Search

Menu
Search
in Ecology

Forecasting toxic metal concentrations in an inland sea ecosystem with machine learning algorithms

188 Views


Abstract

In recent years, statistical and data-driven modeling approaches have been increasingly employed to predict element concentrations and to examine relationships among environmental features. In this context, the integration of feature selection techniques with machine learning models enhances model generalization and reduces model complexity by enabling the identification of key elements that are strongly associated with the target feature. This study applies machine learning models to investigate the relationships between Aluminum (Al) and other elements and to predict Al concentration levels in an inland marine ecosystem. Specifically, the study evaluates whether accurate predictions can be achieved using a reduced subset of informative elements rather than the full feature set. The findings demonstrate that machine learning methods, when combined with feature selection, can successfully predict Al concentrations while yielding more interpretable models based on a limited number of significant elements.

Data Availability

The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request.

References

  1. Arslan, H., Agir, A. & Demir, G. Impacts of PM10 exposure on hospitalization for acute bronchitis in Ankara, Türkiye. Front. Life Sci. Relat. Technol. 5, 1–5 (2024).

    Google Scholar 

  2. Gjergjizi Nallbani, B. et al. Utilizing a medicinal plant and soil assays for heavy metal pollution assessment and its impacts in a Turkish Industrial Zone. Spectrosc. Lett. 1–18 (2024).

  3. Banaee, M., Zeidi, A., Mikušková, N. & Faggio, C. Assessing metal toxicity on crustaceans in aquatic ecosystems: a comprehensive review. Biol. Trace Element Res. 1–19 (2024).

  4. Fulke, A. B., Ratanpal, S. & Sonker, S. Understanding heavy metal toxicity: Implications on human health, marine ecosystems and bioremediation strategies. Mar. Pollut. Bull. 206, 116707 (2024).

    Google Scholar 

  5. Jean-Lavenir, N. M. et al. Potentially toxic metals contamination in stream sediments of MBAL area (Pan-African fold belt, Cameroon). Discov. Geosci. 2, 15 (2024).

    Google Scholar 

  6. Prabakaran, K., Sompongchaiyakul, P., Bureekul, S., Wang, X. & Charoenpong, C. Heavy metal bioaccumulation and risk assessment in fishery resources from the Gulf of Thailand. Mar. Pollut. Bull. 198, 115864 (2024).

    Google Scholar 

  7. Borrell, A. et al. High aluminum content in bone of marine mammals and its relation with source levels and origin. Environ. Pollut. 331, 121936 (2023).

    Google Scholar 

  8. Yazicioglu, H. et al. Physiological alterations and genotoxic damage under combined aluminum and cadmium treatments in Bryophyllum daigremontianum clones. Mol. Biol. Rep. 51, 1–21 (2024).

    Google Scholar 

  9. Botté, A., Zaidi, M., Guery, J., Fichet, D. & Leignel, V. Aluminium in aquatic environments: Abundance and ecotoxicological impacts. Aquat. Ecol. 56, 751–773 (2022).

    Google Scholar 

  10. Tiwari, A. K., Pal, D. B. & Prasad, N. Agricultural waste biomass utilization in waste water treatment. In Utilization of Waste Biomass in Energy, Environment and Catalysis, 19–41 (CRC Press, 2022).

  11. Islam, M. S. et al. Contamination and ecological risk assessment of Cr, As, Cd and Pb in water and sediment of the southeastern Bay of Bengal coast in a developing country. Mar. Pollut. Bull. 197, 115720 (2023).

    Google Scholar 

  12. Lao, Y., Ma, J., Pan, K., Chen, F. & Zhang, Z. A brief review of effects of aluminum on marine diatoms. Bull. Environ. Contam. Toxicol. 113, 31 (2024).

    Google Scholar 

  13. Sáez-Guinoa, J., García-Franco, E., Llera-Sastresa, E. & Romeo, L. M. The effects of energy consumption of alumina production in the environmental impacts using life cycle assessment. Int. J. Life Cycle Assess. 29, 380–393 (2024).

    Google Scholar 

  14. Santore, R. C. et al. Development and application of a biotic ligand model for predicting the chronic toxicity of dissolved and precipitated aluminum to aquatic organisms. Environ. Toxicol. Chem. 37, 70–79 (2018).

    Google Scholar 

  15. Feng, J., Li, X., Yang, Y. & Zhou, Z. Preparation of low-cost aluminum-loaded longan shell adsorbent for fluoride removal: Experimental and modeling studies. J. Environ. Chem.Eng. 10, 108917 (2022).

    Google Scholar 

  16. Wang, J., Liu, Q., Xu, L., Siddique, M. S. & Yu, W. Impacts of water hardness on coagulation-UF-NF process using aluminum salts. Sep. Purif. Technol. 314, 123611 (2023).

    Google Scholar 

  17. Gantayat, R. R. & Elumalai, V. Salinity-induced changes in heavy metal behavior and mobility in semi-arid coastal aquifers: A comprehensive review. Water 16, 1052 (2024).

    Google Scholar 

  18. Ghani, S. A. A. Trace metals in seawater, sediments and some fish species from Marsa Matrouh Beaches in north-western Mediterranean coast. Egypt. The Egyptian J. Aquat. Res. 41, 145–154 (2015).

  19. Angel, B. M., Apte, S. C., Batley, G. E. & Golding, L. A. Geochemical controls on aluminium concentrations in coastal waters. Environ. Chem. 13, 111–118 (2015).

    Google Scholar 

  20. Abdelaal, A., Abdelkader, A. I., Alshehri, F., Elatiar, A. & Almadani, S. A. Assessment and spatiotemporal variability of heavy metals pollution in water and sediments of a coastal landscape at the Nile Delta. Water 14, 3981 (2022).

    Google Scholar 

  21. Mbandzi-Phorego, N., Puccinelli, E., Pieterse, P. P., Ndaba, J. & Porri, F. Metal bioaccumulation in marine invertebrates and risk assessment in sediments from South African coastal harbours and natural rocky shores. Environ. Pollut. 124230 (2024).

  22. Walton, R. C., McCrohan, C. R., Livens, F. & White, K. N. Trophic transfer of aluminium through an aquatic grazer-omnivore food chain. Aquat. Toxicol. 99, 93–99 (2010).

    Google Scholar 

  23. Hardisson, A., Revert, C., Gonzales-Weler, D. & Rubio, C. Aluminium exposure through the diet. Food Sci. Nutr 3, 19 (2017).

    Google Scholar 

  24. Barnhart, B., Flinders, C., Ragsdale, R., Johnson, G. & Wiegand, P. Deriving human health and aquatic life water quality criteria in the United States for bioaccumulative substances: A historical review and future perspective. Environ. Toxicol. Chem. 40, 2394–2405 (2021).

    Google Scholar 

  25. Alasfar, R. H. & Isaifan, R. J. Aluminum environmental pollution: The silent killer. Environ. Sci. Pollut. Res. 28, 44587–44597 (2021).

    Google Scholar 

  26. Bonfiglio, R., Scimeca, M. & Mauriello, A. The impact of aluminum exposure on human health. Arch. Toxicol. 97, 2997–2998 (2023).

    Google Scholar 

  27. Ergashov, A. The general effect of aluminum on the body. Int. J. Med. Sci. Clin. Res. 3, 90–95 (2023).

    Google Scholar 

  28. Yilmaz, N., Ozyigit, I. I., Dogan, I., Demir, G. & Yalcin, I. E. A case study performed in Küçükçekmece Lagoon channel/Istanbul, Turkey: How the heavy metal contamination and the seasonal variations on phytoplankton composition influence water quality. Desalin. Water Treat. 239, 126–136 (2021).

    Google Scholar 

  29. Trevizani, T. H., Domit, C., Santos, M. C. D. O. & Figueira, R. C. L. Bioaccumulation of heavy metals in estuaries in the southwest Atlantic Ocean. Environ. Sci. Pollut. Res. 30, 26703–26717 (2023).

    Google Scholar 

  30. Yaseen, Z. M. et al. Heavy metals prediction in coastal marine sediments using hybridizedmachine learning models with metaheuristic optimization algorithm. Chemosphere 352, 141329 (2024).

    Google Scholar 

  31. Deng, D., Wu, Y., Ren, B. & Yin, H. Applying Chemical and Statistical Analysis Methods to Evaluate Water and Stream Sediments around the Coal Mine Area in Dazhu China.. Water 15, 1421 (2023).

    Google Scholar 

  32. Bhagat, S. K. et al. Prediction of sediment heavy metal at the Australian Bays using newly developed hybrid artificial intelligence models. Environ. Pollut. 268, 115663 (2021).

    Google Scholar 

  33. Mert, B. K. & Kasapogullari, D. A case study of using artificial neural networks to predict heavy metal pollution in Lake Iznik. Environ. Monit. Assess. 196, 1–26 (2024).

    Google Scholar 

  34. Yolcu, U., Yalcin, I. E., Uras, M. E. & Ozyigit, I. I. Modeling the effects of essential heavy metals on environmental pollution: A linear and nonlinear prediction model via cascade forward-neural network. Math. Methods Appl. Sci. 47, 4306–4318 (2024).

    Google Scholar 

  35. Chen, D. et al. Delineating and identifying risk zones of soil heavy metal pollution in an industrialized region using machine learning. Environ. Pollut. 318, 120932 (2023).

    Google Scholar 

  36. Cui, S. et al. Advances and applications of machine learning and deep learning in environmental ecology and health. Environ. Pollut. 122358 (2023).

  37. Gryech, I., Ghogho, M., Mahraoui, C. & Kobbane, A. An exploration of features impacting respiratory diseases in urban areas. Int. J. Environ. Res. Public Health 19, 3095 (2022).

    Google Scholar 

  38. Gryech, I., Asaad, C., Ghogho, M. & Kobbane, A. Applications of machine learning & Internet of Things for outdoor air pollution monitoring and prediction: A systematic literature review. Eng. Appl. Artif. Intell. 137, 109182 (2024).

    Google Scholar 

  39. Xu, X., Lai, T., Jahan, S. & Farid, F. Water and Sediment Analyse Using Predictive Models. arXiv preprint arXiv:2203.03422 (2022).

  40. Nguyen, H. N. et al. Predicting element concentrations by machine learning models in neutron activation analysis. J. Radioanal. Nucl. Chem. 333, 1759–1768 (2024).

    Google Scholar 

  41. Han, Z. et al. Predicting and investigating water quality index by robust machine learning methods. J. Environ. Manag. 381, 125156 (2025).

    Google Scholar 

  42. Chen, X. et al. Water quality parameters-based prediction of dissolved oxygen in estuaries using advanced explainable ensemble machine learning. J. Environ. Manag. 380, 125146 (2025).

    Google Scholar 

  43. Dai, H., Huang, G., Zeng, H. & Yang, F. PM2.5 concentration prediction based on spatiotemporal feature selection using XGBoost-MSCNN-GA-LSTM. Sustainability 13, 12071 (2021).

    Google Scholar 

  44. Zhang, B., Zhang, Y. & Jiang, X. Feature selection for global tropospheric ozone prediction based on the BO-XGBoost-RFE algorithm. Sci. Rep. 12, 9244 (2022).

    Google Scholar 

  45. Demir, S. & Sahin, E. K. Liquefaction prediction with robust machine learning algorithms (SVM, RF, and XGBoost) supported by genetic algorithm-based feature selection and parameter optimization from the perspective of data processing. Environ. Earth Sci. 81, 459 (2022).

    Google Scholar 

  46. Garabaghi, F. H., Benzer, S. & Benzer, R. Modeling dissolved oxygen concentration using machine learning techniques with dimensionality reduction approach. Environ. Monit. Assess. 195, 879 (2023).

    Google Scholar 

  47. Ahajjam, A. et al. Enhancing prediction of wildfire occurrence and behavior in Alaska using spatio-temporal clustering and ensemble machine learning. Ecol. Info. 85, 102963 (2025).

    Google Scholar 

  48. Theng, D. & Bhoyar, K. K. Feature selection techniques for machine learning: A survey of more than two decades of research. Knowl. Inf. Syst. 66, 1575–1637 (2024).

    Google Scholar 

  49. Kohavi, R. & John, G. H. Wrappers for feature subset selection. Artif. Intell. 97, 273–324 (1997).

    Google Scholar 

  50. Guyon, I., Weston, J., Barnhill, S. & Vapnik, V. Gene selection for cancer classification using support vector machines. Mach. Learn. 46, 389–422 (2002).

    Google Scholar 

  51. Kuhn, M. et al. Package ‘caret’. R J. 223, 48 (2020).

    Google Scholar 

  52. Holland, J. Adaptation in Natural and Artificial Systems, lstedn (1975).

  53. Eiben, A. E. & Smith, J. E. Introduction to evolutionary computing (Springer, 2015).

    Google Scholar 

  54. Wolpert, D. H. Stacked generalization. Neural Netw. 5, 241–259 (1992).

    Google Scholar 

  55. Seber, G. A. & Lee, A. J. Linear regression analysis (John Wiley & Sons, 2012).

    Google Scholar 

  56. Turksen, I. B. Fuzzy functions with LSE. Appl. Soft Comput. 8, 1178–1188 (2008).

    Google Scholar 

  57. Aladag, C. H., Turksen, I. B., Dalar, A. Z., Egrioglu, E. & Yolcu, U. Application of type-1fuzzy functions approach for time series forecasting. Turk. J. Fuzzy Syst. 5, 1–9 (2014).

    Google Scholar 

  58. Tak, N. & Inan, D. Type-1 fuzzy forecasting functions with elastic net regularization. Expert Syst. Appl. 199, 116916 (2022).

    Google Scholar 

  59. Cebeci, Z. et al. Package ‘ppclust’ (2019).

  60. Hans, C. Elastic net regression modeling with the orthant normal prior. J. Am. Stat. Assoc. 106, 1383–1393 (2011).

    Google Scholar 

  61. Kelly, J. W., Degenhart, A. D., Siewiorek, D. P., Smailagic, A. & Wang, W. Sparse linear regression with elastic net regularization for brain-computer interfaces. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 4275–4278 (IEEE, 2012).

  62. Friedman, J. et al. Package ‘glmnet’. CRAN R Repositary 595 (2021).

  63. Friedman, J. H. Greedy function approximation: a gradient boosting machine. Annals of statistics 1189–1232 (2001).

  64. Chen, T. & Guestrin, C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785–794 (2016).

  65. Qiu, Y. et al. Performance evaluation of hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibration. Eng. Comput. 38, 4145–4162 (2022).

    Google Scholar 

  66. Chen, T., He, T., Benesty, M. & Khotilovich, V. Package ‘xgboost’. R Version 90, 40 (2019).

    Google Scholar 

  67. Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).

    Google Scholar 

  68. González-Sopeña, J., Pakrashi, V. & Ghosh, B. An overview of performance evaluation metrics for short-term statistical wind power forecasting. Renew. Sustain. Energy Rev. 138, 110515 (2021).

    Google Scholar 

  69. Bat, L., Şahin, F., Öztekin, A., Özsandıkçı, U. & Özkan, E. Y. Trace elements pollution in surface sediment of the sea of marmara coastal and transition water. Mar. Pollut. Bull. 218, 118067 (2025).

    Google Scholar 

  70. Pourang, N. et al. Spatiotemporal patterns, source apportionment, and ecological risk of major and trace elements in sediment cores from anzali international wetland. Sci. Rep. 15, 41965 (2025).

    Google Scholar 

  71. Li, J. Natural and anthropogenic controls on heavy metal distribution in east China sea sediments. Front. Mar. Sci. 12, 1689901 (2025).

    Google Scholar 

  72. Li, F., Yin, H., Zhu, T. & Zhuang, W. Understanding the role of manganese oxides in retaining harmful metals: Insights into oxidation and adsorption mechanisms at microstructure level. Eco-Environ. Health 3, 89–106 (2024).

    Google Scholar 

  73. Zeng, P. et al. RWKV-SKF: A recurrent architecture with state-space and frequency-domain filtering for dissolved oxygen predicting and revealing influencing mechanisms. Inf. Sci. 123018(2025).

Download references

Funding

This study was partially supported by the Scientific and Technological Research Council of Türkiye (TÜBİTAK) under Grant Number 123F266. The authors thank TÜBİTAK for their support.

Funding: Not received for publication fee.

Author information

Authors and Affiliations

  1. Department of Statistics, Marmara University, 34730, Istanbul, Turkey

    Aylin Ucan & Nihat Tak

  2. Department of Biology, Marmara University, 34730, Istanbul, Turkey

    Asli Hocaoglu-Ozyigit & Ibrahim Ilker Ozyigit

Authors

  1. Aylin Ucan
    View author publications

    Search author on:PubMed Google Scholar

  2. Nihat Tak
    View author publications

    Search author on:PubMed Google Scholar

  3. Asli Hocaoglu-Ozyigit
    View author publications

    Search author on:PubMed Google Scholar

  4. Ibrahim Ilker Ozyigit
    View author publications

    Search author on:PubMed Google Scholar

Contributions

AU: Formal analysis, software, visualization, writing-original draft, writing-review; NT: Supervision, conceptualization, formal analysis, writing-original draft, writing-review; AHO: Financial support, material preparation, data curation, writing-review; IIO: Financial support, data curation, writing-review, and editing.

Corresponding author

Correspondence to
Nihat Tak.

Ethics declarations

Competing interests

On behalf of all authors of the paper, I declare that there is no competing interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Supplementary Information. (download PDF )

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Cite this article

Ucan, A., Tak, N., Hocaoglu-Ozyigit, A. et al. Forecasting toxic metal concentrations in an inland sea ecosystem with machine learning algorithms.
Sci Rep (2026). https://doi.org/10.1038/s41598-026-48252-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41598-026-48252-5

Source: Ecology - nature.com

Climate warming strengthened but droughts eliminated the coupling between productivity and tree growth in semi-arid plantations

Environmental impacts of intensive beef fattening: a case study in the Veneto region, Italy

This portal is not a newspaper as it is updated without periodicity. It cannot be considered an editorial product pursuant to law n. 62 of 7.03.2001. The author of the portal is not responsible for the content of comments to posts, the content of the linked sites. Some texts or images included in this portal are taken from the internet and, therefore, considered to be in the public domain; if their publication is violated, the copyright will be promptly communicated via e-mail. They will be immediately removed.

Back to Top
Close