Skip to main content

Advertisement

SpringerLink
Log in

A comparative study of the feed forward back propagation (FFBP) and layer recurrent (LR) neural network model for forecasting ground level ozone concentration

  • Published:
Air Quality, Atmosphere & Health Aims and scope Submit manuscript

Abstract

Ozone (O3) in the troposphere is considered as a secondary air pollutant and has an adverse impact on human health and climatic condition. In many countries including India, O3 is listed as one of the criteria pollutants. Thus, a proper forecasting technique of ozone concentration is necessary for protecting the human health. The concentration of ozone in the troposphere depends on the meteorological condition and precursor’s levels. Hence, it is essential to consider these dependent factors in the development of prediction model. The study aims to develop an ozone forecasting model using artificial neural network (ANN). Three-year air pollution and meteorological data (1 January 2009 to 31 December 2011) of Kolkata City was used for model development. Two types of learning algorithms [feed forward back propagation (FFBP) and layer recurrent (LR)] were used for training the ANN model. Four meteorological factors (relative humidity, temperature, wind speed, and wind direction) along with the NO2 concentration and previous day’s ozone concentration were used as input parameters in the model for predicting the ozone concentration. The number of neurons in the hidden layers of a neural network model was optimized for both the algorithms. The number of input combinations was also optimized using forward search algorithm. The model performances were tested using four statistical indices [percentage of root mean square error (RMSE), coefficient of determination (R 2), fractional bias (FB), index of agreement (IOA)] for evaluating the ANN models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  • Abdul-Wahab SA, Al-Alawi SM (2008) Prediction of sulfur dioxide (SO2) concentration levels from the Mina Al-Fahal Refinery in Oman using artificial neural networks. Am J Environ Sci 4:473–481

    Article  CAS  Google Scholar 

  • Anderson HR (2009) Air pollution and mortality: a history. Atmos Environ 43:142–152

    Article  CAS  Google Scholar 

  • Awang NR, Elbayoumi M, Ramli NA, Yahaya AS (2016) Diurnal variations of ground-level ozone in three port cities in Malaysia. Air Qual Atmos Health 9(1):25–39

    Article  CAS  Google Scholar 

  • Bascom R, Bromberg PA, Costa DA, Devlin R, Dockery DW, Frampton MW, Lambert W, Samet JM, Speizer FE, Utell M (1996) Health effects of outdoor air pollution. Am J Resp Crit Care Med 153:3–50

    Article  Google Scholar 

  • Bnanankhah A, Nejadkoorki F (2012) Artificial neural network: a nonlinear tool for air quality modelling and monitoring. International Conference on Applied Life Sciences Turkey September 10–12.

  • Brimblecombe P (1987) The Big Smoke: a history of air pollution in London since medieval times. Routledge, Methuen, London

    Google Scholar 

  • Camalier L, Cox W, Dolwick P (2007) The effects of meteorology on ozone in urban areas and their use in assessing ozone trends. Atmos Environ 41:7127–7137

    Article  CAS  Google Scholar 

  • Chaloulakou A, Assimacopoulas D, Lekkas T (1999) Forecasting daily maximum ozone concentrations in the Athens Basin. Environ Monit Assess 56:97–112

    Article  CAS  Google Scholar 

  • Chen S, Billings SA, Luo W (1989) Orthogonal least squares methods and their application to nonlinear system identification. Int J Control 50:1873–1896

    Article  Google Scholar 

  • Chen S, Hong X, Harris CJ, Sharkey PM (2004) Sparse modeling using orthogonal forward regression with PRESS statistic and regularization. IEEE Trans Syst Man Cybern Part B 34:898–911

    Article  Google Scholar 

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

    Article  CAS  Google Scholar 

  • Cox WM, Chu S-H (1996) Assessment of inter annual ozone variation in urban areas from a climatological perspective. Atmos Environ 30:2615–2625

    Article  CAS  Google Scholar 

  • Dapeng XU, Yap D, Taylor PA (1996) Meteorologically adjusted ground level ozone trends in Ontario. Atmos Environ 30(7):1117–1124

    Article  Google Scholar 

  • Dawson JP, Adams PJ, Pandis SN (2007) Sensitivity of ozone to summertime climate in the Eastern USA: a modeling case study. Atmos Environ 41:1494–1511

    Article  CAS  Google Scholar 

  • Gardner MW, Dorling SR (1999) Neural network modelling and prediction of hourly NOx and NO2 concentrations in urban air in London. Atmos Environ 33:709–719

    Article  CAS  Google Scholar 

  • Gardner MW, Dorling SR (2000) Statistical surface ozone models: an improved methodology to account for non-linear behaviour. Atmos Environ 34:21–34

    Article  CAS  Google Scholar 

  • Gorai AK, Tuluri F, Tchounwou PB, Ambinakudige S (2015) Influence of local meteorology and NO2 conditions on ground level ozone concentration in eastern part of Texas, USA. Air Qual Atmos Health 8:81–96. doi:10.1007/s11869-014-0276-5

    Article  CAS  Google Scholar 

  • Hadjiiski L, Geladi P, Hopke P (1999) A comparison of modelling nonlinear systems with artificial neural networks and partial least squares. Chemometr Intell Lab 49(1):91–103

    Article  CAS  Google Scholar 

  • Karaca F, Alagha O, Erturk F (2005) Statistical characterization of atmospheric PM10 and PM2.5 concentrations at a non-impacted suburban site of Istanbul, Turkey. Chemosphere 59(8):1183–1190

    Article  CAS  Google Scholar 

  • Khan JA, Van Aelst S, Zamar RH (2007) Building a robust linear model with forward selection and stepwise procedures. Comput Stat Data An 52(1):239–248

    Article  Google Scholar 

  • Kolehmainen M, Martikainen H, Hiltunen T, Ruusaknen J (2000) Forecasting air quality parameters using hybrid neural network modelling. Environ Monit Assess 65:277–286

    Article  CAS  Google Scholar 

  • Korsog PE, Wolff GT (1991) An examination of ozone urban trends in the northeastern US (1973–1983) using a robust statistical method. Atmos Environ B 25:47–57

    Article  Google Scholar 

  • Kumar A, Goyal P (2011) Forecasting of air quality in Delhi using principal component regression technique. Atmos Pollut Res 2:436–444

    Article  CAS  Google Scholar 

  • Kumar A, Goyal P (2013) Forecasting of air quality index in Delhi using neural network based on principal component analysis. Pure Appl Geophys 170(4):711–722

    Article  Google Scholar 

  • Lippmann M (1991) Health effects of tropospheric ozone. Environ Sci Techno 25:1954–1962

    Article  CAS  Google Scholar 

  • Mathew RH, Kumar P, Harrison RM (2012) Particles air quality policy and health. Chem Soc Rev 41:6606–6630

    Article  Google Scholar 

  • Nagendra SMS, Khare M (2006) Artificial neural network approach for modelling nitrogen dioxide dispersion from vehicular exhaust emissions. Eco Model 190(1–2):99–115

    Article  CAS  Google Scholar 

  • National Ambient Air Quality Standard (NAAQS), New Delhi, India (2009) Available online http://cpcb.nic.in/National_Ambient_Air_Quality_Standards.php (Last accessed on 12th December 2014)

  • Nunnari G, Dorling S, Schlink U, Cawley G, Foxall R, Chatterton T (2004) Modelling SO2 concentration at a point with statistical approaches. Environ Model Softw 19(10):887–905

    Article  Google Scholar 

  • Panchal G, Ganatra A, Kosta YP, Pancha D (2011) Behaviour analysis of multilayer perceptrons with multiple hidden neurons and hidden layers. IJCTE 3(2):332–337

    Article  Google Scholar 

  • Rao ST, Sistla G, Pagnotti V, Peterson WB, Irwin JS, Turner DB (1985) Evaluation of the performance of RAM with the regional air pollution study data base. Atmos Environ 19:229–245

    Article  Google Scholar 

  • Robeson SM, Steyn DG (1990) Evaluation and comparison of statistical forecast models for daily maximum ozone concentrations. Atmos Environ B 24:303–312

    Article  Google Scholar 

  • Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. In: Rumelhart DE, McClelland JL (eds) Parallel distributed processing, 8th edn. MIT Press, Cambridge, England, pp 45–76

    Google Scholar 

  • Srinivasan D, Liew AC, Chang CS (1994) A neural network short-term load forecaster. Elect Power Syst Res 28:227–234

    Article  Google Scholar 

  • Swingler K (1996) Applying neural networks: a practical guide. Academic Press, London

    Google Scholar 

  • Wang XX, Chen S, Lowe D, Harris CJ (2006) Sparse support vector regression based on orthogonal forward selection for the generalised kernel model. Neurocomputing 70:462–474

    Article  Google Scholar 

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

    Article  Google Scholar 

  • Willmott CJ, Ackleson SG, Davis RE, Feddema JJ, Klink KM, Legates DR, O’donnell J, Rowe CM (1985) Statistics for the evaluation and comparison of models. J Geophys Res 90(C5):8995–9005

    Article  Google Scholar 

  • Yi J, Prybutok VR (1996) A neural network model forecasting for prediction of daily maximum region concentration in an industrialized urban area. Environ Pollut 92:349–357

    Article  CAS  Google Scholar 

  • Ziomas IC, Melas D, Zerefos CS, Bais AF, Paliatsos AG (1995) Forecasting peak pollutant levels from meteorological variables. Atmos Environ 29:3703–3711

    Article  CAS  Google Scholar 

Download references

Acknowledgments

The authors would like to acknowledge the financial support from the Department of Science and Technology, New Delhi Grant No. SR/FTP/ES-17/2012. The authors are thankful to the West Bengal Pollution Control Board for providing the air quality data. The authors are thankful to the anonymous reviewer for putting their valuable comments on the manuscript for improving the quality.

Author information

Authors and Affiliations

  1. Department of Mining Engineering, National Institute of Technology, Rourkela, Odisha, 769008, India

    A. K. Gorai & Gargi Mitra

Authors
  1. A. K. Gorai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Gargi Mitra
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to A. K. Gorai.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interests regarding the publication of this paper.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gorai, A.K., Mitra, G. A comparative study of the feed forward back propagation (FFBP) and layer recurrent (LR) neural network model for forecasting ground level ozone concentration. Air Qual Atmos Health 10, 213–223 (2017). https://doi.org/10.1007/s11869-016-0417-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11869-016-0417-0

Keywords

Search

Navigation