Abstract: The interpretation of advance drilling forecasts for tunnels involves many problems, such as highly subjective judgment, low quantitative data utilization, and inconsistent evaluation standards. Therefore, the extreme gradient boosting ensemble model (XGBoost) in machine learning is introduced, and the doublelayer (integrity and classification) quality evaluation of the surrounding rock of the tunnel is conducted based on the drilling data. First, the 11 233 original drilling sampling data are preprocessed to improve data quality using data noise reduction, equidistant segmentation, and secondary index calculation methods. Second, a genetic algorithm (GA)classifier chain (CC)XGBoost model is constructed. This model realizes the automatic optimization of the hyperparameter combination of the complex machinelearning model and considers the inherent relevance of multilabel classification. The classification accuracy of the GACCXGBoost model in the doublelayer label is 95.91% and 97.95%, and the comprehensive classification accuracy is 93.88%. The actual tunnel engineering application indicates that the prediction results of the model meet the interpretation requirements of geological forecasts for onsite advance drilling.