Spotting A Tree From A Pixel – Ground Truth and Posthuman Visions

The video essay contemplates the collaboration between me, a photographer, with remote sensing researchers from the Department of Geoinformatics at Aalto University in the ongoing project Ground Truth. Ground Truth is a photography project about ‘seeing something when there is nothing there.’ Following the research group set out to overcome the spatial resolution limit of satellite imagery, this project investigates cutting-edge imaging techniques of forests while looking back at photography’s love affair with natural landscapes. The project shed light on a new visuality in which the scientists move through multiple scales, from pine needles to the entire forest landscape, to infer information hidden behind a pixel. The interdisciplinary dialogue on computational photography and hyperspectral imaging brought together two distinct ways of looking at the forest, one symbolized by the camera, another by the terrestrial laser scanner, to illustrate an algorithmic image system that increasingly escapes the human scale.

In everyday language, the term ground truth refers to a first-hand experience. Ground Truth connotes the documentary tradition and the act of witnessing. In remote sensing, however, ground truth relates to data collected on-site, which are then used to calibrate, to build models, to predict, to interpret, to decipher information from images, in this case, satellite images. Similarly, the collaboration reveals another operational layer of photography beyond the immediately visible, illustrating an expanded notion of photography in contemporary discourse. Ground Truth interweaves archival imagery, documentary photography, experiment dataset, and 3D digital art to demonstrate a complex image system composed of different mediums and scales. The constellation of materials contrasts the representational approach of drawing and photography with the data-oriented and algorithmic approach of computer-aided seeing. The parallel reading of the same landscape contextualizes an epistemological regime that emphasizes computational models rather than optical lenses.