AQUATIC SCIENCES AND ENGINEERING, cilt.41, sa.1, ss.41-48, 2026 (ESCI, Scopus, TRDizin)
Microplastics (MPs) contamination has become a pressing issue in freshwater ecosystems, yet existingstudies in T & uuml;rkiye remain geographically uneven and concentrated in only a few basins. This study brings together data from previously published investigations to create a harmonized national-scale dataset of 79 sediment records, each containing regional, seasonal, and environmental descriptors. Sediments were chosen as the focus because they act as long-term sinks for MPs, offering a more stable and comparable basis than water or biota samples for assessing spatial and temporal pollution trends. By compiling information from different studies into a consistent format, the dataset allows more reliable cross-site evaluations of MPs contamination in freshwater ecosystems across T & uuml;rkiye. To explore predictive capacity, three machine learning (ML) algorithms (Ridge Regression, Random Forest, and Histogram-based Gradient Boosting Regressor) were applied. Model performance was assessed using both 5-and 10-fold cross-validation and independent test sets, evaluated with R2, RMSE, and MAE metrics. Among these, the Histogram-based Gradient Boosting Regressor showed the highestaccuracy (R2 = 0.77), successfully capturing nonlinear relationships even with the relatively small dataset. Interpretability analyses highlighted region and season as the strongest predictors. Elevated MP concentration was consistently found in the Marmara Region and during the summer, reflecting combined pressures from industrial activity, dense urbanization, and seasonal factors such as increased tourism and hydrological changes. Overall, this study provides the first harmonized dataset of MPs concentration in freshwater sediments in T & uuml;rkiye. It also demonstrates the usefulness of predictive modelling and explainable artificial intelligence (XAI) for understanding pollution dynamics and supporting evidence-based strategies for environmental monitoring and management.