IWT/
Articles/
2508001093
  • Open Access
  • Perspective

Interdisciplinary Integration and Innovation of Hybrid Models for Future Intelligent Wastewater Treatment

  • Runze Xu 1, *,   
  • Jia-Shun Cao 1,   
  • Fang Fang 1,   
  • Cheng Song 1,   
  • Bing-Jie Ni 2,   
  • Jinyang Luo 1

Received: 09 May 2025 | Revised: 06 Aug 2025 | Accepted: 07 Aug 2025 | Published: 12 Aug 2025

Abstract

The operation of modern wastewater treatment plants has gradually transformed from the empirical paradigm to the computational paradigm. The potential application of mathematical models including mechanistic models and data-driven models have been extensively investigated to predict and improve the performance and efficiency of wastewater treatment processes. However, this paper points out that inherent weaknesses still exist in the standalone model attributed to the high complexity of wastewater treatment processes, emerging prediction targets, limitation of data availability, and lack of critical features in model development. Instead, hybrid models that combine mechanistic models with machine learning models may establish a superior approach to potentially address the limitations of those two modeling strategies mentioned above. Serial, parallel, and circular structures in hybrid models have been proposed to solve issues involved in wastewater treatment processes, whereas closer and deeper cooperation between mechanistic and data-driven models should be explored for solving more important functional scopes involved in the wastewater treatment field. We hope this paper can inspire the idea of developing hybrid models to support intelligent decision-making for wastewater treatment processes.

References 

  • 1.
    Gao, P. Chasing “Emerging” Contaminants: An Endless Journey toward Environmental Health. Environ. Sci. Technol. 2024, 58, 1790–1792. https://doi.org/10.1021/acs.est.3c10630.
  • 2.
    Liu, Q.; Flores-Alsina, X.; Ramin, E.; et al. Making waves: Power-to-X for the Water Resource Recovery Facilities of the future. Water Res. 2024, 257, 121691. https://doi.org/10.1016/j.watres.2024.121691.
  • 3.
    Fu, G.; Savic, D.; Butler, D. Making Waves: Towards data-centric water engineering. Water Res. 2024, 256, 121585. https://doi.org/10.1016/j.watres.2024.121585.
  • 4.
    Li, K.; Duan, H.; Liu, L.; et al. An Integrated First Principal and Deep Learning Approach for Modeling Nitrous Oxide Emissions from Wastewater Treatment Plants. Environ. Sci. Technol. 2022, 56, 2816–2826. https://doi.org/10.1021/acs.est.1c05020.
  • 5.
    Zhu, J.J.; Yang, M.Q.; Ren, Z.J. Machine Learning in Environmental Research: Common Pitfalls and Best Practices. Environ. Sci. Technol. 2023, 57, 17671–17689. https://doi.org/10.1021/acs.est.3c00026.
  • 6.
    Schneider, M.Y.; Quaghebeur, W.; Borzooei, S.; et al. Hybrid modelling of water resource recovery facilities: Status and opportunities. Water Sci. Technol. 2022, 85, 2503–2524. https://doi.org/10.2166/wst.2022.115.
  • 7.
    Wu, X.; Zheng, Z.; Wang, L.; et al. Coupling process-based modeling with machine learning for long-term simulation of wastewater treatment plant operations. J. Environ. Manag. 2023, 341, 118116. https://doi.org/10.1016/j.jenvman.2023.118116.
  • 8.
    Xu, R.-Z.; Cao, J.-S.; Luo, J.-Y.; et al. Integrating mechanistic and deep learning models for accurately predicting the enrichment of polyhydroxyalkanoates accumulating bacteria in mixed microbial cultures. Bioresour. Technol. 2021, 344, 126276. https://doi.org/10.1016/j.biortech.2021.126276.
  • 9.
    Huang, R.; Ma, C.; Ma, J.; et al. Machine learning in natural and engineered water systems. Water Res. 2021, 205, 117666. https://doi.org/10.1016/j.watres.2021.117666.
  • 10.
    Shi, K.; Liang, B.; Cheng, H.Y.; et al. Regulating microbial redox reactions towards enhanced removal of refractory organic nitrogen from wastewater. Water Res. 2024, 258, 121778. https://doi.org/10.1016/j.watres.2024.121778.
  • 11.
    Chang, H.; Zhao, Y.; Bisinella, V.; et al. Climate change impacts of conventional sewage sludge treatment and disposal. Water Res. 2023, 240, 120109. https://doi.org/10.1016/j.watres.2023.120109.
  • 12.
    Xu, R.-Z.; Cao, J.-S.; Ye, T.; et al. Automated machine learning-based prediction of microplastics induced impacts on methane production in anaerobic digestion. Water Res. 2022, 223, 118975–118975. https://doi.org/10.1016/j.watres.2022.118975.
  • 13.
    Xu, R.-Z.; Cao, J.-S.; Wu, Y.; et al. An integrated approach based on virtual data augmentation and deep neural networks modeling for VFA production prediction in anaerobic fermentation process. Water Res. 2020, 184, 116103. https://doi.org/10.1016/j.watres.2020.116103.
  • 14.
    Stiegler, A.N.; Cecchetti, A.R.; Scholes, R.C.; et al. Persistent Trace Organic Contaminants Are Transformed Rapidly under Sulfate- and Fe(III)-Reducing Conditions in a Nature-Based Subsurface Water Treatment System. Environ. Sci. Technol. 2023, 57, 16616–16627. https://doi.org/10.1021/acs.est.3c03719.
  • 15.
    Emaminejad, S.A.; Sparks, J.; Cusick, R.D. Integrating Bio-Electrochemical Sensors and Machine Learning to Predict the Efficacy of Biological Nutrient Removal Processes at Water Resource Recovery Facilities. Environ. Sci. Technol. 2023, 57, 18372–18381. https://doi.org/10.1021/acs.est.3c00352.
  • 16.
    Samuelsson, O.; Lindblom, E.U.; Bjork, A.; et al. To calibrate or not to calibrate, that is the question. Water Res. 2023, 229, 119338. https://doi.org/10.1016/j.watres.2022.119338.
  • 17.
    Thibeault, V.; Allard, A.; Desrosiers, P. The low-rank hypothesis of complex systems. Nat. Phys. 2024, 20, 294–302. https://doi.org/10.1038/s41567-023-02303-0.
  • 18.
    Zhao, J.; Shang, C.; Yin, R. Developing a hybrid model for predicting the reaction kinetics between chlorine and micropollutants in water. Water Res. 2023, 247, 120794. https://doi.org/10.1016/j.watres.2023.120794.
  • 19.
    Pan, Y.; Dagnew, M. A new approach to estimating oxygen off-gas fraction and dynamic alpha factor in aeration systems using hybrid machine learning and mechanistic models. J. Water Process. Eng. 2022, 48, 102924. https://doi.org/10.1016/j.jwpe.2022.102924.
  • 20.
    Fang, F.; Ni, B.-J.; Xie, W.-M.; et al. An integrated dynamic model for simulating a full-scale municipal wastewater treatment plant under fluctuating conditions. Chem. Eng. J. 2010, 160, 522–529. https://doi.org/10.1016/j.cej.2010.03.063.
  • 21.
    Cong, Q.-m.; Bo, G.-h.; Shi, H.-y. Integrated soft sensor of COD for WWTP based on ASP model and RBF neural network. Meas. Control 2023, 56, 295–303. https://doi.org/10.1177/00202940221089272.
  • 22.
    Cheng, X.; Guo, Z.; Shen, Y.; et al. Knowledge and data-driven hybrid system for modeling fuzzy wastewater treatment process. Neural Comput. Appl. 2023, 35, 7185–7206. https://doi.org/10.1007/s00521-021-06499-1.
  • 23.
    Chen, Z.; Zhang, J.; Chu, Q.; et al. Study on hybrid modeling of urban wastewater treatment process. In Proceedings of the 34th Chinese Control and Decision Conference (CCDC), Hefei, China, 15–17 August 2022; pp. 792–797.
  • 24.
    Kumar, B.S.; Venkateswarlu, C. Estimating biofilm reaction kinetics using hybrid mechanistic-neural network rate function model. Bioresour. Technol. 2012, 103, 300–308. https://doi.org/10.1016/j.biortech.2011.10.006.
  • 25.
    Xu, R.-Z.; Cao, J.-S.; Luo, J.-Y.; et al. Data-driven neural networks for biological wastewater resource recovery: Development and challenges. J. Clean. Prod. 2024, 476, 143781. https://doi.org/10.1016/j.jclepro.2024.143781.
  • 26.
    Ye, J.; Do, N.C.; Zeng, W.; et al. Physics-informed neural networks for hydraulic transient analysis in pipeline systems. Water Res. 2022, 221, 118828. https://doi.org/10.1016/j.watres.2022.118828.
  • 27.
    Novikov, I.S.; Gubaev, K.; Podryabinkin, E.V.; et al. The MLIP package: Moment tensor potentials with MPI and active learning. Mach. Learn. Sci. Technol. 2021, 2, 025002. https://doi.org/10.1088/2632-2153/abc9fe.
  • 28.
    Koksal, E.; Asrav, T.; Esenboga, E.; et al. Physics-informed and data-driven modeling of an industrial wastewater treatment plant with actual validation. Comput. Chem. Eng. 2024, 189, 108801. https://doi.org/10.1016/j.compchemeng.2024.108801.
  • 29.
    Koksal, E.; Aydin, E. A hybrid approach of transfer learning and physics-informed modelling: Improving dissolved oxygen concentration prediction in an industrial wastewater treatment plant. Chem. Eng. Sci. 2025, 304, 121088 https://doi.org/10.1016/j.ces.2024.121088.
  • 30.
    Guo, Z.; Zhang, Q.Q.; Cai, Y.Y.; et al. Hybrid Physical Mechanism and Artificial Intelligence-Based Model for Evaluating Nonpoint Source Pesticide Pollution at a Megacity Scale. Environ. Sci. Technol. 2025, 59, 11083–11094. https://doi.org/10.1021/acs.est.4c14075.
  • 31.
    Shen, C.; Appling, A.P.; Gentine, P.; et al. Differentiable modelling to unify machine learning and physical models for geosciences. Nat. Rev. Earth Environ. 2023, 4, 552–567. https://doi.org/10.1038/s43017-023-00450-9.
  • 32.
    Zou, X.; Guo, H.; Jiang, C.; et al. Physics-informed neural network-based serial hybrid model capturing the hidden kinetics for sulfur-driven autotrophic denitrification process. Water Res. 2023, 243, 120331. https://doi.org/10.1016/j.watres.2023.120331.
  • 33.
    Quaghebeur, W.; Torfs, E.; De Baets, B.; et al. Hybrid differential equations: Integrating mechanistic and data-driven techniques for modelling of water systems. Water Res. 2022, 213, 118166. https://doi.org/10.1016/j.watres.2022.118166.
Share this article:
Download PDF
Issue
Volume 1, Issue 1
How to Cite
Xu, R.; Cao, J.-S.; Fang, F.; Song, C.; Ni, B.-J.; Luo, J. Interdisciplinary Integration and Innovation of Hybrid Models for Future Intelligent Wastewater Treatment. Innovations in Water Treatment 2025, 1 (1), 1.
RIS
BibTex
Copyright & License
article copyright Image
Copyright (c) 2025 by the authors.