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

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

Geography

International Institute for Applied Systems Analysis, Laxenburg
SUNY Buffalo
University of Ljubljana

Research output: Contribution to journal › Review article › peer-review

2 Scopus citations

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.

Original language	English
Article number	111919
Journal	iScience
Volume	28
Issue number	3
DOIs	https://doi.org/10.1016/j.isci.2025.111919
State	Published - Mar 21 2025

Keywords

Cartography
Earth sciences
Environmental science
Remote sensing

Access to Document

10.1016/j.isci.2025.111919

Cite this

See, L., Chen, Q., Crooks, A., Laso Bayas, J. C., Fraisl, D., Fritz, S., Georgieva, I., Hager, G., Hofer, M., Lesiv, M., Malek, Ž., Milenković, M., Moorthy, I., Orduña-Cabrera, F., Pérez-Guzmán, K., Schepaschenko, D., Shchepashchenko, M., Steinhauser, J., & McCallum, I. (2025). New directions in mapping the Earth's surface with citizen science and generative AI. iScience, 28(3), Article 111919. https://doi.org/10.1016/j.isci.2025.111919

@article{60f534ab1b2b413da1e7ae06a8983169,

title = "New directions in mapping the Earth's surface with citizen science and generative AI",

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",

author = "Linda See and Qingqing Chen and Andrew Crooks and \{Laso Bayas\}, \{Juan Carlos\} and Dilek Fraisl and Steffen Fritz and Ivelina Georgieva and Gerid Hager and Martin Hofer and Myroslava Lesiv and {\v Z}iga Malek and Milutin Milenkovi{\'c} and Inian Moorthy and Fernando Ordu{\~n}a-Cabrera and Katya P{\'e}rez-Guzm{\'a}n and Dmitry Schepaschenko and Maria Shchepashchenko and Jan Steinhauser and Ian McCallum",

note = "Publisher Copyright: {\textcopyright} 2025 The Author(s)",

year = "2025",

month = mar,

day = "21",

doi = "10.1016/j.isci.2025.111919",

language = "English",

volume = "28",

journal = "iScience",

issn = "2589-0042",

publisher = "Elsevier Inc.",

number = "3",

}

See, L, Chen, Q, Crooks, A, Laso Bayas, JC, Fraisl, D, Fritz, S, Georgieva, I, Hager, G, Hofer, M, Lesiv, M, Malek, Ž, Milenković, M, Moorthy, I, Orduña-Cabrera, F, Pérez-Guzmán, K, Schepaschenko, D, Shchepashchenko, M, Steinhauser, J & McCallum, I 2025, 'New directions in mapping the Earth's surface with citizen science and generative AI', iScience, vol. 28, no. 3, 111919. https://doi.org/10.1016/j.isci.2025.111919

TY - JOUR

T1 - New directions in mapping the Earth's surface with citizen science and generative AI

AU - See, Linda

AU - Chen, Qingqing

AU - Crooks, Andrew

AU - Laso Bayas, Juan Carlos

AU - Fraisl, Dilek

AU - Fritz, Steffen

AU - Georgieva, Ivelina

AU - Hager, Gerid

AU - Hofer, Martin

AU - Lesiv, Myroslava

AU - Malek, Žiga

AU - Milenković, Milutin

AU - Moorthy, Inian

AU - Orduña-Cabrera, Fernando

AU - Pérez-Guzmán, Katya

AU - Schepaschenko, Dmitry

AU - Shchepashchenko, Maria

AU - Steinhauser, Jan

AU - McCallum, Ian

PY - 2025/3/21

Y1 - 2025/3/21

N2 - 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.

AB - 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.

KW - Cartography

KW - Earth sciences

KW - Environmental science

KW - Remote sensing

UR - https://www.scopus.com/pages/publications/85217909053

U2 - 10.1016/j.isci.2025.111919

DO - 10.1016/j.isci.2025.111919

M3 - Review article

AN - SCOPUS:85217909053

SN - 2589-0042

VL - 28

JO - iScience

JF - iScience

IS - 3

M1 - 111919

ER -

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

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this