Advertisement

Environmental Science and Pollution Research

, Volume 25, Issue 21, pp 21149–21163 | Cite as

Effluent composition prediction of a two-stage anaerobic digestion process: machine learning and stoichiometry techniques

  • Luz Alejo
  • John Atkinson
  • Víctor Guzmán-Fierro
  • Marlene Roeckel
Research Article
  • 512 Downloads

Abstract

Computational self-adapting methods (Support Vector Machines, SVM) are compared with an analytical method in effluent composition prediction of a two-stage anaerobic digestion (AD) process. Experimental data for the AD of poultry manure were used. The analytical method considers the protein as the only source of ammonia production in AD after degradation. Total ammonia nitrogen (TAN), total solids (TS), chemical oxygen demand (COD), and total volatile solids (TVS) were measured in the influent and effluent of the process. The TAN concentration in the effluent was predicted, this being the most inhibiting and polluting compound in AD. Despite the limited data available, the SVM-based model outperformed the analytical method for the TAN prediction, achieving a relative average error of 15.2% against 43% for the analytical method. Moreover, SVM showed higher prediction accuracy in comparison with Artificial Neural Networks. This result reveals the future promise of SVM for prediction in non-linear and dynamic AD processes.

Graphical abstract

Keywords

Anaerobic digestion Protein degradation Machine learning Prediction methods Support vector machines 

Notes

Acknowledgments

This research was conducted with the FONDECYT (Chile) No. 1140491, INNOVA (Chile) No. 12IDL2-13605, CONICYT-PCHA/Doctorado Nacional2016/21160226 and INNOVA (Chile) No 15VEIID-45613 grants.

References

  1. Abbasi M, Abduli MA, Omidvar B, Baghvand A (2012) Forecasting municipal solid waste generation by hybrid support vector machine and partial least square model. Int J Environ Res 7:27–38Google Scholar
  2. Abouelenien F, Namba Y, Kosseva MR, Nishio N, Nakashimada Y (2014) Enhancement of methane production from co-digestion of chicken manure with agricultural wastes. Bioresour Technol 159:80–87.  https://doi.org/10.1016/j.biortech.2014.02.050 CrossRefGoogle Scholar
  3. Alejo-Alvarez L, Guzmán-Fierro V, Fernández K, Roeckel M (2016) Technical and economical optimization of a full-scale poultry manure treatment process: total ammonia nitrogen balance. Environ Technol 28.  https://doi.org/10.1080/09593330.2016.1167963
  4. Angelidaki I, Ellegaard L, Ahring BK (1993) A mathematical model for dynamic simulation of anaerobic digestion of complex substrates: focusing on ammonia inhibition. Biotechnol Bioeng 42:159–166.  https://doi.org/10.1002/bit.260420203 CrossRefGoogle Scholar
  5. Angelidaki I, Ellegaard L, Ahring BK (1999) A comprehensive model of anaerobic bioconversion of complex substrates to biogas. Biotechnol Bioeng 63:363–372.  https://doi.org/10.1002/(SICI)1097-0290(19990505)63:3<363::AID-BIT13>3.0.CO;2-Z CrossRefGoogle Scholar
  6. Awolusi OO, Nasr M, Kumari S, Bux F (2016) Artificial intelligence for the evaluation of operational parameters influencing nitrification and nitrifiers in an activated sludge process. Microb Ecol 72:49–63.  https://doi.org/10.1007/s00248-016-0739-3 CrossRefGoogle Scholar
  7. Batstone DJ, Keller J, Angelidaki I, Kalyuzhnyi SV, Pavlostathis SG, Rozzi A, Sanders WT, Siegrist H, Vavilin VA (2002) The IWA anaerobic digestion model no 1 (ADM1). Water Sci Technol 45:65–73CrossRefGoogle Scholar
  8. Batstone DJ, Puyol D, Flores-Alsina X, Rodríguez J (2015) Mathematical modelling of anaerobic digestion processes: applications and future needs. Rev Environ Sci Biotechnol 14:595–613.  https://doi.org/10.1007/s11157-015-9376-4 CrossRefGoogle Scholar
  9. Bergland W, Botheju D, Dinamarca C, Bakke R (2011) Considering culture adaptations to high ammonia concentration in ADM1. SIMS 2011 52nd Int. Conf. Scand. Simul. Soc. 1, 1–8Google Scholar
  10. Blumensaat F, Keller J (2005) Modelling of two-stage anaerobic digestion using the IWA anaerobic digestion model no. 1 (ADM1). Water Res 39:171–183.  https://doi.org/10.1016/j.watres.2004.07.024 CrossRefGoogle Scholar
  11. Boisen S, Bech-Andersen S, Eggum BO (1987) A critical view on the conversion factor 6.25 from total nitrogen to protein. Acta Agric Scand 37:299–304.  https://doi.org/10.1080/00015128709436560 CrossRefGoogle Scholar
  12. Borowski S, Domański J, Weatherley L (2014) Anaerobic co-digestion of swine and poultry manure with municipal sewage sludge. Waste Manag 34:513–521.  https://doi.org/10.1016/j.wasman.2013.10.022 CrossRefGoogle Scholar
  13. Breure AM, Mooijman KA, van Andel JG (1986) Protein degradation in anaerobic digestion: influence of volatile fatty acids and carbohydrates on hydrolysis and acidogenic fermentation of gelatin. Appl Microbiol Biotechnol 24:426–431.  https://doi.org/10.1007/BF00294602 CrossRefGoogle Scholar
  14. Browne MW (2000) Cross-validation methods. J Math Psychol 44:108–132.  https://doi.org/10.1006/jmps.1999.1279 CrossRefGoogle Scholar
  15. Bujoczek G, Oleszkiewicz J, Sparling R, Cenkowski S (2000) High solid anaerobic digestion of chicken manure. J Agric Eng Res 76:51–60.  https://doi.org/10.1006/jaer.2000.0529 CrossRefGoogle Scholar
  16. Cao H, Xin Y, Yuan Q (2016) Prediction of biochar yield from cattle manure pyrolysis via least squares support vector machine intelligent approach. Bioresour Technol 202:158–164.  https://doi.org/10.1016/j.biortech.2015.12.024 CrossRefGoogle Scholar
  17. Chang R, College W (2002) Quimica General, 7th ed. McGraw-HillGoogle Scholar
  18. Corominas L, Garrido-Baserba M, Villez K, Olsson G, Cortés U, Poch M (2017) Transforming data into knowledge for improved wastewater treatment operation: a critical review of techniques. Environ Model Softw.  https://doi.org/10.1016/j.envsoft.2017.11.023
  19. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297.  https://doi.org/10.1023/A:1022627411411 CrossRefGoogle Scholar
  20. Dellana SA, West D (2009) Predictive modeling for wastewater applications: linear and nonlinear approaches. Environ Model Softw 24:96–106.  https://doi.org/10.1016/j.envsoft.2008.06.002 CrossRefGoogle Scholar
  21. Dixon M, Gallop JR, Lambert SC, Healy JV (2007) Experience with data mining for the anaerobic wastewater treatment process. Environ Model Softw 22:315–322.  https://doi.org/10.1016/j.envsoft.2005.07.031 CrossRefGoogle Scholar
  22. Donoso-Bravo A, Mailier J, Martin C, Rodríguez J, Aceves-Lara CA, Wouwer AV (2011) Model selection, identification and validation in anaerobic digestion: a review. Water Res 45:5347–5364.  https://doi.org/10.1016/j.watres.2011.08.059 CrossRefGoogle Scholar
  23. Erdirencelebi D, Yalpir S (2011) Adaptive network fuzzy inference system modeling for the input selection and prediction of anaerobic digestion effluent quality. Appl Math Model 35:3821–3832.  https://doi.org/10.1016/j.apm.2011.02.015 CrossRefGoogle Scholar
  24. Gavala HN, Angelidaki I, Ahring BK (2003) Kinetics and modeling of anaerobic digestion process. Biomethanation I 81:57–93.  https://doi.org/10.1007/3-540-45838-7 CrossRefGoogle Scholar
  25. Ghaly AE, Macdonald KN (2012) Drying of poultry manure for use as animal feed. Am J Agric Biol Sci 7:239–254.  https://doi.org/10.3844/ajabssp.2012.239.254 CrossRefGoogle Scholar
  26. Guo H, Jeong K, Lim J, Jo J, Kim YM, Park J, Kim JH, Cho KH (2015) Prediction of effluent concentration in a wastewater treatment plant using machine learning models. J Environ Sci 32:1–12.  https://doi.org/10.1016/j.jes.2015.01.007 CrossRefGoogle Scholar
  27. Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009). The WEKA data mining software: an update. ACM SIGKDD Explor. Newsl 11:10–18.  https://doi.org/10.1145/1656274.1656278
  28. Hansen KH, Angelidaki I, Ahring BK (1998) Anaerobic digestion of swine manure inhibition by ammonia. Water Sci Technol 32:5–12Google Scholar
  29. Holm-Nielsen JB, Al Seadi T, Oleskowicz-Popiel P (2009) The future of anaerobic digestion and biogas utilization. Bioresour Technol 100:5478–5484.  https://doi.org/10.1016/j.biortech.2008.12.046 CrossRefGoogle Scholar
  30. Iyappan P, Karthikeyan S, Sekar S (2011) Changes in the composition of poultry farm excreta (PFE) by the cumulative influence of the age of birds, feed and climatic conditions and a simple mean for minimizing the environmental hazard. Int J Environ Sci 1:847–859Google Scholar
  31. Kelleher BP, Leahy JJ, Henihan AM, O’Dwyer TF, Sutton D, Leahy MJ (2002) Advances in poultry litter disposal technology—a review. Bioresour Technol 83:27–36.  https://doi.org/10.1016/S0960-8524(01)00133-X CrossRefGoogle Scholar
  32. Kleerebezem R, van Loosdrecht MCM (2006) Critical analysis of some concepts proposed in ADM1. Water Sci Technol 54:51–57.  https://doi.org/10.2166/wst.2006.525 CrossRefGoogle Scholar
  33. Kuhn, M., 2008. Building predictive models in R using the caret package. J Stat Softw 28.  https://doi.org/10.18637/jss.v028.i05
  34. Lancaster HO, Seneta E (2005) Chi-square distribution, in: Encyclopedia of biostatistics. John Wiley & Sons, Ltd.  https://doi.org/10.1002/0470011815.b2a15018
  35. Lauwers J, Appels L, Thompson IP, Degrève J, Van Impe JF, Dewil R (2013) Mathematical modelling of anaerobic digestion of biomass and waste: power and limitations. Prog Energy Combust Sci 39:383–402.  https://doi.org/10.1016/j.pecs.2013.03.003 CrossRefGoogle Scholar
  36. Mosquera-Corral A, Sánchez M, Campos JL, Méndez R, Lema JM (2001) Simultaneous methanogenesis and denitrification of pretreated effluents from a fish canning industry. Water Res 35:411–418.  https://doi.org/10.1016/S0043-1354(00)00288-8 CrossRefGoogle Scholar
  37. Powers W, Capelari M (2017) Production, management and the environment symposium: measurement and mitigation of reactive nitrogen species from swine and poultry production. J Anim Sci 95:2236–2240.  https://doi.org/10.2527/jas2016.1187 CrossRefGoogle Scholar
  38. R Foundation for Statistical Computing (2016) R: a language and environment for statistical computing. R Core Team, ViennaGoogle Scholar
  39. Ramsay IR, Pullammanappallil PC (2001) Protein degradation during anaerobic wastewater treatment: derivation of stoichiometry. Biodegradation 12:247–257.  https://doi.org/10.1023/A:1013116728817 CrossRefGoogle Scholar
  40. Rashid R, Jamaluddin H, Aishah N, Amin S (2016) Empirical and feed forward neural networks models of tapioca starch. Appl Artif Intell 20:9514–9597.  https://doi.org/10.1080/08839510500191422 CrossRefGoogle Scholar
  41. Rivera-Salvador V, Aranda-Barradas JS, Espinosa-Solares T, Robles-Martínez F, Toledo JU (2015) The anaerobic digestion model Iwa-Adm1: a review of its evolution. Ing Agríc Biosist 1:109–117.  https://doi.org/10.5154/r.inagbi.2010.01.001 CrossRefGoogle Scholar
  42. Roshani A, Shayegan J, Babaee A (2012) Methane production from anaerobic co-digestion of poultry manure. J Environ Stud 38:22–24Google Scholar
  43. Samanta B, Al-Balushi KR, Al-Araimi SA (2003) Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection. Eng Appl Artif Intell 16:657–665.  https://doi.org/10.1016/j.engappai.2003.09.006 CrossRefGoogle Scholar
  44. Siegrist H, Vogt D, Garcia-Heras JL, Gujer W (2002) Mathematical model for meso- and thermophilic anaerobic sewage sludge digestion. Environ Sci Technol 36:1113–1123.  https://doi.org/10.1021/es010139p CrossRefGoogle Scholar
  45. Smola AJ, Scholkopf B (2004) A tutorial on support vector regression. Stat Comput 14:199–222.  https://doi.org/10.1023/B:Stco.0000035301.49549.88 CrossRefGoogle Scholar
  46. Strik DPBTB, Domnanovich AM, Zani L, Braun R, Holubar P (2005) Prediction of trace compounds in biogas from anaerobic digestion using the MATLAB neural network toolbox. Environ Model Softw 20:803–810.  https://doi.org/10.1016/j.envsoft.2004.09.006 CrossRefGoogle Scholar
  47. Turkdogan-Aydinol FI, Yetilmezsoy K (2010) A fuzzy-logic-based model to predict biogas and methane production rates in a pilot-scale mesophilic UASB reactor treating molasses wastewater. J Hazard Mater 182:460–471.  https://doi.org/10.1016/j.jhazmat.2010.06.054 CrossRefGoogle Scholar
  48. Üstün B, Melssen WJ, Buydens LMC (2006) Facilitating the application of support vector regression by using a universal Pearson VII function based kernel. Chemom Intell Lab Syst 81:29–40.  https://doi.org/10.1016/j.chemolab.2005.09.003 CrossRefGoogle Scholar
  49. Vanhooren H, Meirlaen J, Amerlinck Y, Claeys F, Vangheluwe H, Vanrolleghem PA (2003) WEST: modelling biological wastewater treatment. J Hydroinf 27–50Google Scholar
  50. Yenigün O, Demirel B (2013) Ammonia inhibition in anaerobic digestion: a review. Process Biochem 48:901–911.  https://doi.org/10.1016/j.procbio.2013.04.012 CrossRefGoogle Scholar
  51. Yu L, Wensel P, Ma J, Chen S (2013) Mathematical modeling in anaerobic digestion (AD). J Biorem Biodegrad S4, 12.  https://doi.org/10.4172/2155-6199.S4-003

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Luz Alejo
    • 1
  • John Atkinson
    • 2
  • Víctor Guzmán-Fierro
    • 1
  • Marlene Roeckel
    • 1
  1. 1.Departamento de Ingeniería QuímicaUniversidad de ConcepciónConcepciónChile
  2. 2.Facultad de Ingeniería y CienciasUniversidad Adolfo IbáñezSantiagoChile

Personalised recommendations