Predicting Wastewater Characteristics Using Artificial Neural Network and Machine Learning Methods for Enhanced Operation of Oxidation Ditch
Source abstract
Abstract
This study investigates the operational efficiency of the lab-scale oxidation ditch (OD) functioning in simultaneous nitrification and denitrification modes, focusing on forecasting biochemical oxygen demand (BOD5) concentrations over a five-day horizon. This forecasting capability aims to optimize the operational regime of aeration tanks by adjusting the specific load on organic pollutants through active sludge dosage modulation. A comprehensive statistical analysis was conducted to identify trends and seasonality alongside significant correlations between the forecasted values and various time lags. A total of 20 time lags and the “month” feature were selected as significant predictors. These models employed include Multi-head Attention Gated Recurrent Unit (MAGRU), long short-term memory (LSTM), Autoregressive Integrated Moving Average–Long Short-Term Memory (ARIMA–LSTM), and Prophet and gradient boosting models: CatBoost and XGBoost. Evaluation metrics (Mean Squared Error (MSE), Mean Absolute Error (MAE), Symmetric Mean Absolute Percentage Error (SMAPE), and Coefficient of Determination (R2)) indicated similar performance across models, with ARIMA–LSTM yielding the best results. This architecture effectively captures short-term trends associated with the variability of incoming wastewater. The SMAPE score of 1.052% on test data demonstrates the model’s accuracy and highlights the potential of integrating artificial neural networks (ANN) and machine learning (ML) with mechanistic models for optimizing wastewater treatment processes. However, residual analysis revealed systematic overestimation, necessitating further exploration of significant predictors across various datasets to enhance forecasting quality.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Water Quality Monitoring and Analysis · Water Quality Monitoring Technologies · Fault Detection and Control Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Research and Education Centre “Water Supply and Wastewater Treatment”, Moscow State University of Civil Engineering, 26, Yaroslaskoye Highway, Moscow 129337, Russia
Funding
Moscow State University of Civil Engineering
References (50)
Show source-provided references
1. Alali, Y., Harrou, F., and Sun, Y. (2023). Unlocking the potential of wastewater treatment: Machine learning based energy consumption prediction. Water, 15.10.3390/w15132349 ↗
2. Halalsheh, N., Alshboul, O., Shehadeh, A., Al Mamlook, R.E., Al-Othman, A., Tawalbeh, M., Almuflih, A.S., and Papelis, C. (2022). Breakthrough curves prediction of selenite adsorption on chemically modified zeolite using boosted decision tree algorithms for water treatment applications. Water, 14.10.3390/w14162519 ↗
3. Applications of machine learning algorithms for biological wastewater treatment: Updates and perspectives10.1007/s10098-020-01993-x ↗
4. Gulshin, I., and Kuzina, O. (2024). Machine Learning Methods for the Prediction of Wastewater Treatment Efficiency and Anomaly Classification with Lack of Historical Data. Appl. Sci., 14.10.3390/app142210689 ↗
5. Zhang, Y., Wu, H., Xu, R., Wang, Y., Chen, L., and Wei, C. (2024). Machine learning modeling for the prediction of phosphorus and nitrogen removal efficiency and screening of crucial microorganisms in wastewater treatment plants. Sci. Total Environ., 907.10.1016/j.scitotenv.2023.167730 ↗
6. El-Rawy, M., Abd-Ellah, M.K., Fathi, H., and Ahmed, A.K.A. (2021). Forecasting effluent and performance of wastewater treatment plant using different machine learning techniques. J. Water Process Eng., 44.10.1016/j.jwpe.2021.102380 ↗
7. Wastewater treatment aeration process optimization: A data mining approach10.1016/j.jenvman.2016.07.047 ↗
8. Machine learning classification algorithms for inadequate wastewater treatment risk mitigation10.1016/j.psep.2022.01.065 ↗
9. Zaghloul, M.S., and Achari, G. (2022). Application of machine learning techniques to model a full-scale wastewater treatment plant with biological nutrient removal. J. Environ. Chem. Eng., 10.10.1016/j.jece.2022.107430 ↗
10. Sakiewicz, P., Piotrowski, K., Ober, J., and Karwot, J. (2020). Innovative artificial neural network approach for integrated biogas–wastewater treatment system modelling: Effect of plant operating parameters on process intensification. Renew. Sustain. Energy Rev., 124.10.1016/j.rser.2020.109784 ↗
11. Jawad, J., Hawari, A.H., and Zaidi, S.J. (2021). Artificial neural network modeling of wastewater treatment and desalination using membrane processes: A review. Chem. Eng. J., 419.10.1016/j.cej.2021.129540 ↗
12. Warren-Vega, W.M., Montes-Pena, K.D., Romero-Cano, L.A., and Zarate-Guzman, A.I. (2024). Development of an artificial neural network (ANN) for the prediction of a pilot scale mobile wastewater treatment plant performance. J. Environ. Manag., 366.10.1016/j.jenvman.2024.121612 ↗
13. Waqas, S., Harun, N.Y., Sambudi, N.S., Arshad, U., Nordin, N.A.H.M., Bilad, M.R., Saeed, A.A.H., and Malik, A.A. (2022). SVM and ANN modelling approach for the optimization of membrane permeability of a membrane rotating biological contactor for wastewater treatment. Membranes, 12.10.3390/membranes12090821 ↗
14. Wang, M., Xu, X., Yan, Z., and Wang, H. (2021). An online optimization method for extracting parameters of multi-parameter PV module model based on adaptive Levenberg-Marquardt algorithm. Energy Convers. Manag., 245.10.1016/j.enconman.2021.114611 ↗
15. Ridha, H.M., Hizam, H., Mirjalili, S., Othman, M.L., Ya’acob, M.E., Ahmadipour, M., and Ismaeel, N.Q. (2022). On the problem formulation for parameter extraction of the photovoltaic model: Novel integration of hybrid evolutionary algorithm and Levenberg Marquardt based on adaptive damping parameter formula. Energy Convers. Manag., 256.10.1016/j.enconman.2022.115403 ↗
16. Ranade, N.V., Nagarajan, S., Sarvothaman, V., and Ranade, V.V. (2021). ANN based modelling of hydrodynamic cavitation processes: Biomass pre-treatment and wastewater treatment. Ultrason. Sonochem., 72.10.1016/j.ultsonch.2020.105428 ↗
17. Sibiya, N.P., Amo-Duodu, G., Tetteh, E.K., and Rathilal, S. (2022). Model prediction of coagulation by magnetised rice starch for wastewater treatment using response surface methodology (RSM) with artificial neural network (ANN). Sci. Afr., 17.10.1016/j.sciaf.2022.e01282 ↗
18. Application of a combined response surface methodology (RSM)-artificial neural network (ANN) for multiple target optimization and prediction in a magnetic coagulation process for secondary effluent from municipal wastewater treatment plants10.1007/s11356-021-18060-7 ↗
19. Xu, B., Pooi, C.K., Tan, K.M., Huang, S., Shi, X., and Ng, H.Y. (2023). A novel long short-term memory artificial neural network (LSTM)-based soft-sensor to monitor and forecast wastewater treatment performance. J. Water Process Eng., 54.10.1016/j.jwpe.2023.104041 ↗
20. Farhi, N., Kohen, E., Mamane, H., and Shavitt, Y. (2021). Prediction of wastewater treatment quality using LSTM neural network. Environ. Technol. Innov., 23.10.1016/j.eti.2021.101632 ↗
21. LSTM-based autoencoder models for real-time quality control of wastewater treatment sensor data10.2166/hydro.2024.167 ↗
22. Kow, P.Y., Liou, J.Y., Sun, W., Chang, L.C., and Chang, F.J. (2024). Watershed groundwater level multistep ahead forecasts by fusing convolutional-based autoencoder and LSTM models. J. Environ. Manag., 351.10.1016/j.jenvman.2023.119789 ↗
23. Dual-attention LSTM autoencoder for fault detection in industrial complex dynamic processes10.1016/j.psep.2024.02.042 ↗
24. Safder, U., Kim, J., Pak, G., Rhee, G., and You, K. (2022). Investigating machine learning applications for effective real-time water quality parameter monitoring in full-scale wastewater treatment plants. Water, 14.10.3390/w14193147 ↗
25. Li, J., Dong, J., Chen, Z., Li, X., Yi, X., Niu, G., He, J., Lu, S., Ke, Y., and Huang, M. (2023). Free nitrous acid prediction in ANAMMOX process using hybrid deep neural network model. J. Environ. Manag., 345.10.1016/j.jenvman.2023.118566 ↗
26. Xie, Y., Mai, W., Ke, S., Zhang, C., Chen, Z., Wang, X., Li, Y., Dionysiou, D.D., and Huang, M. (2024). Artificial intelligence-implemented prediction and cost-effective optimization of micropollutant photodegradation using g-C3N4/Bi2O3 heterojunction. Chem. Eng. J., 499.10.1016/j.cej.2024.156029 ↗
27. Wan, X., Li, X., Wang, X., Yi, X., Zhao, Y., He, X., Wu, R., and Huang, M. (2022). Water quality prediction model using Gaussian process regression based on deep learning for carbon neutrality in papermaking wastewater treatment system. Environ. Res., 211.10.1016/j.envres.2022.112942 ↗
28. FDA-SCN Network Based Soft Sensor for Wastewater Treatment Process10.15244/pjoes/169617 ↗
29. Khozani, Z.S., Banadkooki, F.B., Ehteram, M., Ahmed, A.N., and El-Shafie, A. (2022). Combining autoregressive integrated moving average with Long Short-Term Memory neural network and optimisation algorithms for predicting ground water level. J. Clean. Prod., 348.10.1016/j.jclepro.2022.131224 ↗
30. Innovative approach for predicting biogas production from large-scale anaerobic digester using long-short term memory (LSTM) coupled with genetic algorithm (GA)10.1016/j.wasman.2023.12.046 ↗
31. Wang, Q., Wang, H., Gupta, C., Rao, A.R., and Khorasgani, H. (2020, January 10–13). A Non-Linear Function-on-Function Model for Regression with Time Series Data. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9378087 ↗
32. Ly, Q.V., Truong, V.H., Ji, B., Nguyen, X.C., Cho, K.H., Ngo, H.H., and Zhang, Z. (2022). Exploring potential machine learning application based on big data for prediction of wastewater quality from different full-scale wastewater treatment plants. Sci. Total Environ., 832.10.1016/j.scitotenv.2022.154930 ↗
33. Luo, J., Luo, Y., Cheng, X., Liu, X., Wang, F., Fang, F., Cao, J., Liu, W., and Xu, R. (2023). Prediction of biological nutrients removal in full-scale wastewater treatment plants using H2O automated machine learning and back propagation artificial neural network model: Optimization and comparison. Bioresour. Technol., 390.10.1016/j.biortech.2023.129842 ↗
34. Comparative Performance of Three Machine Learning Models in Predicting Influent Flow Rates and Nutrient Loads at Wastewater Treatment Plants10.1021/acsestwater.3c00155 ↗
35. Stochastic evolutionary-based optimization for rapid diagnosis and energy-saving in pilot-and full-scale carrousel oxidation ditches
36. Gogina, E., and Gulshin, I. (2021). Characteristics of low-oxygen oxidation ditch with improved nitrogen removal. Water, 13.10.3390/w13243603 ↗
37. Machine Learning and Automatic ARIMA/Prophet Models-Based Forecasting of COVID-19: Methodology, Evaluation, and Case Study in SAARC Countries10.1007/s00477-022-02307-x ↗
38. Optimization of a Novel Engineered Ecosystem Integrating Carbon, Nitrogen, Phosphorus, and Sulfur Biotransformation for Saline Wastewater Treatment Using an Interpretable Machine Learning Approach10.1021/acs.est.4c03160 ↗
39. Al Nuaimi, H., Abdelmagid, M., Bouabid, A., Chrysikopoulos, C.V., and Maalouf, M. (2023). Classification of WatSan Technologies using machine learning techniques. Water, 15.10.3390/w15152829 ↗
40. Wang, Q., Li, Z., Cai, J., Zhang, M., Liu, Z., Xu, Y., and Li, R. (2023). Spatially adaptive machine learning models for predicting water quality in Hong Kong. J. Hydrol., 622.10.1016/j.jhydrol.2023.129649 ↗
41. Performance Comparison of ARIMA, LSTM, and Prophet Methods in Sales Forecasting
42. Uzel, Z. (2023). Comparative Analysis of LSTM, ARIMA, and Facebook’s Prophet for Traffic Forecasting: Advancements, Challenges, and Limitations. [Ph.D. Thesis, Delft University of Technology].
43. Forecasting the Monkeypox Outbreak Using ARIMA, Prophet, NeuralProphet, and LSTM Models in the United States10.3390/forecast5010005 ↗
44. Singh, N.K., Yadav, M., Singh, V., Padhiyar, H., Kumar, V., Bhatia, S.K., and Show, P.L. (2023). Artificial intelligence and machine learning-based monitoring and design of biological wastewater treatment systems. Bioresour. Technol., 369.10.1016/j.biortech.2022.128486 ↗
45. Prediction model of sparse autoencoder-based bidirectional LSTM for wastewater flow rate10.1007/s11227-022-04827-3 ↗
46. Alvi, M., Batstone, D., Mbamba, C.K., Keymer, P., French, T., Ward, A., Dwyer, J., and Cardell-Oliver, R. (2023). Deep learning in wastewater treatment: A critical review. Water Res., 245.10.1016/j.watres.2023.120518 ↗
47. Al Saleem, M., Harrou, F., and Sun, Y. (2024). Explainable Machine Learning Methods for Predicting Water Treatment Plant Features under Varying Weather Conditions. Results Eng., 21.10.1016/j.rineng.2024.101930 ↗
48. Ekinci, E., Özbay, B., Omurca, S.İ., Sayın, F.E., and Özbay, İ. (2023). Application of Machine Learning Algorithms and Feature Selection Methods for Better Prediction of Sludge Production in a Real Advanced Biological Wastewater Treatment Plant. J. Environ. Manag., 348.10.1016/j.jenvman.2023.119448 ↗
49. Ching, P.M.L., Zou, X., Wu, D., So, R.H.Y., and Chen, G.H. (2022). Development of a wide-range soft sensor for predicting wastewater BOD5 using an eXtreme gradient boosting (XGBoost) machine. Environ. Res., 210.10.1016/j.envres.2022.112953 ↗
50. A Machine Learning Approach for Anomaly Detection in Environmental IoT-Driven Wastewater Purification Systems