New directions in mapping the Earth's surface with citizen science and generative AI

Linda See; Qingqing Chen; Andrew Crooks; Juan Carlos Laso Bayas; Dilek Fraisl; Steffen Fritz; Ivelina Georgieva; Gerid Hager; Martin Hofer; Myroslava Lesiv; Žiga Malek; Milutin Milenković; Inian Moorthy; Fernando Orduña-Cabrera; Katya Pérez-Guzmán; Dmitry Schepaschenko; Maria Shchepashchenko; Jan Steinhauser; Ian McCallum

doi:10.1016/j.isci.2025.111919

New directions in mapping the Earth's surface with citizen science and generative AI

iScience. 2025 Jan 30;28(3):111919. doi: 10.1016/j.isci.2025.111919. eCollection 2025 Mar 21.

Authors

Linda See¹, Qingqing Chen², Andrew Crooks², Juan Carlos Laso Bayas¹, Dilek Fraisl¹, Steffen Fritz¹, Ivelina Georgieva¹, Gerid Hager¹, Martin Hofer¹, Myroslava Lesiv¹, Žiga Malek^{1

3}, Milutin Milenković¹, Inian Moorthy¹, Fernando Orduña-Cabrera¹, Katya Pérez-Guzmán¹, Dmitry Schepaschenko¹, Maria Shchepashchenko¹, Jan Steinhauser¹, Ian McCallum¹

Affiliations

¹ Novel Data Ecosystems for Sustainability (NODES) Research Group, International Institute for Applied Systems Analysis (IIASA), Laxenburg, Lower Austria 2361, Austria.
² Department of Geography, University at Buffalo, The State University of New York, Buffalo, NY 14261, USA.
³ Department of Landscape Architecture, Biotechnical Faculty, University of Ljubljana, Jamnikarjeva 101, 1000 Ljubljana, Slovenia.

Abstract

As more satellite imagery has become openly available, efforts in mapping the Earth's surface have accelerated. Yet the accuracy of these maps is still limited by the lack of in situ data needed to train machine learning algorithms. Citizen science has proven to be a valuable approach for collecting in situ data through applications like Geo-Wiki and Picture Pile, but better approaches for optimizing volunteer time are still required. Although machine learning is being used in some citizen science projects, advances in generative artificial intelligence (AI) are yet to be fully exploited. This paper discusses how generative AI could be harnessed for land cover/land use mapping by enhancing citizen science approaches with multi-modal large language models (MLLMs), including improvements to the spatial awareness of AI.

Keywords: Cartography; Earth sciences; Environmental science; Remote sensing.

Publication types

Review