AI could be applied to falsify geospatial data. CycleGANs has proved itself in ‘remembering’ what it saw in the past, and then generating fake data in any fields like image, speech or music. To demonstrate the thrilling power of AI, this research explored the potentials of deep learning algorithms in capturing geographic features and creating fake satellite images according the learned ‘sense’.

Data and Method

Satellite images from Google Earth and positron (no label) basemap from CartoDB are used as input datasets. And CycleGANs is implemented to train the model and generate fake satellite images.

View details »

Training Process

Some results during training process. After the first epoch, the training model can learn and generate some geometric features. More details can be captured and created as the number of epoch increases.

View details »

Imaginary City

Fake datasets with ‘learned’ style from three big cities are generated through CycleGAN in Corvallis. It seems GANs can ‘remember’ a certain ‘sense of place’ and further apply that ‘sense’ to another place.

View details »