Prediction method of gas content in deep coal seams based on logging parameters: A case study of the Baijiahai region in the Junggar Basin

作者：Yijie Wen, Shu Tao, Fan Yang, Yi Cui, Qinghe Jing, Jie Guo, Shida Chen, Bin Zhang, Jincheng Ye · 发表于：International Journal of Coal Science & Technology · 年份：2025 · DOI：10.1007/s40789-025-00807-z · 被引用次数：10 · 研究领域：Coal Properties and Utilization、Hydrocarbon exploration and reservoir analysis、Geoscience and Mining Technology

Abstract Currently, regression prediction methods based on logging data is one of the main methods for analyzing gas content of coal seams. However, the complexity of logging parameters for deep coal seams and the scarcity of measured gas content data significantly affects the accuracy and generalizability of data regression models. Accurately predicting the gas content of coal seams under small-sample condition become a difficult point in deep coalbed methane (CBM) exploration. The Model-Agnostic Meta-Learning (MAML) and Support Vector Regression (SVR) algorithms are among the few suitable for small-sample learning, exhibiting strong adaptability under limited sample conditions. In this study, logging parameters are used as input variables to construct MAML and SVR models, and their performance in predicting gas content of deep coal seams across different regions and layers is compared. The results demonstrate that the MAML algorithm effectively addresses the complex relationships between gas content of deep coal seam and logging parameters. The prediction errors for test dataset and new samples are merely 3.61% and 4.52% respectively, indicating exceptional adaptability, robust generalization capability, and stable model performance. In contrast, the dependency of SVR model on input parameters restricts its accuracy and generalizability in predicting gas content in deep coal seams with varying geological conditions. Although achieving a test dataset error of 4.71%, the SVR ...