Predictive analysis of urban wastewater capacity using ANN and ODE model: A case study

Abstract

The discharge of urban wastewater represents a significant aspect to be considered in the development and design of water and wastewater treatment projects. In this study, the annual urban wastewater discharge was estimated using an artificial neural network (ANN) and differential equations. In order to achieve this, data pertaining to the recorded wastewater per capita amount for the Kayseri province (located in Turkey) over a 17-year period between 2003 and 2020, the city's population, capacity, number of WWTPs, the amount of daily wastewater discharged per person, and the wastewater treated in WWTPs (y(t)) were collated. As the initial data set was insufficient, it was augmented using the ARIMA model and then normalised. The augmented and normalised data was trained with ANN on two occasions, thus demonstrating the impact of other variables on the y(t) variable. Additionally, mathematical ANN activation functions in the form of a tangent hyperbolic function were proposed for this variable. Subsequently, the arbitrary parameters employed in a linear system comprising differential equations representing the aforementioned five variables were estimated utilising the normalised original data, thereby facilitating the formulation of an Ordinary Differential Equation (ODE) model. The performance of two ANN and ODE models was evaluated on normalized real data, and the results were compared. Consequently, the estimation of the quantity of wastewater with the lowest error rate of 0.00001 MSE among the models incorporating four time-dependent variables as inputs was conducted using the ODE model. The model exhibited an R² value of 0.9363 and a MAPE value of 0.0231. The promising estimation results obtained demonstrate the potential utility of this approach for the efficient management of wastewater demand and the protection of valuable water resources.

Keywords

• Wastewater quantity
• ODE model
• ANN activation function
• parameter estimation
• MSE

References

1. C. Vörösmarty ve J. S. R. L. P. Green, “Global water resources: Vulnerability from climate change and population growth,” Science, vol. 289, no. 5477, 284-288, 2000.
2. V. Novotny, “Diffuse pollution from agriculture — A worldwide outlook,” Water Science and Technology, vol. 39, no. 3, 1-13, 1999.
3. J. McLean, S. B. Cleveland, M. D. II, M. P. Lucas, R. J. Longman, T. W. Giambelluca ve G. A. Jacobs, “Building a portal for climate data—Mapping automation, visualization, and dissemination,” Concurrency and Computation: Practice and Experience, p. e6727, 2023.
4. M. Ahmadi, M. E. Lotfy, R. Shigenobu, A. M. Howlader ve T. Senjyu, “Optimal Sizing of Multiple Renewable Energy Resources and PV Inverter Reactive Power Control Encompassing Environmental, Technical, and Economic Issues,” IEEE Systems Journal, 3026--3037, 2019.
5. S. S. Biswas, “Role of chat gpt in public health,” Annals of biomedical engineering, 868-869, 2023.
6. G. Zhang, Y. Ge, Z. Ye ve M. Al-Bahrani, “Multi-objective planning of energy hub on economic aspects and resources with heat and power sources, energizable, electric vehicle and hydrogen storage system due to uncertainties and demand response,” Journal of Energy Storage, p. 106160, 2023.
7. M. Carrascal, E. Sánchez-Jiménez, J. Fang, C. Pérez-López, A. Ginebreda, D. Barceló ve J. Abian, “Sewage protein information mining: discovery of large biomolecules as biomarkers of population and industrial activities,” Environmental science & technology, 10929--10939, 2023.
8. C. Johnson ve S. J. Bell, “Linking emerging contaminants to production and consumption practices,” Wiley Interdisciplinary Reviews: Water, p. e1615, 2023.

9. J. Li, X. Li, H. Liu, L. Gao, W. Wang, Z. Wang, T. Zhou ve Q. Wang, “Climate change impacts on wastewater infrastructure: A systematic review and typological adaptation strategy,” Water Research, 120282, 2023.
10. C. Song, J.-J. Zhu, J. L. Willis, D. P. Moore, M. A. Zondlo ve Z. J. Ren, “Methane Emissions from Municipal Wastewater Collection and Treatment Systems,” Environmental Science & Technology, 2248--2261, 2023.
11. R. Herrera-Navarrete, A. Colı´n-Cruz, H. J. Arellano-Wences, M. L. Sampedro-Rosas, J. L. Rosas-Acevedo ve A. L. Rodrı´guez-Herrera, “Municipal wastewater treatment plants: Gap, challenges, and opportunities in environmental management,” Environmental Management, 75--88, 2022.
12. M. M. Emily ve G. Muyengwa, “Maintenance of municipality infrastructure: a case study on service delivery in Limpopo Province at South Africa,” American Journal of Operations Research, 309--323, 2021.
13. S. Geyler, N. Bedtke ve E. Gawel, “Sustainable stormwater management in existing settlements—Municipal strategies and current governance trends in Germany,” Sustainability, p. 5510, 2019.
14. C. T. Finnerty, A. E. Childress, K. M. Hardy, E. M. Hoek, M. S. Mauter, M. H. Plumlee, J. B. Rose, M. D. Sobsey, P. Westerhoff, P. J. Alvarez ve others, “The Future of Municipal Wastewater Reuse Concentrate Management: Drivers, Challenges, and Opportunities,” Environmental Science & Technology, 2023.
15. M. Nasr, M. Moustafa, H. Seif ve G. E. Kobrosy, “Application of Artificial Neural Network (ANN) for the prediction of EL-AGAMY wastewater treatment plant performance-EGYPT,” Alexandria engineering journal, vol. 51, no. 1, 37-43, 2012.
16. P. Wongburi ve J. K. Park, “Prediction of Wastewater Treatment Plant Effluent Water Quality Using Recurrent Neural Network (RNN) Models,” Water, p. 3325, 2023.
17. Y. Yang, K.-R. Kim, R. Kou, Y. Li, J. Fu, L. Zhao ve H. Liu, “Prediction of effluent quality in a wastewater treatment plant by dynamic neural network modeling,” Process Safety and Environmental Protection, 515-524, 2022.
18. H. Guo, K. Jeong, J. Lim, J. Jo, Y. M. Kim, J.-p. Park, J. H. Kim ve K. H. Cho, “Prediction of effluent concentration in a wastewater treatment plant using machine learning models”, Journal of Environmental Sciences, no. 32, 90-101, 2015.
19. S. Waqas, N. Y. Harun, N. S. Sambudi, U. Arshan, N. A. H. M. Nordin, M. R. Bilad, A. A. H. Saeed ve A. A. Malik, “SVM and ANN Modelling Approach for the Optimization of Membrane Permeability of a Membrane Rotating Biological Contactor for Wastewater Treatment”, Membranes, vol. 12, no. 9, 821, 2022.
20. K. Godini, G. Azarlan, A. Kimiaei, E. N. Dragoi ve S. Curteanu, “Modeling of a real industrial wastewater treatment plant based on aerated lagoon using a neuro-evolutive technique”, Process Safety and Environmental Protection, vol. 148, 114-124, 2021.
21. A. Tarun ve G. P. Reddy, “Artificial Neural Networks for Waste-water Treatment Plant Control”, Proceedings of International Conference on Industrial Instrumentation and Control , vol. 815, 409-419, 2022.
22. G. y. Zhao, H. Furumai ve M. Fujita, “Supporting data–enhanced hybrid ordinary differential equation model for phosphate dynamics in municipal wastewater treatment”, Bioresource Technology, vol. 409, 131217, 2024.
23. P. Veeresha, M. Yavuz ve C. Baishya, “A computational approach for shallow water forced Korteweg–De Vries equation on critical flow over a hole with three fractional operators,” An International Journal of Optimization and Control: Theories & Applications, vol. 11, no. 3, 52-67, 2021.
24. P. A. Naik, Z. Eskandari, H. E. Shahkari ve K. M. Owolabi, “Bifurcation analysis of a discrete-time prey-predator model,” Bulletin of Biomathematics, vol. 1, no. 2, 111-123, 2023.
25. B. Ersoy, B. Daşbaşı ve E. Aslan, “Mathematical modelling of fiber optic cable with an electro-opticalcladding by incommensurate fractional-order differential equations,” An International Journal of Optimization and Control: Theories & Applications, vol. 14, no. 1, 50-61, 2024.
26. B. Daşbaşı, “Fractional order bacterial infection model with effects of anti-virulence drug and antibiotic,” Chaos, Solitons & Fractals, vol. 170, no. 113331, 1-17, 2023.
27. E. K. Akgül, A. Akgül ve M. Yavuz, “New illustrative applications of integral transforms to financial models with different fractional derivatives,” Chaos, Solitons & Fractals, vol. 146, no. 110877, 2021.
28. L. Boulaasair, “Threshold properties of a stochastic epidemic model with a variable vaccination rate,” Bulletin of Biomathematics, vol. 1, no. 2, 177-191, 2023.
29. U. T. Mustapha, Y. U. Ahmad, A. Yusuf, S. Qureshi ve S. S. Musa, “Transmission dynamics of an age-structured Hepatitis-B infection with differential infectivity,” Bulletin of Biomathematics, vol. 1, no. 2, 124-152, 2023.
30. S. Diehl ve S. Farås, “Control of an ideal activated sludge process in wastewater treatment via an ODE–PDE model,” Journal of Process Control, vol. 23, no. 3, 359-381, 2013.
31. P. Zlateva ve N. Dimitrova, “Analysis of Some Properties of an Activated Sludge Wastewater Treatment Model,” %1 içinde The 6th International Conference on Energy and Environmental Science, 2022.
32. TUIK, “Merkezi Dağıtım Sistemi,” 15 December 2023. [Online]. Available: https://biruni.tuik.gov.tr/medas/?locale=tr.
33. A. Dishan, M. Barel, S. Hizlisoy, R. S. Arslan, H. Hizlisoy, D. A. Gundog, S. Al ve Z. Gonulalan, “The ARIMA model approach for the biofilm-forming capacity prediction of Listeria monocytogenes recovered from carcasses”, BMC Veterinary Research, vol. 20, no. 123, 1-13, 2024.
34. N. Minhaj, R. Ahmed, I. A. Khalique ve M. Imran, “A Comparative Research of Stock Price Prediction of Selected Stock Indexes and the Stock Market by Using Arima Model”, Global Economics Science, vol. 4, no. 1, 1-19, 2022.
35. S. Majumder, “Time Series Analysis — Stationarity Check using Statistical Test”, Analytics Vidhya, 02 05 2020. [Online]. Available: https://medium.com/analytics-vidhya/time-series-analysis-stationarity-check-using-statistical-test-f106e9045370#:~:text=If%20p%20%3E%200.05%2C%20then%20the,present%20data%20and%20past%20data.. [Access: 23 09 2024].
36. “Stationarity and detrending (ADF/KPSS)”, statsmodels, 16 09 2024. [Online]. Available: https://www.statsmodels.org/dev/examples/notebooks/generated/stationarity_detrending_adf_kpss.html#Stationarity-and-detrending-(ADF/KPSS). [Access: 23 09 2024].
37. “Interpret all statistics and graphs for Augmented Dickey-Fuller Test,» Minitab, 01 01 2024. [Online]. Available: https://support.minitab.com/en-us/minitab/help-and-how-to/statistical-modeling/time-series/how-to/augmented-dickey-fuller-test/interpret-the-results/all-statistics-and-graphs/#:~:text=The%20p%2Dvalue%20is%20a,value%20to%20your%20significance%20level.). [Access: 23 09 2024].
38. S. Hizlisoy, R. S. Arslan ve E. Çolakoğlu, “Singer identification model using data augmentation and enhanced feature conversion with hybrid feature vector and machine learning”, EURASIP Journal on Audio, Speech, and Music Processing, vol. 2024, no. 14, 1-14, 2024.
39. R. Nau, “The mathematical structure of arima models,” Duke University Online Article, vol. 1, no. 1, 1-8, 2014.
40. R. Nau, ARIMA models for time series forecasting. Statistical Forecasting: Notes on Regression and Time Series Analysis, Durham: Duke University, 2017.
41. R. S. Arslan ve M. Tasyurek, “AMD-CNN: Android malware detection via feature graph and convolutional neural networks,” Concurrency and Computation: Practice and Experience, p. e7180, 2022.
42. M. Taşyürek, “Odrp: a new approach for spatial street sign detection from exif using deep learning-based object detection, distance estimation, rotation and projection system,” The Visual Computer, 2023.
43. M. Tasyurek ve R. S. Arslan, “RT-Droid: a novel approach for real-time android application analysis with transfer learning-based CNN models,” Journal of Real-Time Image Processing, 1-17, 2023.
44. Y.-c. Wu ve J.-w. Feng, “Development and application of artificial neural network,” Wireless Personal Communications, p. 1645–1656, 2018.
45. A. Baliyan, K. Gaurav ve S. K. Mishra, “A review of short term load forecasting using artificial neural network models,” Procedia Computer Science , p. 121–125, 2015.
46. F. Zakaria, S. A. C. Kar, R. Abdullah, S. I. Ismail ve N. I. M. Enzai, “ A Study on Correlation of Subjects on Electrical Engineering Course Using Artificial Neural Network (ANN),” Asian Journal of University Education, p. 144–155, 2021.
47. B. M. Al-Maqaleh, A. A. Al-Mansoub ve F. N. Al-Badani, “ Forecasting using artificial neural network and statistics models,” International Journal Education and Management Engineering, p. 20–32, 2016.
48. M. M. Saritas ve A. Yasar, “Performance analysis of ANN and Naive Bayes classification algorithm for data classification,” International journal of intelligent systems and applications in engineering, p. 88–91, 2019.
49. S. Agatonovic-Kustrin ve R. Beresford, “Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research,” Journal of pharmaceutical and biomedical analysis, p. 717–727, 2000.
50. F. Amato, A. López, E. M. Peña-Méndez, P. Vanhara, A. Hampl ve J. Havel, “Artificial neural networks in medical diagnosis,” Journal of applied biomedicine, 47-58, 2013.
51. E. Sariev ve G. Germano, “Bayesian regularized artificial neural networks for the estimation of the probability of default,” Quantitative Finance, p. 311–328, 2020.
52. J. Gao, “Performance evaluation of manufacturing collaborative logistics based on BP neural network and rough set,” Neural Computing and Applications, p. 739–754, 2021.
53. P. Jiang, Z. Liu, X. Niu ve L. Zhang, “A combined forecasting system based on statistical method, artificial neural networks, and deep learning methods for short-term wind speed forecasting,” Energy, p. 119361, 2021.
54. A. Escamilla-Garcı´a, G. M. Soto-Zarazúa, M. Toledano-Ayala, E. Rivas-Araiza ve a. A. Gastélum-Barrios, “Applications of artificial neural networks in greenhouse technology and overview for smart agriculture development,” Applied Sciences, p. 3835, 2020.
55. H. Su, W. Qi, C. Yang, J. Sandoval, G. Ferrigno ve E. D. Momi, “Deep neural network approach in robot tool dynamics identification for bilateral teleoperation,” IEEE Robotics and Automation Letters, p. 2943–2949, 2020.
56. R. Shaw ve B. K. Patra, “Classifying students based on cognitive state in flipped learning pedagogy,” Future Generation Computer Systems, p. 305–317, 2022.
57. Q. Cheng, H. Li, Q. Wu, L. Ma ve K. N. Ngan, “Parametric deformable exponential linear units for deep neural networks,” Neural Networks, p. 281–289, 2020.
58. D. Kim, J. Kim ve J. Kim, “Elastic exponential linear units for convolutional neural networks,” Neurocomputing , p. 253–266, 2020.
59. Y. Koçak ve G. Ü. Şiray, “New activation functions for single layer feedforward neural network,” Expert systems with applications, p. 113977, 2021.
60. A. Maniatopoulos ve N. Mitianoudis, “Learnable leaky relu (LeLeLU): An alternative accuracy-optimized activation function,” Information , p. 513, 2021.
61. B. Olimov, S. Karshiev, E. Jang, S. Din, A. Paul ve J. Kim, “Weight initialization based-rectified linear unit activation function to improve the performance of a convolutional neural network model,” Concurrency and Computation: Practice and Experience, p. e6143, 2021.
62. H. Pratiwi, A. P. Windarto, S. Susliansyah, R. R. Aria, S. Susilowati, L. K. Rahayu, Y. Fitriani, A. Merdekawati ve I. R. Rahadjeng, “Sigmoid activation function in selecting the best model of artificial neural networks,” Journal of Physics: Conference Series, p. 012010, 2020.
63. MathWorks. [Online]. Available: https://www.mathworks.com/help/optim/ug/lsqcurvefit.html. [Access: 15 September 2024].
64. O. Toolbox, “Isqcurvefit”, [Online]. Available: http://www.ece.northwestern.edu/local-apps/matlabhelp/toolbox/optim/lsqcurvefit.html. [Access: 15 September 2024].
65. MathWorks, “Isqcurvefit fitting kinetic model to estimate kinetic parameter.”, [Online]. Available: https://www.mathworks.com/matlabcentral/answers/1990058-lsqcurvefit-fitting-kinetic-model-to-estimate-kinetic-parameter. [Access: 15 September 2024].
66. MathWorks, “Fitting two differential equations simultaneously using Isqcurvefit”, [Online]. Available: https://www.mathworks.com/matlabcentral/answers/1657480-fitting-of-two-differential-equations-simultaneously-using-lsqcurvefit. [Access: 15 September 2024].
67. H. Pratiwi, A. P. Windarto, S. Susliansyah, R. R. Aria, S. Susilowati, L. K. Rahayu, Y. Fitriani, A. Merdekawati ve I. R. Rahadjeng, “Sigmoid activation function in selecting the best model of artificial neural networks,” Journal of Physics: Conference Series, p. 012010, 2020.