Assessing recreationists’ preferences of the landscape and species using crowdsourced images and machine learning

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autorschaft

  • Abdesslam Chai-allah
  • Johannes Hermes
  • Anne De La Foye
  • Zander S. Venter
  • Frédéric Joly
  • Gilles Brunschwig
  • Sandro Bimonte
  • Nathan Fox

Organisationseinheiten

Externe Organisationen

  • Université Blaise-Pascal
  • Norwegian Institute for Nature Research (NINA)
  • University of Michigan
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Aufsatznummer105315
FachzeitschriftLandscape and urban planning
Jahrgang257
Frühes Online-Datum9 Feb. 2025
PublikationsstatusElektronisch veröffentlicht (E-Pub) - 9 Feb. 2025

Abstract

Crowdsourced data are now well-established for assessing cultural ecosystem services (CES). In rural areas, understanding which land covers people prefer to recreate in, and how these land covers provide different CES, is necessary to support sustainable use. In this study, we aim to assess recreationists’ revealed preferences of landscape aesthetics and species observation as two CES, considering multiple land cover types in a rural area in France. This assessment was carried out using georeferenced images from two crowdsourced sources (Flickr and Wikiloc) and by analyzing their content using a machine-learning algorithm. We further developed a framework to classify images based on their content into CES-related images (those depicting landscapes or species) and non-CES-related images. Finally, we assessed how images depicting landscape aesthetics and species observation are distributed across the land covers visited by recreationists, and which species groups are the most photographed. Our results showed the dominance of images of open landscape views over close-up species images, and that grasslands are the primary providers of open views. In addition, we found that forests also provide open landscape views, suggesting that forests with gaps in canopy cover and viewpoints can be as important as grasslands in providing aesthetic views, especially in hilly landscapes. For species, the category “plants and flowers“ was the most photographed, followed by invertebrates and birds on Flickr, and domestic livestock on Wikiloc. This study provides insights into the importance of using multiple crowdsourced sources in CES assessment, providing critical insights for both landscape managers and conservationists.

ASJC Scopus Sachgebiete

Ziele für nachhaltige Entwicklung

Zitieren

Assessing recreationists’ preferences of the landscape and species using crowdsourced images and machine learning. / Chai-allah, Abdesslam; Hermes, Johannes; La Foye, Anne De et al.
in: Landscape and urban planning, Jahrgang 257, 105315, 05.2025.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Chai-allah, A., Hermes, J., La Foye, A. D., Venter, Z. S., Joly, F., Brunschwig, G., Bimonte, S., & Fox, N. (2025). Assessing recreationists’ preferences of the landscape and species using crowdsourced images and machine learning. Landscape and urban planning, 257, Artikel 105315. Vorabveröffentlichung online. https://doi.org/10.1016/j.landurbplan.2025.105315
Chai-allah A, Hermes J, La Foye AD, Venter ZS, Joly F, Brunschwig G et al. Assessing recreationists’ preferences of the landscape and species using crowdsourced images and machine learning. Landscape and urban planning. 2025 Mai;257:105315. Epub 2025 Feb 9. doi: 10.1016/j.landurbplan.2025.105315
Chai-allah, Abdesslam ; Hermes, Johannes ; La Foye, Anne De et al. / Assessing recreationists’ preferences of the landscape and species using crowdsourced images and machine learning. in: Landscape and urban planning. 2025 ; Jahrgang 257.
Download
@article{90d0bd53283b4428a1fa2b0b5773210d,
title = "Assessing recreationists{\textquoteright} preferences of the landscape and species using crowdsourced images and machine learning",
abstract = "Crowdsourced data are now well-established for assessing cultural ecosystem services (CES). In rural areas, understanding which land covers people prefer to recreate in, and how these land covers provide different CES, is necessary to support sustainable use. In this study, we aim to assess recreationists{\textquoteright} revealed preferences of landscape aesthetics and species observation as two CES, considering multiple land cover types in a rural area in France. This assessment was carried out using georeferenced images from two crowdsourced sources (Flickr and Wikiloc) and by analyzing their content using a machine-learning algorithm. We further developed a framework to classify images based on their content into CES-related images (those depicting landscapes or species) and non-CES-related images. Finally, we assessed how images depicting landscape aesthetics and species observation are distributed across the land covers visited by recreationists, and which species groups are the most photographed. Our results showed the dominance of images of open landscape views over close-up species images, and that grasslands are the primary providers of open views. In addition, we found that forests also provide open landscape views, suggesting that forests with gaps in canopy cover and viewpoints can be as important as grasslands in providing aesthetic views, especially in hilly landscapes. For species, the category “plants and flowers“ was the most photographed, followed by invertebrates and birds on Flickr, and domestic livestock on Wikiloc. This study provides insights into the importance of using multiple crowdsourced sources in CES assessment, providing critical insights for both landscape managers and conservationists.",
keywords = "Cultural ecosystem services, Image content analysis, Landscape aesthetics, Social media, Species observation",
author = "Abdesslam Chai-allah and Johannes Hermes and {La Foye}, {Anne De} and Venter, {Zander S.} and Fr{\'e}d{\'e}ric Joly and Gilles Brunschwig and Sandro Bimonte and Nathan Fox",
note = "Publisher Copyright: {\textcopyright} 2025 The Author(s)",
year = "2025",
month = feb,
day = "9",
doi = "10.1016/j.landurbplan.2025.105315",
language = "English",
volume = "257",
journal = "Landscape and urban planning",
issn = "0169-2046",
publisher = "Elsevier",

}

Download

TY - JOUR

T1 - Assessing recreationists’ preferences of the landscape and species using crowdsourced images and machine learning

AU - Chai-allah, Abdesslam

AU - Hermes, Johannes

AU - La Foye, Anne De

AU - Venter, Zander S.

AU - Joly, Frédéric

AU - Brunschwig, Gilles

AU - Bimonte, Sandro

AU - Fox, Nathan

N1 - Publisher Copyright: © 2025 The Author(s)

PY - 2025/2/9

Y1 - 2025/2/9

N2 - Crowdsourced data are now well-established for assessing cultural ecosystem services (CES). In rural areas, understanding which land covers people prefer to recreate in, and how these land covers provide different CES, is necessary to support sustainable use. In this study, we aim to assess recreationists’ revealed preferences of landscape aesthetics and species observation as two CES, considering multiple land cover types in a rural area in France. This assessment was carried out using georeferenced images from two crowdsourced sources (Flickr and Wikiloc) and by analyzing their content using a machine-learning algorithm. We further developed a framework to classify images based on their content into CES-related images (those depicting landscapes or species) and non-CES-related images. Finally, we assessed how images depicting landscape aesthetics and species observation are distributed across the land covers visited by recreationists, and which species groups are the most photographed. Our results showed the dominance of images of open landscape views over close-up species images, and that grasslands are the primary providers of open views. In addition, we found that forests also provide open landscape views, suggesting that forests with gaps in canopy cover and viewpoints can be as important as grasslands in providing aesthetic views, especially in hilly landscapes. For species, the category “plants and flowers“ was the most photographed, followed by invertebrates and birds on Flickr, and domestic livestock on Wikiloc. This study provides insights into the importance of using multiple crowdsourced sources in CES assessment, providing critical insights for both landscape managers and conservationists.

AB - Crowdsourced data are now well-established for assessing cultural ecosystem services (CES). In rural areas, understanding which land covers people prefer to recreate in, and how these land covers provide different CES, is necessary to support sustainable use. In this study, we aim to assess recreationists’ revealed preferences of landscape aesthetics and species observation as two CES, considering multiple land cover types in a rural area in France. This assessment was carried out using georeferenced images from two crowdsourced sources (Flickr and Wikiloc) and by analyzing their content using a machine-learning algorithm. We further developed a framework to classify images based on their content into CES-related images (those depicting landscapes or species) and non-CES-related images. Finally, we assessed how images depicting landscape aesthetics and species observation are distributed across the land covers visited by recreationists, and which species groups are the most photographed. Our results showed the dominance of images of open landscape views over close-up species images, and that grasslands are the primary providers of open views. In addition, we found that forests also provide open landscape views, suggesting that forests with gaps in canopy cover and viewpoints can be as important as grasslands in providing aesthetic views, especially in hilly landscapes. For species, the category “plants and flowers“ was the most photographed, followed by invertebrates and birds on Flickr, and domestic livestock on Wikiloc. This study provides insights into the importance of using multiple crowdsourced sources in CES assessment, providing critical insights for both landscape managers and conservationists.

KW - Cultural ecosystem services

KW - Image content analysis

KW - Landscape aesthetics

KW - Social media

KW - Species observation

UR - http://www.scopus.com/inward/record.url?scp=85217109121&partnerID=8YFLogxK

U2 - 10.1016/j.landurbplan.2025.105315

DO - 10.1016/j.landurbplan.2025.105315

M3 - Article

AN - SCOPUS:85217109121

VL - 257

JO - Landscape and urban planning

JF - Landscape and urban planning

SN - 0169-2046

M1 - 105315

ER -