For the prediction of coal and gas outburst intensity, Incorporate Genetic Algorithm Based Back Propagation Neural Network(IGABP) is proposed to solve the limitations in the traditional GABP such as timeconsuming, optimal stop condition of GA pretreatment indeterminacy, independency and complex task of great importance etc. IGABP addresses some improvements in adaptive crossover and mutation probability to promote GA performance. And with the introduction of BP operator in the evolution of GA operations, the standard GA optimization is from random search to selfguiding search and the convergence rate of GA is upgraded, as well as the determination ability of exact solution. With a simulation as a case study, it is found that the minimum error and standard error with IGABP are 0.012 and 0.227, respectively, compared with -0.126 and 1.529 by traditional GABP.