Brain-inspired multimodal approach for effluent quality prediction using wastewater surface images and water quality data

doi:10.1007/s11783-024-1791-x

Front. Environ. Sci. Eng.

2024, Vol. 18

Issue (3) : 31 https://doi.org/10.1007/s11783-024-1791-x

RESEARCH ARTICLE

Brain-inspired multimodal approach for effluent quality prediction using wastewater surface images and water quality data

Junchen Li^1,², Sijie Lin^2,³, Liang Zhang^4,⁵, Yuheng Liu^4,⁵, Yongzhen Peng^4,⁵(

), Qing Hu^2,³(

)

¹. School of Environment, Harbin Institute of Technology, Harbin 150090, China
². School of Environmental Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China
³. Engineering Innovation Center of SUSTech (Beijing), Southern University of Science and Technology, Beijing 100083, China
⁴. Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
⁵. Engineering Research Center of Intelligence Perception and Autonomous Control, Ministry of Education, Beijing 100124, China

Download: PDF(4930 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

● A novel brain-inspired network accurately predicts sewage effluent quality.

● Sewage-surface images are utilized in data analysis by the model.

● The developed method outperforms traditional ones by reducing error by 23%.

● The model offers the potential for cost-effective monitoring.

Efficiently predicting effluent quality through data-driven analysis presents a significant advancement for consistent wastewater treatment operations. In this study, we aimed to develop an integrated method for predicting effluent COD and NH₃ levels. We employed a 200 L pilot-scale sequencing batch reactor (SBR) to gather multimodal data from urban sewage over 40 d. Then we collected data on critical parameters like COD, DO, pH, NH₃, EC, ORP, SS, and water temperature, alongside wastewater surface images, resulting in a data set of approximately 40246 points. Then we proposed a brain-inspired image and temporal fusion model integrated with a CNN-LSTM network (BITF-CL) using this data. This innovative model synergized sewage imagery with water quality data, enhancing prediction accuracy. As a result, the BITF-CL model reduced prediction error by over 23% compared to traditional methods and still performed comparably to conventional techniques even without using DO and SS sensor data. Consequently, this research presents a cost-effective and precise prediction system for sewage treatment, demonstrating the potential of brain-inspired models.

Keywords Wastewater treatment system Water quality prediction Data driven analysis Brain-inspired model Multimodal data Attention mechanism

Corresponding Author(s): Yongzhen Peng,Qing Hu

About author: Peng Lei and Charity Ngina Mwangi contributed equally to this work.

Issue Date: 07 November 2023

Cite this article:

Junchen Li,Sijie Lin,Liang Zhang, et al. Brain-inspired multimodal approach for effluent quality prediction using wastewater surface images and water quality data[J]. Front. Environ. Sci. Eng., 2024, 18(3): 31.

URL:

https://academic.hep.com.cn/fese/EN/10.1007/s11783-024-1791-x
https://academic.hep.com.cn/fese/EN/Y2024/V18/I3/31

Fig.1 Schematic of the (a) experimental platform and (b) platform structure.

Fig.2 Image feature extraction process.

Fig.3 Image and time series feature fusion based on self-attention.

Fig.4 Model architecture of BITF-CL.

Tab.1 Performance comparison among different models (1-min)

Tab.2 Performance comparison among different models (1-h)

Fig.5 Comparison of NH₃ and COD predictions and actual values for 1-min and 1-h intervals. (a) NH₃ and (b) COD prediction for 1-min; (c) NH₃ and (d) COD prediction for 1-h.

Fig.6 Predictive performance for NH₃ and COD levels using different sensor configurations. (a) RMSE, (b) MAPE, and (c) R² for NH₃; (d) RMSE, (e) MAPE, and (f) R² for COD.

Fig.7 Comparison of predicted and actual values of NH₃ and COD concentration after aeration velocity reduction. Predicted vs actual (a) NH₃ and (b) COD values; Error curve for (c) NH₃ and (d) COD values.

Fig.8 Scatter plot of predicted and actual values of NH₃ and COD concentration. NH₃ prediction for (a) CALL, (b) CNS, and (c) CNDS; COD prediction for (d) CALL, (e) CNS, and (f) CNDS.

1	S Al-Asheh , F S Mjalli , H E Alfadala . (2007). Forecasting influent-effluent wastewater treatment plant using time series analysis and artificial neural network techniques. Chemical Product and Process Modeling, 2(3): 55–80 https://doi.org/10.2202/1934-2659.1063
2	A W Alattabi , C Harris , R Alkhaddar , A Alzeyadi , M J P E Abdulredha . (2017). Online monitoring of a sequencing batch reactor treating domestic wastewater. Procedia Engineering, 196: 800–807 https://doi.org/10.1016/j.proeng.2017.08.010
3	M Bagheri , S A Mirbagheri , M Ehteshami , Z Bagheri . (2015). Modeling of a sequencing batch reactor treating municipal wastewater using multi-layer perceptron and radial basis function artificial neural networks. Process Safety and Environmental Protection, 93: 111–123 https://doi.org/10.1016/j.psep.2014.04.006
4	R Barzegar , M T Aalami , J Adamowski . (2020). Short-term water quality variable prediction using a hybrid CNN–LSTM deep learning model. Stochastic Environmental Research and Risk Assessment, 34(2): 415–433 https://doi.org/10.1007/s00477-020-01776-2
5	N Bekkari , A Zeddouri . (2019). Using artificial neural network for predicting and controlling the effluent chemical oxygen demand in wastewater treatment plant. Management of Environmental Quality, 30(3): 593–608 https://doi.org/10.1108/MEQ-04-2018-0084
6	H Boztoprak , Y Özbay , D Güçlü , M Küçükhemek . (2016). Prediction of sludge volume index bulking using image analysis and neural network at a full-scale activated sludge plant. Desalination and Water Treatment, 57(37): 17195–17205 https://doi.org/10.1080/19443994.2015.1085909
7	D Chicco , M J Warrens , G Jurman . (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ. Computer Science, 7: e623 https://doi.org/10.7717/peerj-cs.623
8	J G CostaA M S PauloC L AmorimA L AmaralP M L CastroE C FerreiraD P (2022) Mesquita. Quantitative image analysis as a robust tool to assess effluent quality from an aerobic granular sludge system treating industrial wastewater. Chemosphere, 291(Pt 2): 132773
9	J Fernandez de Canete , P Del Saz-Orozco , R Baratti , M Mulas , A Ruano , A Garcia-Cerezo . (2016). Soft-sensing estimation of plant effluent concentrations in a biological wastewater treatment plant using an optimal neural network. Expert Systems with Applications, 63: 8–19 https://doi.org/10.1016/j.eswa.2016.06.028
10	X Fu , Q Zheng , G Jiang , K Roy , L Huang , C Liu , K Li , H Chen , X Song , J Chen . (2023). Water quality prediction of copper-molybdenum mining-beneficiation wastewater based on the PSO-SVR model. Frontiers of Environmental Science & Engineering, 17(8): 98 https://doi.org/10.1007/s11783-023-1698-9
11	R B Geerdink , R Sebastiaan Van Den Hurk , O J Epema . (2017). Chemical oxygen demand: historical perspectives and future challenges. Analytica Chimica Acta, 961: 1–11 https://doi.org/10.1016/j.aca.2017.01.009
12	F Granata , S Papirio , G Esposito , R Gargano , G De Marinis . (2017). Machine learning algorithms for the forecasting of wastewater quality indicators. Water, 9(2): 105–117 https://doi.org/10.3390/w9020105
13	H Guo , K Jeong , J Lim , J Jo , Y M Kim , J P Park , J H Kim , K H Cho . (2015). Prediction of effluent concentration in a wastewater treatment plant using machine learning models. Journal of Environmental Sciences (China), 32: 90–101 https://doi.org/10.1016/j.jes.2015.01.007
14	S Guštin , R Marinšek-Logar . (2011). Effect of pH, temperature and air flow rate on the continuous ammonia stripping of the anaerobic digestion effluent. Process Safety and Environmental Protection, 89(1): 61–66 https://doi.org/10.1016/j.psep.2010.11.001
15	M B Khan , H Nisar , C A Ng . (2018). Image processing and analysis of phase-contrast microscopic images of activated sludge to monitor the wastewater treatment plants. IEEE Access: Practical Innovations, Open Solutions, 6: 1778–1791 https://doi.org/10.1109/ACCESS.2017.2780249
16	D Lahat , T Adali , C Jutten . (2015). Multimodal data fusion: an overview of methods, challenges, and prospects. Proceedings of the IEEE, 103(9): 1449–1477 https://doi.org/10.1109/JPROC.2015.2460697
17	J W Lee , C Suh , Y S Hong , H S Shin . (2011). Sequential modelling of a full-scale wastewater treatment plant using an artificial neural network. Bioprocess and Biosystems Engineering, 34(8): 963–973 https://doi.org/10.1007/s00449-011-0547-6
18	S I Lee , S J Yoo . (2020). Multimodal deep learning for finance: integrating and forecasting international stock markets. Journal of Supercomputing, 76(10): 8294–8312 https://doi.org/10.1007/s11227-019-03101-3
19	J Li , D Hong , L Gao , J Yao , K Zheng , B Zhang , J Chanussot . (2022a). Deep learning in multimodal remote sensing data fusion: a comprehensive review. International Journal of Applied Earth Observation and Geoinformation, 112: 102926 https://doi.org/10.1016/j.jag.2022.102926
20	J Li , Y Liu , H Jiang , M Yang , S Lin , Q Hu . (2022b). A multi-view image feature fusion network applied in analysis of aeration velocity for WWTP. Water, 14(3): 345–357 https://doi.org/10.3390/w14030345
21	G Litjens , T Kooi , Bejnordi B Ehteshami , A A A Setio , F Ciompi , M Ghafoorian , der Laak J A van , Ginneken B van , C I Sánchez . (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42: 60–88 https://doi.org/10.1016/j.media.2017.07.005
22	L Liu , S J Sheng , J T Yin , L Na . (2014). Prediction and realization of DO in sewage treatment based on machine vision and BP neural network. Telecommunication Computing Electronics and Control, 12(4): 890–896 https://doi.org/10.12928/telkomnika.v12i4.437
23	Z J Liu , J Q Wan , Y W Ma , Y Wang . (2019). Online prediction of effluent COD in the anaerobic wastewater treatment system based on PCA-LSSVM algorithm. Environmental Science and Pollution Research International, 26(13): 12828–12841 https://doi.org/10.1007/s11356-019-04671-8
24	A Mehonic , A J Kenyon . (2022). Brain-inspired computing needs a master plan. Nature, 604(7905): 255–260 https://doi.org/10.1038/s41586-021-04362-w
25	G Muhammad , F Alshehri , F Karray , A E Saddik , M Alsulaiman , T H Falk . (2021). A comprehensive survey on multimodal medical signals fusion for smart healthcare systems. Information Fusion, 76: 355–375 https://doi.org/10.1016/j.inffus.2021.06.007
26	D Mulkerrins , A D Dobson , E Colleran . (2004). Parameters affecting biological phosphate removal from wastewaters. Environment International, 30(2): 249–259 https://doi.org/10.1016/S0160-4120(03)00177-6
27	D Mullins , D Coburn , L Hannon , E Jones , E Clifford , M Glavin . (2018). Using image processing for determination of settled sludge volume. Water Science and Technology, 78(2): 390–401 https://doi.org/10.2166/wst.2018.315
28	M S Nasr , M A Moustafa , H A Seif , G El Kobrosy . (2012). Application of Artificial Neural Network (ANN) for the prediction of EL-AGAMY wastewater treatment plant performance-EGYPT. Alexandria Engineering Journal, 51(1): 37–43 https://doi.org/10.1016/j.aej.2012.07.005
29	Z Niu , G Zhong , H Yu . (2021). A review on the attention mechanism of deep learning. Neurocomputing, 452: 48–62 https://doi.org/10.1016/j.neucom.2021.03.091
30	B Pang , E Nijkamp , Y N Wu . (2020). Deep learning with TensorFlow: a review. Journal of Educational and Behavioral Statistics, 45(2): 227–248 https://doi.org/10.3102/1076998619872761
31	A Paszke , S Gross , F Massa , A Lerer , J Bradbury , G Chanan , T Killeen , Z Lin , N Gimelshein , L Antiga . (2019). Pytorch: an imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, 32: 8026–8037
32	C Peng , Y Li , L Jiao , Y Chen , R Shang . (2019). Densely based multi-scale and multi-modal fully convolutional networks for high-resolution remote-sensing image semantic segmentation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(8): 2612–2626 https://doi.org/10.1109/JSTARS.2019.2906387
33	H Poutiainen , H Niska , H Heinonen-Tanski , M Kolehmainen . (2010). Use of sewer on-line total solids data in wastewater treatment plant modelling. Water Science and Technology, 62(4): 743–750 https://doi.org/10.2166/wst.2010.317
34	W Rawat , Z Wang . (2017). Deep convolutional neural networks for image classification: a comprehensive review. Neural Computation, 29(9): 2352–2449 https://doi.org/10.1162/neco_a_00990
35	A Sengupta , Y Ye , R Wang , C Liu , K Roy . (2019). Going deeper in spiking neural networks: VGG and residual architectures. Frontiers in Neuroscience, 13: 95–105 https://doi.org/10.3389/fnins.2019.00095
36	M V Storey , B Van Der Gaag , B P Burns . (2011). Advances in on-line drinking water quality monitoring and early warning systems. Water Research, 45(2): 741–747 https://doi.org/10.1016/j.watres.2010.08.049
37	X Ta , Y Wei . (2018). Research on a dissolved oxygen prediction method for recirculating aquaculture systems based on a convolution neural network. Computers and Electronics in Agriculture, 145: 302–310 https://doi.org/10.1016/j.compag.2017.12.037
38	A Tealab . (2018). Time series forecasting using artificial neural networks methodologies: a systematic review. Future Computing and Informatics Journal, 3(2): 334–340 https://doi.org/10.1016/j.fcij.2018.10.003
39	J Tomperi , E Koivuranta , K Leiviskä . (2017). Predicting the effluent quality of an industrial wastewater treatment plant by way of optical monitoring. Journal of Water Process Engineering, 16: 283–289 https://doi.org/10.1016/j.jwpe.2017.02.004
40	K Wang , X Wen , D Hou , D Tu , N Zhu , P Huang , G Zhang , H Zhang . (2018). Application of least-squares support vector machines for quantitative evaluation of known contaminant in water distribution system using online water quality parameters. Sensors, 18(4): 938–956 https://doi.org/10.3390/s18040938
41	Wang Y, Zhou J, Chen K, Wang Y, Liu L (2017). Water quality prediction method based on LSTM neural network. In: International Conference on Intelligent Systems and Knowledge Engineering 2017, Nanjing. Beijing: IEEE, 1–5
42	Z Wang , Q Wang , T Wu . (2023). A novel hybrid model for water quality prediction based on VMD and IGOA optimized for LSTM. Frontiers of Environmental Science & Engineering, 17(7): 88 https://doi.org/10.1007/s11783-023-1688-y
43	G Wu , J Hong , D Li , Z Wu . (2019). Efficiency assessment of pollutants discharged in urban wastewater treatment: evidence from 68 key cities in China. Journal of Cleaner Production, 233: 1437–1450 https://doi.org/10.1016/j.jclepro.2019.06.012
44	Y Yang , Q Xiong , C Wu , Q Zou , Y Yu , H Yi , M Gao . (2021). A study on water quality prediction by a hybrid CNN-LSTM model with attention mechanism. Environmental Science and Pollution Research International, 28(39): 55129–55139 https://doi.org/10.1007/s11356-021-14687-8
45	R F Yu , C H Lin , H W Chen , W P Cheng , M C J C E J Kao . (2013). Possible control approaches of the Electro-Fenton process for textile wastewater treatment using on-line monitoring of DO and ORP. Chemical Engineering Journal, 218: 341–349 https://doi.org/10.1016/j.cej.2012.12.061
46	H Zare Abyaneh . (2014). Evaluation of multivariate linear regression and artificial neural networks in prediction of water quality parameters. Journal of Environmental Health Science & Engineering, 12(1): 40–48 https://doi.org/10.1186/2052-336X-12-40
47	X Zhang , D Li . (2023). Multi-input multi-output temporal convolutional network for predicting the long-term water quality of ocean ranches. Environmental Science and Pollution Research, 30(3): 7914–7929 https://doi.org/10.1007/s11356-022-22588-7
48	S Zhu , H Han , M Guo , J Qiao . (2017). A data-derived soft-sensor method for monitoring effluent total phosphorus. Chinese Journal of Chemical Engineering, 25(12): 1791–1797 https://doi.org/10.1016/j.cjche.2017.06.008
49	K R Zodrow , Q Li , R M Buono , W Chen , G Daigger , L Duenas-Osorio , M Elimelech , X Huang , G Jiang , J H Kim . et al.. (2017). Advanced materials, technologies, and complex systems analyses: emerging opportunities to enhance urban water security. Environmental Science & Technology, 51(18): 10274–10281 https://doi.org/10.1021/acs.est.7b01679

[1]	Xuan Wang, Yan Dong, Jing Yang, Zhipeng Liu, Jinsuo Lu. A benchmark-based method for evaluating hyperparameter optimization techniques of neural networks for surface water quality prediction[J]. Front. Environ. Sci. Eng., 2024, 18(5): 54-.
[2]	Yanpeng Huang, Chao Wang, Yuanhao Wang, Guangfeng Lyu, Sijie Lin, Weijiang Liu, Haobo Niu, Qing Hu. Application of machine learning models in groundwater quality assessment and prediction: progress and challenges[J]. Front. Environ. Sci. Eng., 2024, 18(3): 29-.
[3]	Zhaocai Wang, Qingyu Wang, Tunhua Wu. A novel hybrid model for water quality prediction based on VMD and IGOA optimized for LSTM[J]. Front. Environ. Sci. Eng., 2023, 17(7): 88-.
[4]	Junlang Li, Zhenguo Chen, Xiaoyong Li, Xiaohui Yi, Yingzhong Zhao, Xinzhong He, Zehua Huang, Mohamed A. Hassaan, Ahmed El Nemr, Mingzhi Huang. Water quality soft-sensor prediction in anaerobic process using deep neural network optimized by Tree-structured Parzen Estimator[J]. Front. Environ. Sci. Eng., 2023, 17(6): 67-.

Viewed

Full text

Abstract

Cited

Shared

Discussed