Chemical oxygen demand (COD) is an important index to measure the degree of water pollution. In this paper, near-infrared technology is used to obtain 148 wastewater spectra to predict the COD value in wastewater. First, the partial least squares regression (PLS) model was used as the basic model. Monte Carlo cross-validation (MCCV) was used to select 25 samples out of 148 samples that did not conform to conventional statistics. Then, the interval partial least squares (iPLS) regression modeling was carried out on 123 samples, and the spectral bands were divided into 40 subintervals. The optimal subintervals are 20 and 26, and the optimal correlation coefficient of the test set (<i>R</i><i><sub>T</sub></i>) is 0.58. Further, the waveband is divided into five intervals: 17, 19, 20, 22 and 26. When the number of joint intervals under each interval is three, the optimal <i>R</i><i><sub>T</sub></i> is 0.71. When the number of joint subintervals is four, the optimal <i>R</i><i><sub>T</sub></i> is 0.79. Finally, convolutional neural network (CNN) was used for quantitative prediction, and <i>R</i><i><sub>T</sub></i> was 0.9. The results show that CNN can automatically screen the features inside the data, and the quantitative prediction effect is better than that of iPLS and synergy interval partial least squares model (SiPLS) with joint subinterval three and four, indicating that CNN can be used for quantitative analysis of water pollution degree.
KeywordsWastewaterNear-Infrared SpectroscopyChemistry Oxygen DemandPartial Least SquaresConvolutional Neural NetworkStatistical Optimization
Roggo, Y., Chalus, P., Maurer, L., Lema-Martinez C., Edmond, A. and Jent, N. (2007) A Review of Near Infrared Spectroscopy and Chemometrics in Pharmaceutical Technologies. Journal of Pharmaceutical and Biomedical Analysis , 44, 683-700. https://doi.org/10.1016/j.jpba.2007.03.023
Chadha, R. and Haneef, J. (2015) Near-Infrared Spectroscopy: Effective Tool for Screening of Polymorphs in Pharmaceuticals. Applied Spectroscopy Reviews , 50, 565-83. https://doi.org/10.1080/05704928.2015.1044663
Li, X.Y., Chen, H.Z., Xu, L.L., Mo, Q.S., Du, X.R. and Tang, G.Q. (2024) Multi-Model Fusion Stacking Ensemble Learning Method for the Prediction of Berberine by FT-NIR Spectroscopy. Infrared Physics & Technology , 137, Article 105169. https://doi.org/10.1016/j.infrared.2024.105169
Cui, P.D., Wang, Q.Y., Li, Z., Wu, C.L., Li, G., Zhao, J., et al. (2022) A Feasibility Study on Improving the Non-Invasive Detection Accuracy of Bottled Shuanghuanglian Oral Liquid Using Near Infrared Spectroscopy. Spectrochimica Acta Part A : Mol e cular and Biomolecular Spectroscopy , 274, Article 121120. https://doi.org/10.1016/j.saa.2022.121120
Radney, J.G. and Zangmeister, C.D. (2015) Measurement of Gas and Aerosol Phase Absorption Spectra across the Visible and Near-IR Using Supercontinuum Photoacoustic Spectroscopy. Analytical Chemistry , 87, 7356-7363. https://doi.org/10.1021/acs.analchem.5b01541
Qu, Y.X. and Cai, Z.Y. (2018) Identification of Singular Samples in Near Infrared Spectrum of Starch Water Content Prediction by Using Monte Carlo Cross Validation Combined with T Test. IOP Conference Series : Earth and Environmental Science , 186, Article 012035. https://doi.org/10.1088/1755-1315/186/3/012035
Ye, D.D., Sun, L.J., Zou, B., Zhang, Q., Tan, W.Y. and Che, W.K. (2018) Non-Destructive Prediction of Protein Content in Wheat Using NIRS. Spectrochi mica Acta Part A : Molecular and Biomolecular Spectroscopy , 189, 463-472. https://doi.org/10.1016/j.saa.2017.08.055
Ling, M.X., Bian, X.H., Wang, S.S., Huang, T., Liu, P., Wang, S.Y., et al. (2022) A Piecewise Mirror Extension Local Mean Decomposition Method for Denoising of Near-Infrared Spectra with Uneven Noise. Chemometrics and Intelligent Laborat o ry Systems , 230, Article 104655. https://doi.org/10.1016/j.chemolab.2022.104655
Liu, C., Yang, S.X., Li, X.F., Xu, L.J. and Deng, L. (2020) Noise Level Penalizing Robust Gaussian Process Regression for NIR Spectroscopy Quantitative Analysis. Chemometrics and Intelligent Laboratory Systems , 201, Article 104014. https://doi.org/10.1016/j.chemolab.2020.104014
Zhao, Z.N., Liu, Y.H., Yang, S., Li, Y.R., Zhang, Y.S. and Yan, H. (2023) Fast Detection of the Tenderness of Mulberry Leaves by a Portable Near-Infrared Spectrometer with Variable Selection. Infrared Physics & Technology , 133, Article 104818. https://doi.org/10.1016/j.infrared.2023.104818
Nawar, S., Mohamed, E.S., Sayed S.E.-E., Mohamed, W.S., Rebouh, N.Y. and Hammam, A.A. (2023) Estimation of Key Potentially Toxic Elements in Arid Agricultural Soils Using Vis-NIR Spectroscopy with Variable Selection and PLSR Algorithms. Frontiers in Environmental Science , 11, Article 1222871. https://doi.org/10.3389/fenvs.2023.1222871
Chen, M.J., Yin, H.L., Liu, Y., Wang, R.R., Jiang, L.W. and Li, P. (2022) Non-Destructive Prediction of the Hotness of Fresh Pepper with a Single Scan Using Portable Near Infrared Spectroscopy and a Variable Selection Strategy. Analyt i cal Methods , 14, 114-124. https://doi.org/10.1039/D1AY01634B
Zhang, L.N., Tian, H., Wang, L.R., Li, H. and Pu, Z.Y. (2023) Selection and Validation of the Best Detection Location for Hemoglobin Determination by Spatially Resolved Diffuse Transmission Spectroscopy. Infrared Physics & Technology , 133, Article 104839. https://doi.org/10.1016/j.infrared.2023.104839
Marañón, M., Fernández-Novales, J., Tardaguila, J., Gutiérrez, S. and Diago, M.P. (2023) NIR Attribute Selection for the Development of Vineyard Water Status Predictive Models. Biosystems Engineering , 229, 167-178. https://doi.org/10.1016/j.biosystemseng.2023.04.001
Miao, X.X., Miao, Y., Liu, Y., Tao, S.H., Zheng, H.B., Wang, J.M., et al. (2023) Measurement of Nitrogen Content in Rice Plant Using Near Infrared Spectroscopy Combined with Different PLS Algorithms. Spectrochimica Acta Part A : Molecular and Biomolecular Spectroscopy , 284, Article 121733. https://doi.org/10.1016/j.saa.2022.121733
Wang, J.B., Lu, Z.X., Wang, G.M., Hussain, G., Zhao, S.H., Zhang, H.J., et al. (2023) Research on Fault Diagnosis of HMCVT Shift Hydraulic System Based on Optimized BPNN and CNN. Agriculture , 13, Article 461. https://doi.org/10.3390/agriculture13020461
Harini Chandana, S. and Senthil Kumar, R. (2022) A Deep Learning Model to Identify Twins and Look Alike Identification Using Convolutional Neural Network (CNN) and to Compare the Accuracy with SVM Approach. ECS Transactions , 107, Article 14109. https://doi.org/10.1149/10701.14109ecst
Kotir, J.H., Smith C., Brown G., Marshall, N. and Johnstone, R. (2016) A System Dynamics Simulation Model for Sustainable Water Resources Management and Agricultural Development in the Volta River Basin, Ghana. Science of the Total E n vironment , 573, 444-457. https://doi.org/10.1016/j.scitotenv.2016.08.081
Wang, X.D., Ratnaweera, H., Holm, J.A. and Olsbu, V. (2017) Statistical Monitoring and Dynamic Simulation of a Wastewater Treatment Plant: A Combined Approach to Achieve Model Predictive Control. Journal of Environmental Management , 193, 1-7. https://doi.org/10.1016/j.jenvman.2017.01.079
Zhang, L.H., Chao, B. and Zhang, X. (2020) Modeling and Optimization of Microbial Lipid Fermentation from Cellulosic Ethanol Wastewater by Rhodotorula glut i nis Based on the Support Vector Machine. Bioresource Technology , 301, Article 122781. https://doi.org/10.1016/j.biortech.2020.122781
Lee, C.Y., Gallagher, P. and Tu, Z.W. (2018) Generalizing Pooling Functions in CNNs: Mixed, Gated, and Tree. IEEE Transactions on Pattern Analysis and M a chine Intelligence , 40, 863-875. https://doi.org/10.1109/TPAMI.2017.2703082