GEOLOGICAL STRUCTURE MODELING METHOD BASED ON MULTI-SOURCE HETEROGENEOUS DATA

The present disclosure provides a geological structure modeling method based on multi-source heterogeneous data, applicable to the technical fields of geological exploration and artificial intelligence. The method comprises: generating a plurality of geological simulation structure models by using data simulation technology, and constructing a geological simulation structure model library, the geological simulation structure models having diverse folds and fault characteristics; for each geological simulation structure model in the geological simulation structure model library, acquiring geological fault data and unevenly distributed geological horizon data, to obtain a training sample data set; training a neural network by using the training sample data set; and inputting multi-source heterogeneous data of a target region into the trained neural network, and outputting a geological structure model corresponding to the multi-source heterogeneous data, wherein the multi-source heterogeneous data comprises faul