Shapley Additive Explanations for Microplastic Contamination Modelling in the Penang River: A First Implementation of a PCA-Guided Evidential Ensemble Approach for Microplastic Prediction in Water Systems
DOI:
https://doi.org/10.70917/jcc-2026-031Keywords:
Microplastic, Evidential Neural Network, Pollution, Penang River, Environmental TechnologyAbstract
Microplastic (MP) pollution has become a major environmental issue with major impacts on ecological and human health, especially in the tropical river systems that are vulnerable to urbanization and industrialization. This paper presents the first study in the field of evidential ensemble modelling combined with principal component analysis (PCA) and explainable artificial intelligence (XAI) to simulate the presence of microplastics in the River Penang. The objectives were two-fold (i) to establish the prevailing physicochemical gradients that determine MP variability with the help of PCA, (ii) to build and interpret advanced ensemble models that could provide both high predictive and mechanistic information. The three major components were found to explicate a greater percentage of the total variance (over 91%). PC1 was an illustration of thermo-ionic pollution gradients (with a negative correlation between temperature, conductivity, and MPs), PC2 a turbidity-pH axis (strongly negatively correlated with MPs), and PC3 gradients of sediment-dilution. A two-scenario modeling technique was then chosen, including single machine learning models and the ensemble models, namely Evidential Neural Network Ensemble (EVNNE), Robust Linear Ensemble (RLE), Boosted Tree Ensemble (BTE), and Artificial Neural Network Ensemble (ANNE). The single models show less predictive performance compared to other models, with GPR-M1 (RMSE = 4.34, MAE = 3.03) and ANN-M1 (RMSE = 4.76, MAE = 3.11) outperforming RT despite having high error performance. On the other hand, ensemble models increased predictive capability sufficiently. RLE and BTE reduced the RMSE to 2.75 and 1.71, and the MAE to 1.45 and 1.10 respectively, which are substantial errors considering standalone models. EVNNE demonstrates high generalization performance with minimal prediction error (RMSE = 0.078 and MAE = 0.02). The interpretability evaluation of the Explainable AI SHAP analysis values proved the ensemble models' clarity with noticeable insights to the underlying environmental mechanisms. Additionally, pH, electrical conductivity (CDC) and temperature have the strongest impact, while turbidity and dissolved oxygen (DO) have moderate but context-dependent impacts. This study introduced a methodological approach to the monitoring of microplastics through the integration of PCA as the environmental representation extraction method, ensemble modeling as a predictive robust approach, and XAI modeling as an interpretable approach.
References
Abba, S. I., Benaafi, M., Usman, A. G., & Aljundi, I. H. (2022). Sandstone groundwater salinization modelling using physicochemical variables in Southern Saudi Arabia: Application of novel data intelligent algorithms. Ain Shams Engineering Journal, xxxx, 101894. https://doi.org/10.1016/ j.asej.2022.101894
Abba, S. I., Benaafi, M., Usman, A. G., Ozsahin, D. U., Tawabini, B., & Aljundi, I. H. (2023). Mapping of groundwater salinization and modelling using meta-heuristic algorithms for the coastal aquifer of eastern Saudi Arabia. Science of The Total Environment, 858(July 2022), 159697. https://doi.org/10.1016/ j.scitotenv.2022.159697
Abba, S. I., Nourani, V., & Elkiran, G. (2019). Multi-parametric modeling of water treatment plant using AI-based non-linear ensemble. Journal of Water Supply: Research and Technology - AQUA, 68(7), 547–561. https://doi.org/10.2166/aqua.2019.078
Abba, S. I., & Usman, A. G. (2020). Modeling of Water Treatment Plant Performance using Artificial Neural Network: Case Study Tamburawa Kano-Nigeria. September.
Al-shami, S. A., Hassanahmad, A., Azizah, S., & Nor, M. (2010). je s c . je s c . 22(11), 1718–1727.
Andrady, A. L. (2011). Microplastics in the marine environment. Marine Pollution Bulletin, 62(8), 1596–1605. https://doi.org/10.1016/j.marpolbul.2011.05.030
Azalina, N., Feisal, S., Haziqah, N., Firdaus, M., Sani, A., Khairulnisa, D., Ahmad, A., Azwan, M., Faiza, N., Razak, A., Nilam, T., & Tengku, B. (2023). Anthropogenic disturbance of aquatic biodiversity and water quality of an urban river in Penang , Malaysia. Water Science and Engineering, 16(3), 234–242. https://doi.org/10.1016/j.wse.2023.01.003
Benaafi, M., Yassin, M. A., Usman, A. G., & Abba, S. I. (2022). Neurocomputing Modelling of Hydrochemical and Physical Properties of Groundwater Coupled with Spatial Clustering , GIS , and Statistical Techniques.
Costache, R., Pham, Q. B., Sharifi, E., Linh, N. T. T., Abba, S. I., Vojtek, M., Vojteková, J., Nhi, P. T. T., & Khoi, D. N. (2020). Flash-flood susceptibility assessment using multi-criteria decision making and machine learning supported by remote sensing and GIS techniques. Remote Sensing, 12(1). https://doi.org/10.3390/RS12010106
Deng, L., Liu, K., Fan, Y., Qian, X., Ke, T., Liu, T., Li, M., Xu, X., Yang, D., & Li, H. (2025). Interpretable machine learning models reveal the partnership of microplastics and perfluoroalkyl substances in sediments at a century scale. Journal of Hazardous Materials, 486(November 2024), 137018. https://doi.org/10.1016/ j.jhazmat.2024.137018
Egbuna, I. K., Saidu, M., Ahmad, K. H., & Ogeah, P. U. (2025). Advancing environmental sustainability through emerging AI-based monitoring and mitigation strategies for microplastic pollution in aquatic ecosystems.
Elith, J., Leathwick, J. R., & Hastie, T. (2008). A working guide to boosted regression trees. Journal of Animal Ecology, 77(4), 802–813. https://doi.org/10.1111/j.1365-2656.2008.01390.x
Elzain, H. E., Chung, S. Y., Senapathi, V., Sekar, S., Lee, S. Y., Roy, P. D., Hassan, A., & Sabarathinam, C. (2022). Comparative study of machine learning models for evaluating groundwater vulnerability to nitrate contamination. Ecotoxicology and Environmental Safety, 229, 113061. https://doi.org/10.1016/ j.ecoenv.2021.113061
Granata, F., Papirio, S., Esposito, G., Gargano, R., & de Marinis, G. (2017). Machine learning algorithms for the forecasting of wastewater quality indicators. Water (Switzerland), 9(2), 1–12. https://doi.org/10.3390/ w9020105
Hale, R. C., Seeley, M. E., La Guardia, M. J., Mai, L., & Zeng, E. Y. (2020). A Global Perspective on Microplastics. Journal of Geophysical Research: Oceans, 125(1), 1–40. https://doi.org/10.1029/ 2018JC014719
Jibril, M. M., Idris, S., Hauwa, M., Jibrin, B., Jibrin, U., Adamu, M., Usman, D. A. G., Dilber, A. G. I., Ozsahin, U., & Karami, Z. (2024). New random intelligent chemometric techniques for sustainable geopolymer concrete : low ‑ energy and carbon ‑ footprint initiatives. Asian Journal of Civil Engineering, 25(2), 2287–2305. https://doi.org/10.1007/s42107-023-00908-7
Kalatzis, D., Katsafadou, A. I., Katsarou, E. I., Chatzopoulos, D. C., & Kiouvrekis, Y. (2025). Explainable Artificial Intelligence for the Rapid Identification and Characterization of Ocean Microplastics. Figure 1, 1–30.
Khatti, T., Naderi-Manesh, H., & Kalantar, S. M. (2019). Application of ANN and RSM techniques for modeling electrospinning process of polycaprolactone. Neural Computing and Applications, 31(1), 239–248. https://doi.org/10.1007/s00521-017-2996-6
Length, F. (2012). Concentration of selected heavy metals in water of the Juru River , Penang , Malaysia. 11(33), 8234–8240. https://doi.org/10.5897/AJB11.3840
Sheng, W., Hadibarata, T., Yuniarto, A., Ho, K., Tang, D., Abdullah, F., Syafrudin, M., Al, D. A., & Al-mohaimeed, A. M. (2021). Characterization of microplastics in the water and sediment of Baram River estuary, Borneo Island. Marine Pollution Bulletin, 172(August), 112880. https://doi.org/10.1016/j.marpolbul.2021.112880
Sultan, U., Abidin, Z., Lumpur, U. K., Simalungun, U., & Sumatra, N. (2023). ANALYSIS OF THE FLASH FLOOD EVENT AND RAINFALL. 21(1), 58–71.
Usman, A. G., Abd, M. A., Hashem, A. F., Hussaini, M., Anwar, T., Koramar, M., & Lawal, B. (2025). Journal of Radiation Research and Applied Sciences Intelligent techniques for modelling the effects of methanol leaves extract of Combretum hypopilinum diels ( Combretaceae ) on hepatic enzymes as indicators of radiation-induced liver injury. 18(July).
Usman, A. G., Işik, S., & Abba, S. I. (2020). A Novel Multi-model Data-Driven Ensemble Technique for the Prediction of Retention Factor in HPLC Method Development. Chromatographia, 83(8), 933–945. https://doi.org/10.1007/s10337-020-03912-0
Usman, A. G., IŞIK, S., & Abba, S. I. (2022). Qualitative prediction of Thymoquinone in the high‐performance liquid chromatography optimization method development using artificial intelligence models coupled with ensemble machine learning. Separation Science Plus, June, 1–9. https://doi.org/10.1002/sscp.202200071
Usman, A. G., Jibrin, A. M., Mati, S., & Abba, S. I. (2025). Evidential-bio-inspired algorithms for modeling groundwater total hardness: A pioneering implementation of evidential neural network for feature selection in water resources management. Environmental Chemistry and Ecotoxicology, 7, 494–505. https://doi.org/10.1016/j.enceco.2025.02.012
Usman, A. G., Mati, S., Jibril, M. M., Usman, J., Shah, S. M. H., Abba, S. I., & Naganna, S. R. (2024). Evidential Neural Network Model for Groundwater Salinization Simulation: A First Application in Hydro-Environmental Engineering. Water (Switzerland), 16(20). https://doi.org/10.3390/ w16202873
Usman, A. G., Usanase, N., Abba, S. I., Ozsahin, I., Uzun, B., Yassin, M. A., Rahman, S. M., & Ozsahin, D. U. (2023). Environmental modelling of CO concentration using AI-based approach supported with filters feature extraction_ A direct and inverse chemometrics-based simulation. Sustainable Chemistry for the Environment, 2(February), 100011. https://doi.org/10.1016/j.scenv.2023. 100011
Usman, J., Abba, S. I., Ishola, N. B., El-Badawy, T., Adamu, H., Gbadamosi, A., Salami, B. A., Usman, A. G., Benaafi, M., Othman, M. H. D., & Aljundi, I. H. (2023). Genetic neuro-computing model for insights on membrane performance in oily wastewater treatment: An integrated experimental approach. Chemical Engineering Research and Design, 199, 33–48. https://doi.org/10.1016/ j.cherd.2023.09.027
Van Dao, D., Adeli, H., Ly, H. B., Le, L. M., Le, V. M., Le, T. T., & Pham, B. T. (2020). A sensitivity and robustness analysis of GPR and ANN for high-performance concrete compressive strength prediction using a monte carlo simulation. Sustainability (Switzerland), 12(3). https://doi.org/ 10.3390/su12030830
Zeng, H., Cui, Y., Shao, R., Li, T., Zhao, Y., Liu, R., Dai, Z., Liu, Y., Wang, J., Xie, Q., & Zhang, X. (2025). Microplastics in animal-derived products and their potential risks to human health. TrAC Trends in Analytical Chemistry, 185, 118187. https://doi.org/10.1016/j.trac.2025.118187
Zhen, Y., Wang, L., Sun, H., & Liu, C. (2023). Prediction of microplastic abundance in surface water of the ocean and influencing factors based on ensemble learning ☆. Environmental Pollution, 331(P2), 121834. https://doi.org/10.1016/j.envpol.2023.121834
Downloads
Published
License
Copyright (c) 2026 Abdullahi Garba Usman, Mohd Saiful Samsudin, Dilber Uzun Ozsahin (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
