The extreme gradient boosting (XGBoost) ensemble learning algorithm excels in solving complex nonlinear relational problems. In order to accurately predict the surface subsidence caused by mining, this work introduces the genetic algorithm (GA) and XGBoost integrated algorithm model for mining subsidence prediction and uses the Python language to develop the GA-XGBoost combined model. The hyperparameter vector of XGBoost is optimized by a genetic algorithm to improve the prediction accuracy and reliability of the XGBoost model. Using some domestic mining subsidence data sets to conduct a model prediction evaluation, the results show that the R2 (coefficient of determination) of the prediction results of the GA-XGBoost model is 0.941, the RMSE (root mean square error) is 0.369, and the MAE (mean absolute error) is 0.308. Then, compared with classic ensemble learning models such as XGBoost, random deep forest, and gradient boost, the GA-XGBoost model has higher prediction accuracy and performance than a single machine learning model.

Infrared radiation thermal imaging technology is proposed for rock mechanics tests. Through the infrared radiation temperature and stress–strain curves of sandstone with different porosity during the process of uniaxial compression loading obtained by an infrared camera and uniaxial compression testing machine, the characteristics of infrared radiation on sandstone are systematically analyzed during uniaxial compression loading. The results show that: (1) The strength of sandstone decreases with the increase of porosity, the infrared thermography of sandstone has obvious characteristics of stage evolution and is closely related to the deformation and failure stage of rock in the process of uniaxial compression; (2) During the rock failure process, infrared thermography is differentiated, and the high-temperature radiation zone can reflect the location, size and shape of rock fractures; (3) During the uniaxial compression loading process, the evolution law of the average infrared radiation temperature (AIRT) is closely related to the porosity and uniaxial compressive of the rock, and it is possible to invert all processes of rock failure. The research results demonstrate that the technique of infrared thermal imaging can be applied to rock mechanics tests, and the evolution law of the infrared radiation characteristics can provide a reference for stability analysis of the underground rock engineering.