Research on multi-channel adaptive coupling prediction system of fusing physical information for spatio-temporal correlation heterogeneity of methane concentration

The dynamic evolution of methane concentration in underground coal mine is the core risk source that induces methane accidents. In order to solve the problem of limited prediction accuracy caused by ignoring the spatio-temporal correlation heterogeneity of methane concentration in existing prediction models and the limitation of interpretability in existing data-driven models, this study proposes a multi-channel adaptive coupling prediction method that fuses physical information. By modeling adaptive fine-grained dependencies across multiple channels, we achieved targeted extraction of dynamic response characteristics of methane concentration from multi-source data in underground coal mines during spatio-temporal evolution processes. For the first time, an error loss term that integrates physical information has been developed for gas concentration prediction, with the final model output obtained by aggregating relevant information through an adaptive graph learning module. The results of the application in different regions of the coal mine show that the proposed method has better versatility and prediction accuracy in the methane concentration prediction task. Through the explainable modeling of dynamic dependencies and the explicit integration of physical constraints, the transparency and credibility of prediction results are significantly improved, which can effectively prevent the occurrence of methane accidents in coal mines and promote the development of the coal mine industry in a sustainable direction.