Terrapattern is a tool for exploring the unmapped and the unmappable: a system for finding ?"more like this, please" in satellite photos. It can also be described as "a visual search engine for satellite imagery", "similar-image search for satellite photos", or "a prototype for geospatial query-by-example".
Terrapattern is an open-source software project created by a collaborative team of artists, creative technologists, and students. It is an experimental research provocation, developed in a university setting, with the aim of presenting a new way of exploring, understanding, and visually organizing the world. Developed at the Frank-Ratchye STUDIO for Creative Inquiry at Carnegie Mellon University with support from the John S. and James L. Knight Foundation, Terrapattern went live on May 24th, 2016.
Terrapattern is intended to democratize geospatial intelligence, and to prompt new thinking about how we see our planet. Our system is particularly well-suited to locate things that aren’t usually indicated on maps, such as specialized nonbuilding structures and other forms of soft infrastructure. We hope it will help citizen scientists, artists, humanitarians, journalists, and other curious people to identify and track "patterns of interest".
Terrapattern provides an open-ended interface for geospatial query-by-example. Simply click an interesting spot on Terrapattern’s map, and it will find places that look similar. While related research projects focus on detecting specific things (like logging roads or strip-mines), Terrapattern is designed for general-purpose search, allowing users to discover categories for which it wasn’t specifically trained. Our goal is to provide a geospatial software tool that makes it easy for everyday people to specify a thing that they are interested in; to automatically find more examples of that thing; and to provide the locations of those instances in a common data format that easily allows for further examination.
We believe Terrapattern is important because it is open-source, open-access, and open-ended. In this way, Terrapattern also operates as a revelatory artwork: a "panoptic perceptron" for open-ended play, and an absurdist tool to lay bare the rhetoric of 20th-century formalist analysis in urban planning and architecture.
Motivation
It has been predicted that, within the next three years, access to daily-updated, whole-earth satellite imagery with sub-meter resolution will become widely available online. There will be many important stories about natural and human activities latent in this data. Without special effort, however, it is doubtful that this imagery will also have the information layers necessary to make such stories discoverable.
In light of this, the Terrapattern prototype is intended to demonstrate a workflow by which users—such as journalists, citizen scientists, humanitarian agencies, social justice activists, archaeologists, urban planners, and other researchers—can easily search for visually-consistent patterns of interest. We are particularly keen to help people locate, characterize and track indicators which have not been detected or measured previously, and which have sociological, humanitarian, scientific, or cultural significance.
In developing Terrapattern, we sought to test the following hypotheses:
That there are undiscovered patterns of activity that are only visible from the vantage point of satellite imagery;
That these patterns can offer insight into trends, stories and phenomena of social, economic, ecological, anthropological, humanitarian, scientific, or other cultural interest;
That there exists a subset of such patterns in satellite imagery which, because of their repetition and visual consistency, lend themselves particularly well to automated detection and analysis by means of machine learning and computer vision;
That there is demand for information about these patterns among domain experts, as well as among journalists, citizen scientists, humanitarian NGO’s, and the general public;
And that it is possible to create software tools which make such workflows easy and reliable.
(source: Levin, G., Newbury, D., McDonald, K., Alvarado, I., Tiwari, A., and Zaheer, M. "Terrapattern: Open-Ended, Visual Query-By-Example for Satellite Imagery using Deep Learning". http://terrapattern.com, 24 May 2016.)