Optimization of indirect wastewater characterization: a hybrid approach based on decision trees, genetic algorithms and spectroscopy

  1. Carreres-Prieto, Daniel 2
  2. García, Juan T. 1
  3. Carrillo, José M. 1
  4. Vigueras-Rodríguez, Antonio 1
  1. 1 Department of Mining and Civil Engineering, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
  2. 2 Center for Technological Innovation in Construction and Civil Engineering (CITEEC), Universidade da Coruña, 15008, A Coruña, Spain
Revista:
Environmental Science: Water Research & Technology

ISSN: 2053-1400 2053-1419

Año de publicación: 2023

Tipo: Artículo

DOI: 10.1039/D3EW00410D GOOGLE SCHOLAR lock_openAcceso abierto editor

Otras publicaciones en: Environmental Science: Water Research & Technology

Objetivos de desarrollo sostenible

Resumen

The spectral response of wastewater samples allows, through the use of correlation models, to estimate the pollutant load of the samples in a simple, fast and economical way. However, the accuracy of these models can be affected by alterations in the spectral by external agents such as vibrations or temperature changes. In these cases, approximating the spectral response to trend lines can sometimes provide better estimates, while in other, it is better to work with the original spectral response. This research work proposes a methodology to accurately estimate the pollutant load of wastewater using a hybrid characterization model based on decision trees, which allows, in all cases, to obtain the best possible characterization. This model, based on the analysis of the spectral response, determines which genetic algorithm-based estimation model to make use of: the original spectral response or to the approximation of this to global or individual trend lines for each colour group, to estimate the following parameters: chemical oxygen demand (COD), biochemical oxygen demand at 5 days (BOD5), total suspended solids (TSS), total nitrogen (TN) and total phosphorus (TP) in raw and treated wastewater respectively. The study was conducted on 650 wastewater samples from 43 WWTPs. The results show that the hybrid characterization model provides the best possible fit, achieving an improvement up to 5% in raw wastewater samples, and up to 26.32% in treated wastewater with respect to the use of models that employ point values of the original spectral response, being much more significant in the case of TN.

Información de financiación

Financiadores

Referencias bibliográficas

  • Altmann, (2016), Water Res., 94, pp. 240, 10.1016/j.watres.2016.03.001
  • Mesquita, (2017), Rev. Environ. Sci. Biotechnol., 16, pp. 395, 10.1007/s11157-017-9439-9
  • Korshin, (2018), Curr. Opin. Environ. Sci. Health, 2, pp. 12, 10.1016/j.coesh.2017.11.003
  • Brito, (2014), Urban Water J., 11, pp. 261, 10.1080/1573062X.2013.783087
  • Feng, (2018), Urban Water J., 15, pp. 381, 10.1080/1573062x.2018.1483525
  • Wasswa, (2019), Environ. Sci.: Water Res. Technol., 5, pp. 370
  • O.Korostynska , A.Mason and A. I.Al-Shamma'a , Monitoring pollutants in wastewater: Traditional lab based versus modern real-time approaches, in Smart Sensors, Measurement and Instrumentation , Springer Berlin Heidelberg , Berlin, Heidelberg , 2013 , pp. 1–24
  • Lepot, (2016), Water Res., 101, pp. 519, 10.1016/j.watres.2016.05.070
  • Song, (2021), Water Res., 190, pp. 116733, 10.1016/j.watres.2020.116733
  • Qin, (2012), Water Res., 46, pp. 1133, 10.1016/j.watres.2011.12.005
  • Langergraber, (2003), Water Sci. Technol., 47, pp. 63, 10.2166/wst.2003.0086
  • Li, (2021), J. Environ. Chem. Eng., 9, pp. 1, 10.1016/j.jece.2021.105517
  • Xue, (2022), Chem. Eng., 10, pp. 1, 10.1016/j.jece.2022.107538
  • Komatsu, (2020), Water Res., 171, pp. 115459, 10.1016/j.watres.2019.115459
  • Jiang, (2022), ACS ES&T Water, 2, pp. 165, 10.1021/acsestwater.1c00305
  • Chen, (2014), Talanta, 120, pp. 325, 10.1016/j.talanta.2013.12.026
  • UV-visible spectrophotometry of water and wastewater , ed. O. Thomas and C. Burgess , Elsevier Science , London, England , 2nd edn, 2017
  • Carré, (2017), Water Sci. Technol., 76, pp. 633, 10.2166/wst.2017.096
  • Ferree, (2001), Water Res., 35, pp. 327, 10.1016/s0043-1354(00)00222-0
  • Suzuki, (1987), Analyst, 112, pp. 1077, 10.1039/an9871201077
  • Niazi, (2012), J. Chemom., 26, pp. 345, 10.1002/cem.2426
  • Carreres-Prieto, (2022), Chemosphere, 293, pp. 133610, 10.1016/j.chemosphere.2022.133610
  • Sigmund, (2020), Environ. Sci. Technol., 54, pp. 4583, 10.1021/acs.est.9b06287
  • Chang, (2001), Civ. Eng. Environ. Syst., 18, pp. 1, 10.1080/02630250108970290
  • M.Otto , Chemometrics: Statistics and Computer Application in Analytical Chemistry , Wiley-VCH Verlag , Weinheim, Germany , 3rd edn, 2016
  • Güller, (2019), Commun. Stat. Case Stud. Data Anal. Appl., 5, pp. 200, 10.1080/23737484.2019.1604192
  • Deepnarain, (2019), Process Saf. Environ. Prot., 126, pp. 25, 10.1016/j.psep.2019.02.023
  • Byliński, (2019), Sustainability, 11, pp. 4407, 10.3390/su11164407
  • Dalmau, (2013), Chem. Eng. J., 217, pp. 174, 10.1016/j.cej.2012.11.060
  • Carreres-Prieto, (2022), Ingenieria del Agua, 26, pp. 261, 10.4995/ia.2022.18073
  • Carreres-Prieto, (2022), Water Sci. Technol., 85, pp. 2565, 10.2166/wst.2022.138
  • Carreres-Prieto, (2023), J. Environ. Chem. Eng., 11, pp. 110219, 10.1016/j.jece.2023.110219
  • Carreres-Prieto, (2023), Sci. Total Environ., 871, pp. 162082, 10.1016/j.scitotenv.2023.162082
  • Baumgartner, (2020), Anal. Chem., 92, pp. 4736, 10.1021/acs.analchem.9b04043
  • Carrasco-Correa, (2021), TrAC, Trends Anal. Chem., 136, pp. 116177, 10.1016/j.trac.2020.116177
  • Han, (2021), ACS ES&T Water, 1, pp. 2548, 10.1021/acsestwater.1c00351
  • Carreres-Prieto, (2019), Sensors, 19, pp. 2951, 10.3390/s19132951
  • M.Affenzeller and S.Wagner , Offspring selection: A new self-adaptive selection scheme for genetic algorithms, in Adaptive and Natural Computing Algorithms , Springer-Verlag , Vienna , 2005 , pp. 218–221
  • Cho, (2004), J. Environ. Manage., 73, pp. 229, 10.1016/j.jenvman.2004.07.004
  • Huang, (2015), Appl. Soft Comput., 27, pp. 1, 10.1016/j.asoc.2014.10.034
  • Holenda, (2007), Optim. Control Appl. Methods, 28, pp. 191, 10.1002/oca.796
  • Ziweritin, (2022), Open Access Library Journal, 9, pp. 1
  • Ahmad, (2017), Energy Build., 147, pp. 77, 10.1016/j.enbuild.2017.04.038
  • Tsai, (2012), Environ. Eng. Sci., 29, pp. 108, 10.1089/ees.2011.0210
  • F.Ranzato and M.Zanella , Genetic adversarial training of decision trees, in Proceedings of the Genetic and Evolutionary Computation Conference , 2021 , pp. 358–367
  • Pedregosa, (2011), J Mach Learn Res, 12, pp. 2825
  • Gupta, (1999), J. Hydrol. Eng., 4, pp. 135, 10.1061/(asce)1084-0699(1999)4:2(135)
  • Moriasi, (2007), Trans. ASABE, 50, pp. 885, 10.13031/2013.23153
  • Melendez-Pastor, (2013), Water, 5, pp. 2026, 10.3390/w5042026
  • Huang, (2023), J. Cleaner Prod., 385, pp. 135681, 10.1016/j.jclepro.2022.135681
  • Sousa, (2007), Anal. Chim. Acta, 588, pp. 231, 10.1016/j.aca.2007.02.022
  • Li, (2020), RSC Adv., 10, pp. 20691, 10.1039/c9ra10732k
  • Melendez-Pastor, (2013), Water, 5, pp. 2026, 10.3390/w5042026
  • Marie-Noëlle, (2005), IFAC Proceedings Volumes, 38, pp. 49, 10.3182/20050703-6-CZ-1902.02212
  • T.Inagaki , Y.Shinoda , M.Miyazawa , H.Takamura , S.Tsuchikawa and M.Affenzeller , et al. , Offspring selection: A new self-adaptive selection scheme for genetic algorithms, in Adaptive and Natural Computing Algorithms , Springer , Vienna , 2005 , pp. 218–221
  • Carré, (2017), Water Sci. Technol., 76, pp. 633, 10.2166/wst.2017.096