object.Based on experimental data of CH4 displacement rate(η)for coal samples under varying coal seam temperatures(T),CO2 injection pressures(P0),and initial adsorption equilibrium pressures(P1),a prediction model for CH4 displacement rate was established using the BP neural network.The model accuracy was evaluated via the coefficient of determination(R2),root-mean-square error(RMSE),and mean absolute error(MAE).Results show that η increases as T and P0 rise,but decreases as P1 increases.For the test set,the model achieved an R2 of 0.986,RMSE of 0.349,and MAE of 0.312,with the error between predicted and actual values within 2.30%.This indicates high prediction accuracy,providing guidance for coal seam gas injection technology.
Keywords：coal seam gas injectionCO2 injectionmethane displacement rategas predictiongas emissionCH4 displacement experiment
Publication Date：2025-06-30
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 158-163 )