Speaking: Sabrina Marx & Oliver Fritz Heidelberg Institute for Geoinformation Technology at Heidelberg University
The Permafrost Discovery Gateway hosts a monthly webinar series on the second Thursday of each month at 9:00 am Alaska time, raising topics of interest to the permafrost community. The webinar aims to 1) connect the international science community interested in big data remote sensing of permafrost landscapes, and 2) provide the Permafrost Discovery Gateway development team with end-user stories (by the presenter and webinar participants), such as exploring tools the community needs to create and explore big data.
Abstract
People living in the Arctic witness dramatic landscape changes affecting their livelihood and subsistence, especially in terms of permafrost thaw. By combining Citizien Science and Machine Learning methods, we aim to support the monitoring of surface changes attributed to permafrost thaw. Together with young citizen scientists from schools in Northwest Canada and Germany, the ongoing project UndercoverEisAgenten aspires to empower Arctic communities to enhance the data basis of permafrost degradation. During the project, students from both countries exchange and discuss climate warming, permafrost and the associated regional and global challenges. A core element of the project is the development of a web application that enables citizen scientists to map landscape changes. To this end, students in Canada operate drones to capture high-resolution aerial imagery of the Arctic land surface. The imagery is processed and divided into manageable batches of simple mapping tasks (“micro tasks”). Through volunteer contributions , a unique reference data set is generated to support efforts to better understand and monitor permafrost degradation. Thereby, we build on expertise gained from MapSwipe, an open-source mobile app designed to make mapping around the world more coordinated and efficient with about 30,000 volunteers and 3 million square kilometers already mapped. We will present the current status of the UndercoverEisAgenten mapping application, discuss challenges regarding data quality of crowdsourced data, and envision future combinations of automatic and human-interactive approaches for mapping permafrost structures.