The Latentscape AP Series is an exploration of imaginary virtual landscapes full of complex shapes, cracks, sediments and flows. The works are generated with the help of GANs, an algorithm commonly used in Artificial Intelligence, and trained with custom Digital Elevation Model datasets, which capture topographical surfaces. Each piece is immersed in music produced by SampleRNN architecture, which is trained with sounds from different musical traditions, radio transmissions and field recordings, distant in space and time. The landscapes and music, with their topological and timbral diversity, depict the meeting points of human data as the fusion of thoughts, feelings and experiences, and not just mere digits and numbers.
Latentscape AP 1 depicts a landscape in fire and ice. A strong, lava red mountain range clashes, yet coexists with its snow-topped peaks and frozen valleys. Against an otherworldly soundtrack, the viewer is plunged into an ethereal world where two meteorological extremities coincide.