Abstract: Outburst risk evaluationa model based on rough set theory and unascertained measure theory was established.For the aim of selecting the optimistic indexes,the paper analyzed the field datum of a variety of outburst risk predictors based on rough set theory,and deleted the unimportant indexes.The weight were distributed based on the relative importance of each indicator.The unascertained function of predictor was established based on the unascertained theory and the unascertained comprehensive evaluation vector was calculated.The outburst risk evaluation results was obtained eventually based on the classification of confidence recognition criteria.The model was applied to verify its practicality and effectiveness.Comparing with the results of fuzzy forecasting method and regression prediction method,the results showed that the evaluating effect of the model was better,and more in line with the actual situation of the scene.