Integrating crowdsourced social media and machine learning to map cultural ecosystem services: insights from the Seyhan Basin, Türkiye
Urban Ecosystems, cilt.29, sa.5, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 29 Sayı: 5
- Basım Tarihi: 2026
- Doi Numarası: 10.1007/s11252-026-02151-9
- Dergi Adı: Urban Ecosystems
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, ABI/INFORM, BIOSIS, CAB Abstracts, Environment Index, Zoological Record, Natural Science Collection (ProQuest), Social Science Premium Collection (ProQuest), Biomedical Reference Collection: Corporate Edition (EBSCO), Political Science Database (ProQuest)
- Anahtar Kelimeler: Crowdsourced data, Cultural ecosystem services, Flickr, MaxEnt, Seyhan Basin, Spatial modelling
- Çukurova Üniversitesi Adresli: Evet
Özet
Cultural Ecosystem Services (CES), the non-material benefits people derive from nature, are essential to human well-being, identity, and sense of place. Yet their intangible and perception-based nature continues to challenge spatial quantification and policy integration. This study develops a data-driven framework for mapping CES in the Seyhan Basin, Türkiye, by integrating crowdsourced Flickr geotags with environmental and socio-cultural predictors using the Maximum Entropy (MaxEnt) algorithm. Four CES domains, cultural heritage, recreation, spirituality, and landscape aesthetics, were modelled based on variables including land use and land cover, accessibility, elevation, hydrological proximity, and population density. The model achieved high predictive accuracy across all CES categories (AUC = 0.86–0.96), demonstrating strong reliability and minimal overfitting. Accessibility emerged as the dominant driver of heritage and spiritual services, while topographic complexity and water proximity shaped aesthetic and recreational distributions. The resulting CES hotspot maps revealed a dual spatial structure: human-centered clusters concentrated around Adana, Niğde, and Kayseri, and nature-centered clusters distributed across the Taurus Mountains and Aladağlar National Park. These findings underscore the interplay between accessibility and environmental diversity in shaping cultural landscapes. The proposed workflow provides a scalable, reproducible, and cost-efficient method for embedding CES into sustainable tourism, heritage management, and regional planning, advancing the global application of machine-learning-based ecosystem service mapping in Mediterranean socio-ecological systems.