Shale gas productivity main control factor analysis method based on convolutional neural network and SHAP value

The invention provides a shale gas productivity main control factor analysis method based on a convolutional neural network and an SHAP value, and belongs to the field of shale gas development. The method comprises the following steps: determining factors influencing the shale gas productivity of a target block; wherein each influence factor is used as a feature; obtaining shale gas data to form a feature data set according to the determined influence factors of the shale gas productivity, and obtaining productivity corresponding to the shale gas data to form a label data set; establishing a productivity prediction model based on a convolutional neural network by using the feature data set and the label data set; calculating the SHAP value of each feature in the feature data set based on the trained productivity prediction model, and quantifying the influence degree of each factor on productivity; and on the basis of the obtained SHAP value, analyzing the internal relationship between the productivity and the