Though the illustrations mimic those seen in compendiums of the natural world, they're actually the product generative adversarial networks (GANs), the same technology used in deepfakes. According to Crespo, the creations are designed to highlight the diversity of nature in addition to creating new "parallel" natural worlds.
"Computer vision and machine learning could offer a bridge between us and a speculative 'natures' that can only be accessed through high levels of parallel computation. Starting from the level of our known reality, we could ultimately be digitizing cognitive processes and utilizing them to feed new inputs into the biological world, which feeds back into a cycle."
Sofia Crespo