Accurate geology modeling is critical in coal mining engineering for increasing mining efficiency and safety. Traditional 3D modeling approaches rely on drill hole data to fill in unknown geographical characteristics using interpolation or machine learning methods. However, the cost of individual borehole projects is high, and borehole distribution is sparse; the filling of sparse boreholes by interpolation smoothes the geologic data to some extent, and some abnormal geologic conditions cannot be shown in the interpolated geologic data; and the classification of subsurface space by machine learning is hampered by sparse training samples and model overfitting or underfitting. As a result, this paper proposes a method to reduce the complexity and uncertainty in the process of 3D geological modeling by integrating the classification results of multiple classifiers based on the machine learning classification model and constructing a 3D geological model based on gas extraction borehole data using the Boosting integration strategy. The results reveal that the Boosting integration model outperforms a single machine learning model in geological modeling, with improved classification accuracy and resilience. A comparative investigation of different classifiers demonstrates that the Boosting integrated model outperforms a single classifier in geological modeling. The geologic profile analysis confirms the dependability and stability of the Boosting integrated model, which can provide an effective solution for 3D geologic modeling of coal mine workings and is critical for increasing mining productivity and lowering accident risks.
Read full abstract