Ternary deep metallogenic prediction method and system based on machine learning

The invention discloses a ternary deep metallogenic prediction method and system based on machine learning, and relates to the technical field of machine learning, and the deep metallogenic prediction method comprises the steps: obtaining the attribute features of a target region; the attribute features comprise geological features, geochemical features, geophysical features and remote sensing interpretation features; predicting the attribute features based on a regional metallogenic mode recognition model to obtain a regional metallogenic mode; establishing an underground three-dimensional geologic model of the target area; according to the underground three-dimensional geologic model, three-dimensional attributes of underground rock and ore in the target area are obtained; and inputting the regional metallogenic mode and the three-dimensional attributes into the trained deep prospecting prediction model to obtain metallogenic information of the target region. According to the method, prediction of the regio