Integrating functional trait diversity and machine learning for ecological status assessment of Turkish coastal waters under the EU water framework directive
Estuarine, Coastal and Shelf Science, cilt.341, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 341
- Basım Tarihi: 2026
- Doi Numarası: 10.1016/j.ecss.2026.110107
- Dergi Adı: Estuarine, Coastal and Shelf Science
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, BIOSIS, Environment Index, Geobase, INSPEC, Zoological Record, Academic Search Ultimate (EBSCO)
- Anahtar Kelimeler: ANFIS, Biodiversity indices, Biomonitoring, Ecological status assessment, Phytoplankton community structure, Trait-based ecology
- Ondokuz Mayıs Üniversitesi Adresli: Evet
Özet
Understanding the functional attributes of phytoplankton communities is critical for improving ecological status assessments in coastal waters. This study presents the first comprehensive assessment of phytoplankton functional diversity (FD) alongside taxonomic biodiversity across Turkish coastal waters using an integrated analytical approach that combines ordination techniques, trait-based metrics, and machine learning (ML) algorithms. Phytoplankton biomass and trait data collected from 78 coastal stations (2016–2020) were used to compute Functional Richness (FRic), Functional Evenness (FEve), Functional Divergence (FDiv), Shannon diversity, Menhinick's richness, and Pielou's evenness. Community composition was characterised using Principal Coordinate Analysis (PCoA) based on (Bray–Curtis) dissimilarities, while major environmental gradients were identified through Principal Component Analysis (PCA). FDiv was the most predictable index, with SVR achieving the highest accuracy (R2 = 0.847), closely followed by Random Forest (R2 = 0.843) and Gradient Boosting (R2 = 0.827). The hybrid framework introduced here provides a transferable, early-warning tool for ecological diagnostics and establishes a robust foundation for next-generation coastal biomonitoring.The findings of this study have direct implications for policymakers and environmental managers, particularly within the implementation framework of the European Union Water Framework Directive (EU WFD).