Spatial random forest algorithm for outcrop geologic body rock stratum layering

The invention discloses a spatial random forest algorithm for outcrop geologic body rock stratum layering, and relates to the technical field of geological exploration. The method comprises the steps of constructing an outcrop rock stratum three-dimensional point cloud model based on oblique photogrammetry data, performing voxel segmentation on the outcrop rock stratum three-dimensional point cloud model, constructing a rock stratum voxel spatial feature and attribute feature integrated expression model, constructing a spatial decision tree by the expression model, constructing a spatial random forest algorithm through the spatial decision tree, and substituting the voxels into a spatial random forest algorithm for prediction to obtain rock stratum categories matched with the voxels. Geographic information science is taken as a theoretical basis, attribute characteristics and spatial characteristics of the point cloud data are extracted from the point cloud data in combination with geologic body rock stratum