Multi-model integrated shale reservoir rock mechanical parameter logging prediction method

The invention relates to a multi-model integrated shale reservoir rock mechanical parameter logging prediction method, which comprises the following steps of calculating evaluation indexes of prediction of different rock mechanical parameters of a shale reservoir by various machine learning base models based on Pearson correlation coefficients; the machine learning base model with the evaluation index values ranked in the top is selected, and an integrated learning algorithm is adopted to construct a rock mechanics parameter intelligent integrated prediction model; and performing rock mechanical parameter logging prediction by using the intelligent integrated rock mechanical parameter prediction model. According to the method, the local optimum point in the prediction process can be avoided, the model can be prevented from losing the prediction capability of unknown data, the generalization performance of a machine learning prediction method can be improved, the adaptability of the model in actual shale reser