Support vector machine regression model of CBM content and application

In order to quantitatively predictive the content of the coal bed methane (CBM), we make use of the known parameters of the core tests data to establish the support vector machine regression model between the core data and coal-bed methane content. The model is based on the small sample size theory. Using the model, we can predict the volume of gas content. We choose the coal seam thickness, coal vitrinite reflectance value and coal ash 3 parameters as input feature vectors, and coal-bed methane content as the output vector of support vector machine regression prediction model. Application of the proposed model in Binchang mining shows that the prediction error between the measured results and prediction are small and meet the accuracy requirements.