STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Polymer & Composites Original Research

Machine-Learning-Assisted Development of Polymer-Biochar Composite Adsorbents for the Removal of Heavy Metals from Gomti River Water

  1. Nidhi Singh Civil Engineering Department, GLA University, Mathura
  2. Smita Tung Civil Engineering Department, GLA University, Mathura

Abstract

Rapid urbanization, industrial discharge, and agricultural runoff pose a significant threat to freshwater sustainability and public health. Within these ecosystems, polymer pollutants—such as microplastics, nanoplastics, synthetic fibres, and additive residues—have emerged as persistent vectors capable of adsorbing and transporting toxic heavy metals. Because these polymeric contaminants dynamically interact with conventional aquatic parameters to alter pollutant mobility and ecological risk profiles, there is an urgent need to transition from passive environmental monitoring to active, materials-driven remediation. To address this challenge, this study presents the development and machine-learning-assisted performance evaluation of a novel polymer-biochar composite adsorbent designed for the removal of heavy metals from complex aquatic matrices. The Gomti River Basin was utilized as a real-world environmental testbed. A dataset comprising 100 water samples collected from five representative locations, characterized by 18 physicochemical and heavy-metal parameters, served as the competing ionic background matrix. To predict the composite's adsorption efficiency under varying, non-linear riverine conditions, a comparative assessment of machine learning (ML) models—Multiple Linear Regression (MLR) and Artificial Neural Network (ANN)—was conducted. A standardized 70:30 train–test split combined with nested 10-fold cross-validation was employed to ensure robust model development. Among the investigated models, the ANN demonstrated superior predictive capability for evaluating the composite's performance against matrix interferences, achieving a testing R² of 0.99, RMSE of 0.05, and 92.5% of predictions falling within ±20% of observed values. From a physical chemistry perspective, the ML framework identified that elevated Electrical Conductivity (EC), Total Dissolved Solids (TDS), and sulfate concentrations act as the dominant variables influencing the electrical double layer, surface complexation, and biosorption capacity of the polymeric material. Ultimately, these findings demonstrate that integrating green polymer-composite design with data-driven ML modelling provides a highly effective pathway for optimizing nanoparticle-enabled water-treatment technologies, thereby advancing the goals of circular polymer science and sustainable aquatic management.

Keywords

References (49)

  1. Lu YJ, Wang CW, Wang CH. A hybrid diagnostic system for corrosion mechanism identification in petrochemical equipment: Integrating Bayesian probabilities and association rule. Process Safety and Environmental Protection. 2025;201:107577. doi:10.1016/j.psep.2025.107577
  2. Ayvaz MT. A linked simulation–optimization model for solving the unknown groundwater pollution source identification problems. Journal of Contaminant Hydrology. 2010;117(1-4):46-59. doi:10.1016/j.jconhyd.2010.06.004
  3. Turner A, Holmes LA. Adsorption of trace metals by microplastic pellets in fresh water. Environmental Chemistry. 2015;12(5):600-610. doi:10.1071/en14143
  4. Holmes LA, Turner A, Thompson RC. Adsorption of trace metals to plastic resin pellets in the marine environment. Environmental Pollution. 2012;160:42-48. doi:10.1016/j.envpol.2011.08.052
  5. Zheng H, Hou S, Liu J, Xiong Y, Wang Y. Advanced Machine Learning and Water Quality Index (WQI) Assessment: Evaluating Groundwater Quality at the Yopurga Landfill. Water. 2024;16(12):1666. doi:10.3390/w16121666
  6. Jiang S, Fan J, Xia X, Li X, Zhang R. An Effective Kalman Filter-Based Method for Groundwater Pollution Source Identification and Plume Morphology Characterization. Water. 2018;10(8):1063. doi:10.3390/w10081063
  7. A. K. Das, N. Gupta, T. Mahmood, B. C. Tripathy, R. Das, and S. Das, An Efficient Water Quality Evaluation Model Using Weighted Hesitant Fuzzy Soft Sets for Water Pollution Rating, 1st ed. CRC Press, Taylor & Francis, 2025.
  8. Das AK, Gupta N, Mahmood T, Tripathy BC, Das R, Das S. An innovative fuzzy multi-criteria decision making model for analyzing anthropogenic influences on urban river water quality. Iran Journal of Computer Science. 2024;8(1):103-124. doi:10.1007/s42044-024-00211-x
  9. Hahladakis JN, Velis CA, Weber R, Iacovidou E, Purnell P. An overview of chemical additives present in plastics: Migration, release, fate and environmental impact during their use, disposal and recycling. Journal of Hazardous Materials. 2018;344:179-199. doi:10.1016/j.jhazmat.2017.10.014
  10. Ahmed M, Mumtaz R, Hassan Zaidi SM. Analysis of water quality indices and machine learning techniques for rating water pollution: a case study of Rawal Dam, Pakistan. Water Supply. 2021;21(6):3225-3250. doi:10.2166/ws.2021.082
  11. S. Prakash and Mishra, “Analysis of Water Quality of Gomti River At District Sultanpur (U.P.),” Int. J. Eng. Sci. Invent. Res. Dev., vol. I, no. III, p. 113, 2014.
  12. Khan R, Saxena A, Shukla S, Goel P, Bhattacharya P, Li P, et al. Appraisal of water quality and ecological sensitivity with reference to riverfront development along the River Gomti, India. Applied Water Science. 2022;12(1). doi:10.1007/s13201-021-01560-9
  13. Singh KP, Basant A, Malik A, Jain G. Artificial neural network modeling of the river water quality—A case study. Ecological Modelling. 2009;220(6):888-895. doi:10.1016/j.ecolmodel.2009.01.004
  14. Singh RM, Datta B. Artificial neural network modeling for identification of unknown pollution sources in groundwater with partially missing concentration observation data. Water Resources Management. 2006;21(3):557-572. doi:10.1007/s11269-006-9029-z
  15. Dong Y, Gao M, Song Z, Qiu W. As(III) adsorption onto different-sized polystyrene microplastic particles and its mechanism. Chemosphere. 2020;239:124792. doi:10.1016/j.chemosphere.2019.124792
  16. Das AK, Gupta N, Mahmood T, Tripathy BC, Das R, Das S. Assessing anthropogenic influences on the water quality of Gomati River using an innovative weighted fuzzy soft set based water pollution rating system. Discover Water. 2024;4(1). doi:10.1007/s43832-024-00136-3
  17. Mohinuddin S, Sengupta S, Sarkar B, Saha UD, Islam A, Islam ARMT, et al. Assessing lake water quality during COVID-19 era using geospatial techniques and artificial neural network model. Environmental Science and Pollution Research. 2023;30(24):65848-65864. doi:10.1007/s11356-023-26878-6
  18. Saqib N, Rai PK, Kanga S, Kumar D, Đurin B, Singh SK. Assessment of Ground Water Quality of Lucknow City under GIS Framework Using Water Quality Index (WQI). Water. 2023;15(17):3048. doi:10.3390/w15173048
  19. Khalaf AM, Rustum R. ASSESSMENT OF PROJECTED EXTREME CLIMATE CHANGE IMPACT ON THE OPERATIONAL PERFORMANCE OF SURFACE WATER RESERVOIRS. Water Conservation & Management. 2023;8(1):11-19. doi:10.26480/wcm.01.2024.11.19
  20. Singh N, Tung S. Assessment of Water Quality of Gomti River at Lucknow. Air, Soil and Water Research. 2025;18. doi:10.1177/11786221251328589
  21. Pimparkar AM, Patil SN, Patil BD, Kadam AK. Comparative assessment of wetland water quality from rural and urban area of Aurangabad District, Maharashtra, India using water quality index. HydroResearch. 2023;6:269-278. doi:10.1016/j.hydres.2023.10.001
  22. Poursaeid M. Comprehensive water quality indicators modeling by environmental protection view using multi optimized weighted ensemble machine learnings. Process Safety and Environmental Protection. 2025;193:696-709. doi:10.1016/j.psep.2024.11.042
  23. Bose S, Mele E, Silberschmidt VV. Computational modelling of collagen-based flexible electronics: assessing the effect of hydration. Multiscale and Multidisciplinary Modeling, Experiments and Design. 2023;7(3):1643-1655. doi:10.1007/s41939-023-00230-4
  24. Sohn I. Deep belief network based intrusion detection techniques: A survey. Expert Systems with Applications. 2021;167:114170. doi:10.1016/j.eswa.2020.114170
  25. Chen L, Wang Q, Zhu G, Lin X, Qiu D, Jiao Y, et al. Dataset of stable isotopes of precipitation in the Eurasian continent. Earth System Science Data. 2024;16(3):1543-1557. doi:10.5194/essd-16-1543-2024
  26. Anul Haq M, Khadar Jilani A, Prabu P. Deep Learning Based Modeling of Groundwater Storage Change. Computers, Materials & Continua. 2022;70(3):4599-4617. doi:10.32604/cmc.2022.020495
  27. Sidek LM, Mohiyaden HA, Marufuzzaman M, Noh NSM, Heddam S, Ehteram M, et al. Developing an ensembled machine learning model for predicting water quality index in Johor River Basin. Environmental Sciences Europe. 2024;36(1). doi:10.1186/s12302-024-00897-7
  28. Das B, Jain S, Singh S, Thakur P. Evaluation of multisite performance of SWAT model in the Gomti River Basin, India. Applied Water Science. 2019;9(5). doi:10.1007/s13201-019-1013-x
  29. Chen L, Zhu G, Lin X, Li R, Lu S, Jiao Y, et al. The Complexity of Moisture Sources Affects the Altitude Effect of Stable Isotopes of Precipitation in Inland Mountainous Regions. Water Resources Research. 2024;60(6). doi:10.1029/2023wr036084
  30. Li R, Zhu G, Chen L, Qi X, Lu S, Meng G, et al. Global Stable Isotope Dataset for Surface Water. Earth System Science Data. 2025;17(5):2135-2145. doi:10.5194/essd-17-2135-2025
  31. Cao M, Baxevanakis KP, Silberschmidt VV. High-temperature behaviour and interfacial damage of CGI: 3D numerical modelling. Multiscale and Multidisciplinary Modeling, Experiments and Design. 2023;7(3):1515-1525. doi:10.1007/s41939-023-00188-3
  32. Nandi BP, Singh G, Jain A, Tayal DK. Evolution of neural network to deep learning in prediction of air, water pollution and its Indian context. International Journal of Environmental Science and Technology. 2023;21(1):1021-1036. doi:10.1007/s13762-023-04911-y
  33. Saalidong BM, Aram SA, Otu S, Lartey PO. Examining the dynamics of the relationship between water pH and other water quality parameters in ground and surface water systems. PLOS ONE. 2022;17(1):e0262117. doi:10.1371/journal.pone.0262117
  34. Dheeraj VP, Singh CS, Kishore N, Sonkar AK. Groundwater Quality Assessment in Korba Coalfield Region, India: An Integrated Approach of GIS and Heavy Metal Pollution Index (HPI) Model. Nature Environment and Pollution Technology. 2023;22(1):369-382. doi:10.46488/nept.2023.v22i01.036
  35. Krishnamoorthy L, Lakshmanan VR. Groundwater quality assessment using machine learning models: a comprehensive study on the industrial corridor of a semi-arid region. Environmental Science and Pollution Research. 2024;32(49):28319-28342. doi:10.1007/s11356-024-34119-7
  36. Nayak A, Matta G, Uniyal DP. Hydrochemical characterization of groundwater quality using chemometric analysis and water quality indices in the foothills of Himalayas. Environment, Development and Sustainability. 2022;25(12):14229-14260. doi:10.1007/s10668-022-02661-4
  37. Iqbal K, Ahmad S, Dutta V. Pollution mapping in the urban segment of a tropical river: is water quality index (WQI) enough for a nutrient-polluted river? Applied Water Science. 2019;9(8). doi:10.1007/s13201-019-1083-9
  38. M. Almeshaal, S. Palanisamy, T. M. Murugesan, M. Palaniappan, and C. Santulli, “Physico-chemical characterization of Grewia Monticola Sond (GMS) fibers for prospective application in biocomposites,” J. Nat. Fibers, vol. 19, no. 17, pp. 15276–15290, 2022.
  39. Santy S, Mujumdar P, Bala G. Potential Impacts of Climate and Land Use Change on the Water Quality of Ganga River around the Industrialized Kanpur Region. Scientific Reports. 2020;10(1). doi:10.1038/s41598-020-66171-x
  40. Khan R, Saxena A. Potentially toxic elements (PTEs) in Gomti-Ganga Alluvial Plain, associated human health risks assessment and potential remediation using novel-nanomaterials. Environmental Monitoring and Assessment. 2022;195(1). doi:10.1007/s10661-022-10562-2
  41. Wei W, Xu W, Deng J, Guo Y. Self-aeration development and fully cross-sectional air diffusion in high-speed open channel flows. Journal of Hydraulic Research. 2022;60(3):445-459. doi:10.1080/00221686.2021.2004250
  42. S. Palanisamy et al., “Tensile properties and fracture morphology of Acacia caesia bark fibers treated with different alkali concentrations,” J. Nat. Fibers, vol. 19, no. 15, pp. 11258–11269, 2022.
  43. F. Wang, K. M. Shih, and X. Y. Li, “The Partition Behavior of Perfluorooctanesulfonate (PFOS) and Perfluorooctanesulfonamide (FOSA) on Microplastics,” Chemosphere, vol. 181, pp. 60–67, 2017, doi:10.1016/j.chemosphere.2017.04.039.
  44. Godoy V, Blázquez G, Calero M, Quesada L, Martín-Lara MA. The potential of microplastics as carriers of metals. Environmental Pollution. 2019;255:113363. doi:10.1016/j.envpol.2019.113363
  45. Khullar S, Singh N. Machine learning techniques in river water quality modelling: a research travelogue. Water Supply. 2020;21(1):1-13. doi:10.2166/ws.2020.277
  46. Wang B, Tan Z, Sheng W, Liu Z, Wu X, Ma L, et al. Identification of Groundwater Contamination Sources Based on a Deep Belief Neural Network. Water. 2024;16(17):2449. doi:10.3390/w16172449
  47. N. Ayrilmis, G. Kanat, E. Yildiz Avsar, S. Palanisamy, and A. Ashori, “Utilizing waste manhole covers and fibreboard as reinforcing fillers for thermoplastic composites,” J. Reinf. Plast. Compos., vol. 44, no. 17–18, pp. 1108–1118, 2025.
  48. Wei C, Zhao T, Cao J, Li P. Water Quality Prediction Model Based on Interval Type-2 Fuzzy Neural Network with Adaptive Membership Function. International Journal of Fuzzy Systems. 2025;28(3):940-954. doi:10.1007/s40815-025-01999-x
  49. WHO, “WHO 2008,” WHO Library Cataloguing-in-Publication Data, 2008.
Support