The invention discloses a rockburst disaster prediction method based on an optimized extreme gradient lifting classification model, and relates to the technical field of environment monitoring, and the method comprises the steps: obtaining multi-shift
monitoring data of a
coal mine working face, carrying out the preprocessing, dividing the data into a
training set and a
test set, and taking an initial hyper-parameter extreme gradient lifting classifier as a basic model, and using at least one meta-
heuristic optimization
algorithm to optimize the hyper-parameters, training and constructing a
hybrid prediction model, inputting real-time
monitoring data into the
hybrid prediction model to carry out rockburst disaster prediction, and outputting a
coal mine
rock burst disaster risk prediction result. According to the method, the technical problems of low disaster prediction accuracy and dangerous state
recall rate and high missing report risk caused by insufficient sensitivity of an existing
coal mine
rock burst disaster prediction model to unbalanced
monitoring data are solved, and the purposes of optimizing an extreme gradient lifting classifier through a meta-
heuristic algorithm and improving the prediction accuracy of the coal mine
rock burst disaster prediction model are achieved. The disaster prediction accuracy and the dangerous state
recall rate are improved, and the missing report risk is reduced.