Prediction of Microplastic Concentrations in Freshwater Sediments of Türkiye Using Machine Learning and Explainable AI

Abstract

Microplastics (MPs) contamination has become a pressing issue in freshwater ecosystems, yet existing studies in Türkiye 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 Türkiye. 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 highest accuracy (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 Türkiye. 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.

Keywords

• Microplastics pollution
• Freshwater ecosystems
• Machine learning (ML)
• Explainable artificial intelligence (XAI)
• Türkiye

References

1. Andrady, A. L. (2011). Microplastics in the marine environment. Marine Pollution Bulletin, 62(8), 1596-1605. https://doi.org/https://doi.org/10.1016/j.marpolbul.2011.05.030 google scholar
2. Bai, C. L., Liu, L. Y., Hu, Y. B., Zeng, E. Y., & Guo, Y. (2022). Microplastics: A review of analytical methods, occurrence and characteristics in food, and potential toxicities to biota. Sci Total Environ, 806(Pt 1), 150263. https://doi.org/10.1016/j.scitotenv.2021.150263 google scholar
3. Bi, S., Wu, R., Liu, X., Wei, P., Zhao, S., Ma, X., Liu, E., Chen, H., & Xu, J. (2025). Integration of machine learning and meta-analysis reveals the behaviors and mechanisms of antibiotic adsorption on microplastics. Journal of Hazardous Materials, 489, 137479. https://doi.org/https://doi.org/10.1016/j.jhazmat.2025.137479 google scholar
4. Bishop, C. M., & Nasrabadi, N. M. (2006). Pattern recognition and machine learning (Vol. 4). Springer. google scholar
5. Browne, M. A., Crump, P., Niven, S. J., Teuten, E., Tonkin, A., Galloway, T., & Thompson, R. (2011). Accumulation of microplastic on shorelines woldwide: sources and sinks. Environ Sci Technol, 45(21), 9175-9179. https://doi.org/10.1021/es201811s google scholar
6. Egwu, L. S., Enayaba, O. F., Ajiboye, A. A., Damoye, T., Ogundeji, I. S., & Agbams, P. (2024). A REVIEW OF MACHINE LEARNING TECHNIQUES APPLICATIONS IN ENVIRONMENTAL SCIENCE. International Journal of Science Research and Technology, 6(9). https://doi.org/10.70382/tijsrat.v06i9.002 google scholar
7. Gao, S., Orlowski, N., Bopf, F. K., & Breuer, L. (2024). A review on microplastics in major European rivers. WIREs Water, 11(3), e1713. https://doi.org/https://doi.org/10.1002/wat2.1713 google scholar
8. Godasiaei, S. H. (2025). Predictive modeling of microplastic adsorption in aquatic environments using advanced machine learning models. Science of The Total Environment, 958, 178015. https://doi.org/https://doi.org/10.1016/j.scitotenv.2024.178015 google scholar

9. Gündoğdu, S., & Çevik, C. (2017). Micro- and mesoplastics in Northeast Levantine coast of Turkey: The preliminary results from surface samples. Marine Pollution Bulletin, 118(1), 341-347. https://doi.org/https://doi.org/10.1016/j.marpolbul.2017.03.002 google scholar
10. Hartz, L., Grabinski, L., & Salameh, S. (2025). Microplastic pollution in aquatic environments: a meta-analysis of influencing factors and methodological recommendations [Systematic Review]. Frontiers in Environmental Science, Volume 13 - 2025. https://doi.org/10.3389/fenvs.2025.1600570 google scholar
11. Horton, A. A., Walton, A., Spurgeon, D. J., Lahive, E., & Svendsen, C. (2017). Microplastics in freshwater and terrestrial environments: Evaluating the current understanding to identify the knowledge gaps and future research priorities. Science of The Total Environment, 586, 127-141. https://doi.org/https://doi.org/10.1016/j.scitotenv.2017.01.190 google scholar
12. Karbalaei, S., Golieskardi, A., Hamzah, H. B., Abdulwahid, S., Hanachi, P., Walker, T. R., & Karami, A. (2019). Abundance and characteristics of microplastics in commercial marine fish from Malaysia. Mar Pollut Bull, 148, 5-15. https://doi.org/10.1016/j.marpolbul.2019.07.072 google scholar
13. Khanam, M. M., Uddin, M. K., & Kazi, J. U. (2025). Advances in machine learning for the detection and characterization of microplastics in the environment [Review]. Frontiers in Environmental Science, Volume 13 - 2025. https://doi.org/10.3389/fenvs.2025.1573579 google scholar
14. Li, J., Liu, H., & Paul Chen, J. (2018). Microplastics in freshwater systems: A review on occurrence, environmental effects, and methods for microplastics detection. Water Research, 137, 362-374. https://doi.org/https://doi.org/10.1016/j.watres.2017.12.056 google scholar
15. Liang, C., Zhang, Z., Li, Y., Wang, Y., He, M., Xia, F., & Wu, H. (2025). Simulation, prediction and optimization for synthesis and heavy metals adsorption of schwertmannite by machine learning. Environmental Research, 265, 120471. https://doi.org/https://doi.org/10.1016/j.envres.2024.120471 google scholar
16. Makhanya, N. P., Kumi, M., Mbohwa, C., & Oboirien, B. (2025). Application of machine learning in adsorption energy storage using metal organic frameworks: A review. Journal of Energy Storage, 111, 115363. https://doi.org/https://doi.org/10.1016/j.est.2025.115363 google scholar
17. Manual, A. B. s. (2013). An introduction to statistical learning with applications in R. google scholar
18. Meng, M., Zhong, R., & Wei, Z. (2020). Prediction of methane adsorption in shale: Classical models and machine learning based models. Fuel, 278, 118358. https://doi.org/https://doi.org/10.1016/j.fuel.2020.118358 google scholar
19. Papparotto, M., Gavazza, C., Matteotti, P., & Fambri, L. (2025). Seasonal Comparative Monitoring of Plastic and Microplastic Pollution in Lake Garda (Italy) Using Seabin During Summer–Autumn 2024. Microplastics, 4(3), 44. https://www.mdpi.com/2673-8929/4/3/44 google scholar
20. Saarni, S., Soininen, T., Uurasjärvi, E., Hartikainen, S., Meronen, S., Saarinen, T., & Koistinen, A. (2023). Seasonal variation observed in microplastic deposition rates in boreal lake sediments. Journal of Soils and Sediments, 23(4), 1960-1970. https://doi.org/10.1007/s11368-023-03465-3 google scholar
21. Schiller, J., Stiller, S., & Ryo, M. (2025). Artificial intelligence in environmental and Earth system sciences: explainability and trustworthiness. Artificial Intelligence Review, 58(10), 316. https://doi.org/10.1007/s10462-025-11165-2 google scholar
22. Sharma, S., & Chatterjee, S. (2017). Microplastic pollution, a threat to marine ecosystem and human health: a short review. Environmental Science and Pollution Research, 24(27), 21530-21547. https://doi.org/10.1007/s11356-017-9910-8 google scholar
23. Talbot, R., Granek, E., Chang, H., Wood, R., & Brander, S. (2022). Spatial and temporal variations of microplastic concentrations in Portland's freshwater ecosystems. Science of The Total Environment, 833, 155143. https://doi.org/https://doi.org/10.1016/j.scitotenv.2022.155143 google scholar
24. Tedoldi, D., Kim, B., Sandoval, S., Forquet, N., & Tassin, B. (2025). Position paper: Common mistakes and solutions for a better use of correlation- and regression-based approaches in environmental sciences. Environmental Modelling & Software, 192, 106526. https://doi.org/https://doi.org/10.1016/j.envsoft.2025.106526 google scholar
25. Tran, H.-T., Hadi, M., Nguyen, T. T. H., Hoang, H. G., Nguyen, M.-K., Nguyen, K. N., & Vo, D.-V. N. (2023). Machine learning approaches for predicting microplastic pollution in peatland areas. Marine Pollution Bulletin, 194, 115417. https://doi.org/https://doi.org/10.1016/j.marpolbul.2023.115417 google scholar
26. Weber, F., Zinnen, A., & Kerpen, J. (2023). Development of a machine learning-based method for the analysis of microplastics in environmental samples using μ-Raman spectroscopy. Microplastics and Nanoplastics, 3(1), 9. https://doi.org/10.1186/s43591-023-00057-3 google scholar
27. Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 30, 79-82. https://www.int-res.com/abstracts/cr/v30/cr030079 google scholar
28. Wright, S. L., & Kelly, F. J. (2017). Plastic and Human Health: A Micro Issue? Environ Sci Technol, 51(12), 6634-6647. https://doi.org/10.1021/acs.est.7b00423 google scholar
29. Zhang, W., Huang, W., Tan, J., Huang, D., Ma, J., & Wu, B. (2023). Modeling, optimization and understanding of adsorption process for pollutant removal via machine learning: Recent progress and future perspectives. Chemosphere, 311, 137044. https://doi.org/https://doi.org/10.1016/j.chemosphere.2022.137044 google scholar