Coal seam permeability change prediction method based on FA-SSA-SVM algorithm

The invention provides a coal seam permeability change prediction method based on an FA-SSA-SVM algorithm, and belongs to the field of CO2 storage. According to the method, a novel hybrid intelligent model is constructed by integrating a support vector machine (SVM), a sparrow search algorithm (SSA) and a firefly algorithm (FA), the SVM is used for exploring the relation between the coal reservoir permeability change and the influence variable thereof, and the SSA and the FA are used for optimizing hyper-parameters of the SVM. The SSA is disturbed by using the FA, the search performance of a global solution is improved by disturbing a general solution and an optimal solution in the SSA, a global optimal solution of SVM hyper-parameters is obtained, and nonlinear prediction of the relationship between the permeability change of the coal reservoir and the influence variables thereof in a high-dimensional space is realized. The FA-SSA-SVM prediction model can achieve a good prediction effect on the basis of considering various complex factors in the CO2 storage process, and has the advantages of being low in cost, high in prediction precision, high in generalization ability and the like.