Elektrane (2025) [pp. 525-535]
AUTHOR(S) / AUTOR(I): Nikola Stanković, Miško Milanović
Download Full Pdf 
DOI: https://doi.org/10.46793/EEP25.525S
ABSTRACT / SAŽETAK:
This paper explores the application of modern machine learning models combined with Geographic Information System (GIS) techniques to map and evaluate the efficiency of wastewater treatment systems based on constructed wetlands across Europe. The study focused on predicting the effluent Biochemical Oxygen Demand (BODout, mg/L), a key indicator of treated water quality. Five machine learning models were employed: Linear Regression, Random Forest, XGBoost, LASSO Regression, and Artificial Neural Networks. The analysis was conducted in the R environment (version 4.5.0), while spatial visualization was performed using QGIS (version 3.34.5). The dataset covered 151 wastewater treatment plants across 18 European countries. Input variables included chemical, climatic, and geographical parameters such as temperature, precipitation, plant area, wastewater inflow, influent concentrations of BOD, ammonium nitrogen, total nitrogen, total phosphorus, and geographic coordinates. The Random Forest model achieved the best performance with R² = 0.28 and RMSE = 12.9 mg/L, indicating its superior ability to predict BODout values compared to other models. The most influential predictors were influent BOD concentration, ammonium nitrogen, and total nitrogen, while climatic parameters (precipitation and temperature) also showed notable effects. GIS integration enabled spatial visualization of discrepancies between observed and predicted values, allowing the identification of plants and regions with lower treatment efficiency. The results demonstrate that combining GIS and machine learning offers an innovative and efficient framework for spatial analysis and optimization of wastewater management systems.
KEYWORDS / KLJUČNE REČI:
GIS, machine learning, constructed wetlands, biochemical oxygen demand, wastewater
ACKNOWLEDGEMENT / PROJEKAT:
REFERENCES / LITERATURA:
[1] Davis, L., Handbook of Constructed Wetlands-A guide to creating wetlands for: Agricultural waste water, domestic waste water, coal mine drainage, storm water in the MidAtlantic Region: Volume 2. Natural Resources Conservation Service and the US Environmental Protection Agency. 1995
[2] Vymazal, J., The use constructed wetlands with horizontal sub-surface flow for various types of waste water. Ecological Engineering, 35 (2009), (1), 1–17. https://doi.org/10.1016/j.ecoleng.2008.08.016
[3] Mulkeen, C. J., Gormally, M. J., Swaney, W. T., Healy, M. G., & Williams, C. D., Sciomyzidae (Diptera) Assemblages in Constructed and Natural Wetlands: Implications for Constructed Wetland Design. Wetlands 44 (2023), (5), Article 2024. https://doi.org/10.1007/s13157-023-01759-3
[4] Brix, H., Use of constructed wetlands in water pollution control: Historical development, present status, and future perspectives. Water Science and Technology, 30 (1994), (8), 209-223.https://doi.org/10.2166/wst.1994.0413
[5] Haydar, S., Anis, M., & Afaq, M., Performance evaluation of hybrid constructed wetlands for the treatment of municipal wastewater in developing countries. Chinese Journal of Chemical Engineering, 28 (2020), (6), 1717–1724. https://doi.org/10.1016/j.cjche.2020.02.017
[6] Prihatini, N. S., Jumar, Arisnawati, R. S., Nadhillah, R. Z., Wulandari, R. P., Fazriati, D. A., & Soemarno., Ability of Local Species Plant in Surface Flow Constructed Wetland to Reduce
Biochemical Oxygen Demand (BOD) and Chemical Oxygen Demand (COD) in Sasirangan Wastewater. International Journal of Bioscience, 11 (2017), (4), 144–149. http://doi.org/10.12692/ijb/11.4.144-149
[7] Prihatini, N. S., Firmansyah, M., Nirtha, I., Abdi, C., & Suryanata, A., Removal of Fe in well water using surface flow constructed wetland system with Eichhornia crassipes and Pistia stratiotes L. International Journal of Biosciences, 22 (2023), (1), 18–26. http://dx.doi.org/10.12692/ijb/22.1.18-26
[8] Prihatini, N. S., & Soemarno., Role of Plant-Bacteria Association in Constructed Wetlands for the Removal of Iron (Fe) from Contaminated Water. In S. Kumar, K. Bauddh, R. Singh, N. Kumar, & R. Kumar (Eds.), Aquatic Macrophytes: Ecology, Functions and Services (2023) (pp.297–311). Springer. https://doi.org/10.1007/978-981-99-3822-3_14
[9] Hach, C. C., Klein, R. L., & Gibbs, C. R., Introduction to Biochemical Oxygen Demand (Technical Information Series—Booklet No. 7). (1997) Hach Company. https://imall.vn/wpcontent/uploads/2021/07/Catalogue-Hach-HRI3P.pdf
[10] Jouanneau, S., Recoules, L., Durand, M. J., Boukabache, A., Picot, V., Primault, Y., Lakel, A., Sengelin, M., Barillon, B., & Thouand, G., Methods for assessing biochemical oxygen demand (BOD): A review. Water Research, 49 (2013), 62–82.https://doi.org/10.1016/j.watres.2013.10.066
[11] Von Sperling, M., & Platzer, C., Designing wetlands for specific applications – Treatment wetlands in developing regions. In G. Langergraber, G. Dotro, J. Nivala, A. Rizzo, & O. R. Stein (Eds.), Wetland Technology, Practical Information on the Design and Application of Treatment Wetlands (Scientific and Technical Report, 27, pp. 18–22). (2019) IWA Publishing. https://doi.org/10.2166/9781789060171_0017
[12] Abdullahi, A. B., Siregar, A. R., Pakiding, W., & Riwu, M., The analysis of BOD (Biological Oxygen Demand) and COD (Chemical Oxygen Demand) contents in the water of around laying chicken farm. The 3rd International Conference of Animal Science and Technology (Earth and Environmental Science, Vol. 788), 2020, Makassar, Indonesia. https://doi.org/10.1088/1755-1315/788/1/012155
[13] Pérez, Y., Vargas, E., García-Cortés, D., Hernández, W., Checo, H., & Jáuregui-Haza, U., Efficiency and effectiveness of systems for the treatment of domestic wastewater based on subsurface flow constructed wetlands in Jarabacoa, Dominican Republic. Water Science and Engineering, 17 (2024), 2, 118–128. https://doi.org/10.1016/j.wse.2023.08.004
[14] Qin, R., & Chen, H., The procession of constructed wetland removal mechanism of pollutants. Proceedings of the 4th International Conference on Mechanical Materials and Manufacturing Engineering (2016) (pp. 568–570). Atlantis Press. https://www.atlantispress. com/proceedings/mmme-16/25859862
[15] Gabr, M. E., Al-Ansari, N., Salem, A., & Awad, A., Proposing a Wetland-Based Economic Approach for Wastewater Treatment in Arid Regions as an Alternative Irrigation Water Source. Hydrology, 10, (2023), 1, Article 20. https://doi.org/10.3390/hydrology10010020
[16] Nurmahomed, N., Sobhun, T., Ragen, A. K., & Sheridan, C. M., Performance of a constructed wetland treating synthetic greywater. Bioresource Technology Reports, 17 (2022), Article 100930. https://doi.org/10.1016/j.biteb.2021.100930
[17] Shutes, R. B. E., Artificial wetlands and water quality improvement. Environment International, 26, (2001), 5–6, 441–447. https://doi.org/10.1016/S0160-4120(01)00025-3
[18] Von Sperling, M., & Platzer, C., Designing wetlands for specific applications – Treatment wetlands in developing regions. In G. Langergraber, G. Dotro, J. Nivala, A. Rizzo, & O. R. Stein (Eds.), Wetland Technology, Practical Information on the Design and Application of Treatment Wetlands (Scientific and Technical Report, 27, pp. 18–22). (2019) IWA Publishing. https://doi.org/10.2166/9781789060171_0017
[19] Shams, S., et al., Water quality prediction using machine learning models: A comparative study. Multimedia Tools and Applications (2024) 83:35307–35334. https://doi.org/10.1007/s11042-023-16737-4
[20] Biau, G. & Scornet, E., A Random Forest Guided Tour. (2015) https://doi.org/10.48550/arXiv.1511.05741
[21] Chen, T. & Guestrin, C., XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. (2016) https://doi.org/10.48550/arXiv.1603.02754
[22] Bentejac, C., Csörgo, A., & Martinez-Munoz, G., A Comparative Analysis of XGBoost. (2019) https://doi.org/10.48550/arXiv.1911.01914
[23] Tibshirani, R., Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B (Methodological), 58 (1996), 1, 267–288.
[24] Rustam, F., Ashraf, I., Mehmood, A., et al., An Artificial Neural Network Model for Water Quality and Water Consumption Prediction. Water, 14 (2022), 21, 3359.https://doi.org/10.3390/w14213359
[25] Mishra, A., & Singh, V. P., GIS and Remote Sensing Applications in Water Resources. (2021) Springer. https://doi.org/10.1007/978-3-030-54756-4
[26] https://climateknowledgeportal.worldbank.org/