Water quality prediction of copper-molybdenum mining-beneficiation wastewater based on the PSO-SVR model

doi:10.1007/s11783-023-1698-9

Front. Environ. Sci. Eng.

2023, Vol. 17

Issue (8) : 98 https://doi.org/10.1007/s11783-023-1698-9

RESEARCH ARTICLE

Water quality prediction of copper-molybdenum mining-beneficiation wastewater based on the PSO-SVR model

Xiaohua Fu¹, Qingxing Zheng^1,², Guomin Jiang³, Kallol Roy⁴, Lei Huang⁵, Chang Liu², Kun Li^6,⁷, Honglei Chen¹, Xinyu Song^1,², Jianyu Chen², Zhenxing Wang²(

)

¹. Ecological Environment Management and Assessment Center, Central South University of Forestry and Technology, Changsha 410004, China
². State Environmental Protection Key Laboratory of Water Environmental Simulation and Pollution Control, South China Institute of Environmental Sciences, Ministry of Ecology and Environment, Guangzhou 510655, China
³. Chinese Non-Ferrous Industrial Engineering Center of Pollution Control Technology & Equipment, Science Environment Protection Co., Ltd., Changsha 410036, China
⁴. Institute of Computer Science, University of Tartu, Tartu 51009, Estonia
⁵. School of Environmental Science and Engineering, Guangzhou University, Guangzhou 510006, China
⁶. A.B Freeman School of Business, Tulane University, New Orleans, LA 70118, USA
⁷. Guangzhou Huacai Environmental Protection Technology Co., Ltd., Guangzhou 511480, China

Download: PDF(4049 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

● Data acquisition and pre-processing for wastewater treatment were summarized.

● A PSO-SVR model for predicting COD_eff in wastewater was proposed.

● The COD_eff prediction performances of the three models in the paper were compared.

● The COD_eff prediction effects of different models in other studies were discussed.

The mining-beneficiation wastewater treatment is highly complex and nonlinear. Various factors like influent quality, flow rate, pH and chemical dose, tend to restrict the effluent effectiveness of mining-beneficiation wastewater treatment. Chemical oxygen demand (COD) is a crucial indicator to measure the quality of mining-beneficiation wastewater. Predicting COD concentration accurately of mining-beneficiation wastewater after treatment is essential for achieving stable and compliant discharge. This reduces environmental risk and significantly improves the discharge quality of wastewater. This paper presents a novel AI algorithm PSO-SVR, to predict water quality. Hyperparameter optimization of our proposed model PSO-SVR, uses particle swarm optimization to improve support vector regression for COD prediction. The generalization capacity tested on out-of-distribution (OOD) data for our PSO-SVR model is strong, with the following performance metrics of root means square error (RMSE) is 1.51, mean absolute error (MAE) is 1.26, and the coefficient of determination (R²) is 0.85. We compare the performance of PSO-SVR model with back propagation neural network (BPNN) and radial basis function neural network (RBFNN) and shows it edges over in terms of the performance metrics of RMSE, MAE and R², and is the best model for COD prediction of mining-beneficiation wastewater. This is because of the less overfitting tendency of PSO-SVR compared with neural network architectures. Our proposed PSO-SVR model is optimum for the prediction of COD in copper-molybdenum mining-beneficiation wastewater treatment. In addition, PSO-SVR can be used to predict COD on a wide variety of wastewater through the process of transfer learning.

Keywords Chemical oxygen demand Mining-beneficiation wastewater treatment Particle swarm optimization Support vector regression Artificial neural network

Corresponding Author(s): Zhenxing Wang

Issue Date: 13 March 2023

Cite this article:

Xiaohua Fu,Qingxing Zheng,Guomin Jiang, et al. Water quality prediction of copper-molybdenum mining-beneficiation wastewater based on the PSO-SVR model[J]. Front. Environ. Sci. Eng., 2023, 17(8): 98.

URL:

https://academic.hep.com.cn/fese/EN/10.1007/s11783-023-1698-9
https://academic.hep.com.cn/fese/EN/Y2023/V17/I8/98

Fig.1 Process flow of copper-molybdenum mining-beneficiation wastewater treatment.

Tab.1 Data analysis of key water quality indicator variables in mining-beneficiation wastewater treatment

Fig.2 Flow of SVR prediction model based on PSO algorithm.

Fig.3 Prediction results of COD_eff based on PSO-SVR model. (a) PSO-SVR model fitting simulation results. (b) PSO-SVR model prediction error distribution. (c) Scatter plot between measured and predicted values of COD_eff in PSO-SVR model.

Tab.2 Comparison of prediction accuracy of different models

Fig.4 Prediction results of COD_eff of each model. (a) The simulation results of each model fitting. (b) Prediction error distribution of each model. (c) Scatter plot between measured and predicted values of COD_eff in each model.

Tab.3 Summary of different studies on COD prediction of wastewater treatment effluent

Tab.4 Optimal parameter settings and prediction accuracy comparison of PSO-SVR model for each augmented data

Fig.5 Prediction results of COD_eff from PSO-SVR model with different expansion multiple data. (a) Prediction effect of PSO-SVR model after data expansion by 2 times. (b) Prediction error distribution of PSO-SVR model after data augmentation by 2 times. (c) Prediction effect of PSO-SVR model after data expansion by 4 times. (d) Prediction error distribution of PSO-SVR model after data augmentation by 4 times. (e) Prediction effect of PSO-SVR model after data expansion by 6 times. (f) Prediction error distribution of PSO-SVR model after data augmentation by 6 times. (g) Proportion of absolute errors in the prediction of data models with different expansion multiples in each numerical interval.

1	H Asami , M Golabi , M Albaji . (2021). Simulation of the biochemical and chemical oxygen demand and total suspended solids in wastewater treatment plants: data-mining approach. Journal of Cleaner Production, 296: 126533 https://doi.org/10.1016/j.jclepro.2021.126533
2	F Bagherzadeh , M J Mehrani , M Basirifard , J Roostaei . (2021). Comparative study on total nitrogen prediction in wastewater treatment plant and effect of various feature selection methods on machine learning algorithms performance. Journal of Water Process Engineering, 41: 102033 https://doi.org/10.1016/j.jwpe.2021.102033
3	L A Belanche , J J Valdés , J Comas , I R Roda , M Poch . (1999). Towards a model of input–output behaviour of wastewater treatment plants using soft computing techniques. Environmental Modelling & Software, 14(5): 409–419 https://doi.org/10.1016/S1364-8152(98)00102-9
4	K Y Chen . (2007). Forecasting systems reliability based on support vector regression with genetic algorithms. Reliability Engineering & System Safety, 92(4): 423–432 https://doi.org/10.1016/j.ress.2005.12.014
5	N Chitsazan , A A Nadiri , F T C Tsai . (2015). Prediction and structural uncertainty analyses of artificial neural networks using hierarchical Bayesian model averaging. Journal of Hydrology (Amsterdam), 528: 52–62 https://doi.org/10.1016/j.jhydrol.2015.06.007
6	T Deng , K W Chau , H F Duan . (2021). Machine learning based marine water quality prediction for coastal hydro-environment management. Journal of Environmental Management, 284: 112051 https://doi.org/10.1016/j.jenvman.2021.112051
7	M El-Rawy , M K Abd-Ellah , H Fathi , A K A Ahmed . (2021). Forecasting effluent and performance of wastewater treatment plant using different machine learning techniques. Journal of Water Process Engineering, 44: 102380 https://doi.org/10.1016/j.jwpe.2021.102380
8	S M Hosseini , N Mahjouri . (2016). Integrating support vector regression and a geomorphologic artificial neural network for daily rainfall-runoff modeling. Applied Soft Computing, 38: 329–345 https://doi.org/10.1016/j.asoc.2015.09.049
9	D Karaboga , B Basturk . (2007). A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm. Journal of Global Optimization, 39(3): 459–471 https://doi.org/10.1007/s10898-007-9149-x
10	H Liu , Y Zhang , H Zhang . (2020). Prediction of effluent quality in papermaking wastewater treatment processes using dynamic kernel-based extreme learning machine. Process Biochemistry (Barking, London, England), 97: 72–79 https://doi.org/10.1016/j.procbio.2020.06.020
11	X Liu , C Gao , P Li . (2012). A comparative analysis of support vector machines and extreme learning machines. Neural Networks, 33: 58–66 https://doi.org/10.1016/j.neunet.2012.04.002
12	Y Man , Y Hu , J Ren . (2019). Forecasting COD load in municipal sewage based on ARMA and VAR algorithms. Resources, Conservation and Recycling, 144: 56–64 https://doi.org/10.1016/j.resconrec.2019.01.030
13	X Meng , J Wu , J Kang , J Gao , R Liu , Y Gao , R Wang , R Fan , S A Khoso , W Sun , Y Hu . (2018). Comparison of the reduction of chemical oxygen demand in wastewater from mineral processing using the coagulation–flocculation, adsorption and Fenton processes. Minerals Engineering, 128: 275–283 https://doi.org/10.1016/j.mineng.2018.09.009
14	X Meng , Y Zhang , J Qiao . (2021). An adaptive task-oriented RBF network for key water quality parameters prediction in wastewater treatment process. Neural Computing & Applications, 33(17): 11401–11414 https://doi.org/10.1007/s00521-020-05659-z
15	A A Nadiri , S Shokri , F T C Tsai , A Asghari Moghaddam . (2018). Prediction of effluent quality parameters of a wastewater treatment plant using a supervised committee fuzzy logic model. Journal of Cleaner Production, 180: 539–549 https://doi.org/10.1016/j.jclepro.2018.01.139
16	A Najah Ahmed , F Binti Othman , H Abdulmohsin Afan , R Khaleel Ibrahim , C Ming Fai , M Shabbir Hossain , M Ehteram , A Elshafie . (2019). Machine learning methods for better water quality prediction. Journal of Hydrology (Amsterdam), 578: 124084 https://doi.org/10.1016/j.jhydrol.2019.124084
17	G Niu , X Yi , C Chen , X Li , D Han , B Yan , M Huang , G Ying . (2020). A novel effluent quality predicting model based on genetic-deep belief network algorithm for cleaner production in a full-scale paper-making wastewater treatment. Journal of Cleaner Production, 265: 121787 https://doi.org/10.1016/j.jclepro.2020.121787
18	A Nouraki , M Alavi , M Golabi , M Albaji . (2021). Prediction of water quality parameters using machine learning models: a case study of the Karun River, Iran. Environmental Science and Pollution Research International, 28(40): 57060–57072 https://doi.org/10.1007/s11356-021-14560-8
19	V Nourani , P Asghari , E Sharghi . (2021). Artificial intelligence based ensemble modeling of wastewater treatment plant using jittered data. Journal of Cleaner Production, 291: 125772 https://doi.org/10.1016/j.jclepro.2020.125772
20	S Sadri Moghaddam , H Mesghali . (2023). A new hybrid ensemble approach for the prediction of effluent total nitrogen from a full-scale wastewater treatment plant using a combined trickling filter-activated sludge system. Environmental Science and Pollution Research International, 30(1): 1622–1639 https://doi.org/10.1007/s11356-022-21864-w
21	M I Shah , M F Javed , A Alqahtani , A Aldrees . (2021). Environmental assessment based surface water quality prediction using hyper-parameter optimized machine learning models based on consistent big data. Process Safety and Environmental Protection, 151: 324–340 https://doi.org/10.1016/j.psep.2021.05.026
22	A Sharafati , S B H S Asadollah , M Hosseinzadeh . (2020). The potential of new ensemble machine learning models for effluent quality parameters prediction and related uncertainty. Process Safety and Environmental Protection, 140: 68–78 https://doi.org/10.1016/j.psep.2020.04.045
23	S Shi , G Xu . (2018). Novel performance prediction model of a biofilm system treating domestic wastewater based on stacked denoising auto-encoders deep learning network. Chemical Engineering Journal, 347: 280–290 https://doi.org/10.1016/j.cej.2018.04.087
24	A J Smola , B Schölkopf , K R Müller . (1998). The connection between regularization operators and support vector kernels. Neural Networks, 11(4): 637–649 https://doi.org/10.1016/S0893-6080(98)00032-X
25	A Solgi , A Pourhaghi , R Bahmani , H Zarei . (2017). Improving SVR and ANFIS performance using wavelet transform and PCA algorithm for modeling and predicting biochemical oxygen demand (BOD). Ecohydrology & Hydrobiology, 17(2): 164–175 https://doi.org/10.1016/j.ecohyd.2017.02.002
26	H Su , H Yi , W Gu , Q Wang , B Liu , B Zhang . (2022a). Cost of raising discharge standards: a plant-by-plant assessment from wastewater sector in China. Journal of Environmental Management, 308: 114642 https://doi.org/10.1016/j.jenvman.2022.114642
27	X Su , X He , G Zhang , Y Chen , K Li . (2022b). Research on SVR water quality prediction model based on improved sparrow search algorithm. Computational Intelligence and Neuroscience, 2022: 7327072 https://doi.org/10.1155/2022/7327072
28	V Vapnik (1999). The Nature of Statistical Learning Theory. Berlin: Springer Science & Business Media
29	J A Vrugt , B A Robinson , J M Hyman . (2009). Self-adaptive multimethod search for global optimization in real-parameter spaces. IEEE Transactions on Evolutionary Computation, 13(2): 243–259 https://doi.org/10.1109/TEVC.2008.924428
30	X Wan , X Li , X Wang , X Yi , Y Zhao , X He , R Wu , M Huang . (2022). Water quality prediction model using Gaussian process regression based on deep learning for carbon neutrality in papermaking wastewater treatment system. Environmental Research, 211: 112942 https://doi.org/10.1016/j.envres.2022.112942
31	D Wang , D Tan , L Liu . (2018). Particle swarm optimization algorithm: an overview. Soft Computing, 22(2): 387–408 https://doi.org/10.1007/s00500-016-2474-6
32	R Wang , Y Yu , Y Chen , Z Pan , X Li , Z Tan , J Zhang . (2022). Model construction and application for effluent prediction in wastewater treatment plant: data processing method optimization and process parameters integration. Journal of Environmental Management, 302: 114020 https://doi.org/10.1016/j.jenvman.2021.114020
33	Z Ye , J Yang , N Zhong , X Tu , J Jia , J Wang . (2020). Tackling environmental challenges in pollution controls using artificial intelligence: a review. Science of the Total Environment, 699: 134279 https://doi.org/10.1016/j.scitotenv.2019.134279
34	H Zhang , C Yang , X Shi , H Liu . (2021). Effluent quality prediction in papermaking wastewater treatment processes using dynamic Bayesian networks. Journal of Cleaner Production, 282: 125396 https://doi.org/10.1016/j.jclepro.2020.125396

[1]

FSE-22137-OF-FXH_suppl_1

Download

[1]	Xiaoxiao Yin, Junyu Tao, Guanyi Chen, Xilei Yao, Pengpeng Luan, Zhanjun Cheng, Ning Li, Zhongyue Zhou, Beibei Yan. Prediction of high-density polyethylene pyrolysis using kinetic parameters based on thermogravimetric and artificial neural networks[J]. Front. Environ. Sci. Eng., 2023, 17(1): 6-.
[2]	Kangying Guo, Baoyu Gao, Jie Wang, Jingwen Pan, Qinyan Yue, Xing Xu. Flocculation behaviors of a novel papermaking sludge-based flocculant in practical printing and dyeing wastewater treatment[J]. Front. Environ. Sci. Eng., 2021, 15(5): 103-.
[3]	Ziming Zhao, Wenjun Sun, Madhumita B. Ray, Ajay K Ray, Tianyin Huang, Jiabin Chen. Optimization and modeling of coagulation-flocculation to remove algae and organic matter from surface water by response surface methodology[J]. Front. Environ. Sci. Eng., 2019, 13(5): 75-.
[4]	Xuewei QI, Ke LI, Walter D. POTTER. Estimation of distribution algorithm enhanced particle swarm optimization for water distribution network optimization[J]. Front. Environ. Sci. Eng., 2016, 10(2): 341-351.
[5]	Liang GUO, Ying ZHAO, Peng WANG. Determination of the principal factors of river water quality through cluster analysis method and its prediction[J]. Front Envir Sci Eng, 2012, 6(2): 238-245.
[6]	WEI Qun, HU Zhiquan, LI Genbao, XIAO Bo, SUN Hao, TAO Meiping. Removing nitrogen and phosphorus from simulated wastewater using algal biofilm technique[J]. Front.Environ.Sci.Eng., 2008, 2(4): 446-451.

Viewed

Full text

Abstract

Cited

Shared

Discussed