Skip to main content

Neural networks as a tool for control and management of a biological reactor for treating hydrogen sulphide


Based on an experimental database consisting of 194 daily cases, artificial neural networks were used to model the removal efficiency of a biofilter for treating hydrogen sulphide (H2S). In this work, the removal efficiency of the reactor was considered as a function of the changes in the air flow and concentration of H2S entering the biofilter. In order to obtain true representative values, the removal efficiencies (outputs) were measured 24 h after each input was changed. A MLP (multilayer perceptron 2-2-1) model with two input variables (unit flow and concentration of the contaminant fed into the biofilter) rendered good prediction values with a determination coefficient of 0.92 for the removal efficiency within the range studied. This means that the MLP model can explain 92% of the overall variability detected in the biofilter corresponding to a wide range of operating conditions.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4



Artificial neural network

b 1 and b 0 :

Slope and intercept, respectively, of a least-squares regression between the predicted and observed data

C :

Concentration of H2S fed to the reactor

d :

Index of agreement


Removal efficiency


Fraction of two


Multiple linear regression


Multilayer perceptron

Q u :

Unit flow

R :

Pearson correlation coefficient

R 2 :

Determination coefficient

R m :

Ratio of means


Total root mean squared error

R st :

The ratio of the systematic error component to total RMSE


  1. van Groenestijn JW, Kraakman NJR (2005) Recent developments in biological waste gas purification in Europe. Chem Eng J 113(2–3):85–91

    Article  CAS  Google Scholar 

  2. Deshusses MA, Johnson C (2000) Development and validation of a simple protocol to rapidly determine the performance of biofilters for VOC treatment. Environ Sci Technol 34:461–467

    Article  CAS  Google Scholar 

  3. Chmiel K, Konieczny A, Palica M, Jarzebski AB (2005) Periodic operation of biofilters. A concise model and experimental validation. Chem Eng Sci 60:2845–2850

    Article  CAS  Google Scholar 

  4. Morales M, Hernández S, Cornabé T, Revah S, Auria R (2003) Effect of drying on biofilter performance: modeling and experimental approach. Environ Sci Technol 37:985–992

    Article  CAS  Google Scholar 

  5. Alonso C, Sudian MT, Sorial GA, Smith FL, Biswas P, Smith PJ, Brenner RC (1997) Gas treatment in trickle-bed biofilters: biomass, how much is enough? Biotechnol Bioeng 54(6):583–594

    Article  CAS  Google Scholar 

  6. Alonso C, Suidan MT, Kim BR, Kim BJ (1998) Dynamic mathematical model for the biodegradation of VOCs in a biofilter: biomass accumulation study. Environ Sci Technol 31:3118–3123

    Article  Google Scholar 

  7. Delhoménie MC, Bibeau L, Gendron J, Brzezinski R, Heitz M (2003) A study of clogging in a biofilter treating toluene vapors. Chem Eng J 94:211–222

    Article  CAS  Google Scholar 

  8. Iliuta I, Larachi F (2004) Transient biofilter aerodynamics and clogging for VOC degradation. Chem Eng Sci 59:3293–3302

    Article  CAS  Google Scholar 

  9. Zarook S, Shaikh AA, Ansar Z (1997) Development, experimental validation and dynamic analysis of a general transient biofilter model. Chem Eng Sci 52:759–773

    Article  CAS  Google Scholar 

  10. Schwarz BCE, Devinny JS, Tsotsis TT (2001) A biofilter network model—importance of the pore structure and other large-scale heterogeneities. Chem Eng Sci 56:475–483

    Article  CAS  Google Scholar 

  11. Gerrard AM, Misiaczek O, Hajkova D, Halecky M, Paca J (2005) Steady state models for the biofiltration of styrene/air mixtures. Chem Biochem Eng Q 19(2):185–190

    CAS  Google Scholar 

  12. Spigno G, Zilli M, Nicolella C (2004) Mathematical modelling and simulation of phenol degradation in biofilters. Biochem Eng J 19:267–275

    Article  CAS  Google Scholar 

  13. Devinny JS, Ramesh J (2005) A phenomenological review of biofilter models. Chem Eng J 113:187–196

    Article  CAS  Google Scholar 

  14. Elias A, Ibarra-Berastegi G, Ormazabal J, Murgia I, Zugazti P (1996) ADM: a model for water treatment in an anaerobic biological reactor. In: Development and application of computer techniques to environmental studies VI. III, CMP. WIT, Southampton, pp 153–162

  15. Liu G, Mi Z (2004) Prediction of pulsation frequency of pulsing flow in trickle-bed reactors using artificial neural network. Chem Eng Sci 59:5787–5794

    Article  CAS  Google Scholar 

  16. Steyer JP, Harmand J (2003) Fault detection and isolation in wastewater treatment plants: comparison of different approaches and experimental results. In: Agathos SN, Reineke W (eds) Biotechnology for the environment: wastewater treatment and modelling, waste gas handling, Kluwer Academic Publishers, Dordrecht, vol. 3C, pp 87–100

  17. 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

    Article  Google Scholar 

  18. Hodgson BJ, Taylor CN, Ushio M, Leigh JR, Kalganova T, Baganz F (2004) Intelligent modelling of bioprocesses: a comparison of structured and unstructured approaches. Bioprocess Biosyst Eng 26:353–359

    Article  CAS  Google Scholar 

  19. Maier R, Dandy GC (2000) Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environ Model Softw 15:101–124

    Article  Google Scholar 

  20. Gardner MW, Dorling R (1998) Artificial neural networks (the multilayer perceptron). A review of applications in the atmospheric sciences. Atmos Environ 32:2627–2636

    Article  CAS  Google Scholar 

  21. Masters T (1993) Practical neural network recipes in C++. Academic, San Diego

    Google Scholar 

  22. Maier HR, Morgan N, Chow CWK (2004) Use of artificial neural networks for predicting optimal alum doses and treated water quality parameters. Environ Model Softw 19:485–494

    Article  Google Scholar 

  23. Bowden G, Maier HR, Dandy GC (2001) Optimal division of data for neural network models in water resources applications. Water Resour Res 38:21–28

    Google Scholar 

  24. Elías A, Barona A, Arreguy A, Ríos J, Aranguiz I, Peñas J (2002) Evaluation of a packing material for the biodegradation of H2S and product analysis. Process Biochem 37:813–820

    Article  Google Scholar 

  25. Barona A, Elías A, Arias R, Cano I, Gonzalez R (2004) Effect of sudden variations in operating conditions on biofilter performance. Biochem Eng J 22(1):25–31

    Article  CAS  Google Scholar 

  26. Barona A, Elias A, Amurrio A, Cano I, Arias R (2005) Hydrogen sulphide adsorption on a waste material used in bioreactors. Biochem Eng J 24:79–86

    Article  CAS  Google Scholar 

  27. Willmott CJ (1981) On the validation of models. Phys Geogr 2:184–194

    Google Scholar 

  28. Willmott CJ (1982) Some comments on the evaluation of model performance. Bull Am Meteorol Soc 63:1309–1313

    Article  Google Scholar 

  29. Willmott CJ, Ackleson SG, Davis RE, Feddema JJ, Klink KM, Legates DR, O’Donnell J, Rowe MC (1985) Statistics for the evaluation and comparison of models. J Geophys Res 90:8995–9005

    Article  Google Scholar 

  30. Hanna SR, Strimaitis DG, Chang JC (1991) User’s guide for software for evaluating hazardous gas dispersion models. American Petroleum Institute, Washington

    Google Scholar 

  31. Comrie A (1997) Comparing neural networks and regression models for ozone forecasting. J Air Waste Manag Assoc 47:653–663

    CAS  Google Scholar 

  32. Hunter A, Kennedy L, Henry J, Ferguson RI (2000) Application of neural networks and sensitivity analysis to improved prediction of trauma survival. Comput Methods Algorithms Biomed 62:11–19

    Article  CAS  Google Scholar 

  33. Wilks DS (1995) Statistical methods in the atmospheric sciences. Academic, San Diego

    Google Scholar 

Download references


The authors wish to thank the Basque Government (BERRILUR project No. IE03-110), the Spanish Government (MCYT PPQ2002-01088 with FEDER funding) and the University of the Basque Country (UPV 00149.345-E-15398/2003 project) for the financial support to develop this research. Special thanks are given to the EUVE for the lab-scale pilot plant simulation.

Author information

Authors and Affiliations


Corresponding author

Correspondence to A. Barona.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Elías, A., Ibarra-Berastegi, G., Arias, R. et al. Neural networks as a tool for control and management of a biological reactor for treating hydrogen sulphide. Bioprocess Biosyst Eng 29, 129–136 (2006).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


  • Bioreactors
  • Artificial neural networks
  • Numerical analysis
  • Statistical modelling
  • Hydrogen sulphide