ANN-based Predictive Modeling of Heavy Metal Trends in Wastewater with Implications for Removal Using Carbon-based Nano-adsorbents
J. Environ. Nanotechnol., Volume 15, No 1 (March 2026) pp. 625-633
Abstract
The treatability of heavy metals in wastewater is affected by industrial expansion and treatment complexity, posing significant challenges. Carbon-based nano-adsorbents have been reported to exhibit excellent adsorption performance for heavy metals. Nevertheless, predicting their performance in actual wastewater remains difficult due to field-scale variability. In this study, an ANN-based approach is introduced to interpret and forecast heavy metal concentrations using large-scale wastewater monitoring data, aimed at supporting data-driven decision-making for nano-adsorbent-based treatment planning. The dataset used in this study is publicly available. The “Watershed Water Quality Dataset” from Kaggle, comprising over 625,000 records, was used. The dataset includes information such as analyte type, sample site, water treatment plant, and temporal details. The ANN model was built to accommodate the nonlinear properties of real wastewater. The model yielded an R² of 0.207 and an RMSE of 1325.49, suggesting limited predictive capability in a non-controlled environment with high variability, rather than strong regression performance. To assess its real-life applicability, a risk-based classification analysis was conducted by transforming concentration values into contamination levels. An accuracy of 61.3%, an area under the receiver operating characteristic curve (ROC–AUC) of ~0.87, and satisfactory precision–recall performance were achieved, indicating that the model can effectively discriminate the most significant high-risk events. Other analyses, including residual distributions, learning curves, and training loss patterns, revealed stable model training without systematic bias. This work demonstrates novelty by showing how large-scale real-world monitoring data and ANN modeling can be integrated to link predictive analytics with the development of treatment strategies for carbon-based nano-adsorbents.
Full Text
Reference
Abu Elgoud, E. M., Abd-Elhamid, A. I., Emam, S. S. and Aly, H. F., Selective removal of some heavy metals from Lanthanide solution by graphene oxide functionalized with sodium citrate, Sci. Rep., 12, 13755 (2022).
https://doi.org/10.1038/s41598-022-17949-8
Ain, Q. -U., Farooq, M. U. and Jalees, M. I., Application of Magnetic Graphene Oxide for Water Purification: Heavy Metals Removal and Disinfection, J. Water Process Eng., 33, 101044 (2020).
https://doi.org/10.1016/j.jwpe.2019.101044
Alimohammady, M., Jahangiri, M., Salavati-Niasari, M. and Aljeboree, A. M., Heavy metal adsorption by graphene oxide modified with 5-amino-3(2-thienyl) pyrazole using central composite design/response surface methodology (CCD/RSM), RSC Adv., 15(44), 36837–36860 (2025).
https://doi.org/10.1039/d5ra04106f
El Shafie, M., Gomaa, A. M., Gaber, G. A., Hussein, A. H., Hamoud, A. S., Elgyar, M. N., Omran, M. S., Hagag, M. A., Eltohamy, Z. A. and El-Majeed, S. A., Optimization of Zn (II) Adsorption from Aqueous Solutions by Lemon Peel–Derived Activated Carbon, Int. J. Eng. amp; Artificial Intell. Art Des., 80–93 (2025).
https://doi.org/10.21608/ijeaid.2025.426149.1012
Fiyadh, S. S., Alardhi, S. M., Al Omar, M., Aljumaily, M. M., Al Saadi, M. A., Fayaed, S. S., Ahmed, S. N., Salman, A. D., Abdalsalm, A. H., Jabbar, N. M. and El-Shafi, A., A comprehensive review on modelling the adsorption process for heavy metal removal from waste water using artificial neural network technique, Heliyon, 9(4), e15455 (2023).
https://doi.org/10.1016/j.heliyon.2023.e15455
Hamzah, M. A. A. M., Yusof, N., Zaini, M. A. A., Akmar, Z. Z., Jaafar, J. and Misdan, N., Advancing Heavy Metal Removal from Industrial Wastewater Using Oil Palm Waste–Based Adsorbent: toward Efficient Adsorption and Commercialization, Curr. Pollut. Rep., 11(1), 52 (2025).
https://doi.org/10.1007/s40726-025-00381-7
Jaid, G. M., Bohan, A. J. and Salman, G. K., Artificial Neural Network Modeling for Removal of Cd (II) and Pb (II) from Wastewater by Using Three Ferrite Nanomaterial (Cu0.9Zn0.1Fe2O4, Cu0.8Zn0.2Fe2O4, and Cu0.7Zn0.3Fe2O4) and Study the Antimicrobial Effectiveness of these Ferrite Substances, Revista de Chimie, 71(10), 67–80 (2020).
https://doi.org/10.37358/rc.20.10.8351
Joshi, A. A. and Ragupathy, G., Performance and mechanisms of waste-based carbon adsorbents in heavy metal removal – an experimental and theoretical approach, RSC Adv., 15(41), 34609–34634(2025).
https://doi.org/10.1039/d5ra03863d
Kumari, B., Seedat, N., Moothi, K. and Roopchund, R., Artificial intelligence-assisted modelling of heavy metal adsorption using cellulose-based and bio-waste adsorbents: A focus on ANN and ANFIS architectures, Res. Eng., 28, 107147 (2025).
https://doi.org/10.1016/j.rineng.2025.10714
Melchor-Durán, A. P., Moreno-Virgen, M. R., Bonilla-Petriciolet, A., Reynel-Ávila, H. E., Lucio, O. E. and González-Vázquez, O. F., Heavy Metal Removal from Water Using Graphene Oxide in Magnetic-Assisted Adsorption Systems: Characterization, Adsorption Properties, and Modelling, Separat., 11(10), 294 (2024).
https://doi.org/10.3390/separations11100294
Mudassar, H., Hina, K., Ghani, U., Afzaal, Q., Anis, S. A., Shifa, S. and Hosam, E. O., Adsorptive removal of Pb2+ from wastewater using ZnO-Biochar nanocomposite, Sci. Rep., 15(1), 29517 (2025).
https://doi.org/10.1038/s41598-025-13228-4
Saleh, M. Q., Tahir, T. F., OMER, R. A., Qader, A. F., Rashid, R. F. and Chaudhary, R. R, Carbon nanotubes for heavy metal removal: Advanced adsorption and detection strategies, Chem. Rev. Lett., 8(5) (2025).
https://doi.org/10.22034/crl.2025.523896.160
Shirsath, D., Synthesis and Application of Magnetic Nanoadsorbent in Removal of Toxic Metals from Aqueous Solution, J. Water Environ. Nanotechnol., 7(1), (2022).
https://doi.org/10.22090/jwent.2022.01.007
Tabassam, M. N., Haseeb, M., Habib, M. A. B., Murtaza, R., Ali, S., Malik, M. R., Numan, M., Mahmood, M., Mustafa, Z. and Khan, W. Z., Next-Generation Adsorbents for Wastewater Remediation: A Nanotechnology-Driven and AI-Enabled Breakthrough Towards Clean Water, Scholars J. Phy. Math. Statis., 12(08), 323–345 (2025).
https://doi.org/10.36347/sjpms.2025.v12i08.001
Wang, Z., Xu, W., Jie, F., Zhao, Z., Zhou, K. and Liu, H., The selective adsorption performance and mechanism of multiwall magnetic carbon nanotubes for heavy metals in wastewater, Sci. Rep., 11(1), 16878 (2021).
https://doi.org/10.1038/s41598-021-96465-7
Yang, X., Liu, P. and Yu, H., Adsorption of heavy metals from wastewater using reduced graphene oxide@titanate hybrids in batch and fixed bed systems, BMC Chem., 19(1), 72 (2025).
