Synthesizing training data for broad area geospatial object detection

A system for broad area geospatial object detection using synthetically-generated training images for improved training of a deep learning model comprising a computing device comprising a processor, a memory, and a plurality of programming instructions stored in the memory and operable on the processor, wherein the plurality of programming instructions:

• (a) retrieves a digital model of an object of interest from a data store;
• (b) creates a flattened image from the retrieved digital model;
• (c) compares the flattened image to a real geospatial image comprising an instance of the object of interest and associated background;
• (d) creates a plurality of shadowed, modified flattened images for the object of interest as if it were physically located and oriented where it would be affected by real-time and real-world shadowing;
• (e) adjusts the shadowed, modified flattened images to resemble the real image;
• (f) identifies and demarcates a footprint associated with each of the shadowed, modified flattened images;
• (g) overlays the demarcated footprint onto a real image;
• (h) generates a labeled corpus of manipulated synthetic training data comprising at least a portion of the modified flattened images;
• and
• (i) trains a deep learning model comprising a convolutional neural network to recognize objects of the same type as the object of interest in geospatial images.