Skip to main navigation menu Skip to main content Skip to site footer
Plant Science Today (PST)

Research Articles

Vol. 13 No. sp5 (2026): Recent Advances in Agriculture

Development of forecasting models for area and production of pineapple (Ananas comosus (L.) Merr.) in Assam

DOI
https://doi.org/10.14719/pst.14285
Submitted
28 February 2026
Published
04-08-2026

Abstract

Pineapple (Ananas comosus (L.) Merr.) is an economically important fruit crop in India with substantial regional production significance. Assam is the leading pineapple producing state of the country. Accurate forecasting of pineapple area and production is critical for agricultural planning and policy formulation. This research included trend pattern analysis and forecasting model development for pineapple area and production data of Assam. Four trendline models were developed for both the area and production series, out of which the logarithmic model was identified as the most suitable for pineapple area and exponential model for pineapple production. Three forecasting approaches were applied: auto-regressive integrated moving average model (ARIMA), artificial neural network (ANN) and non-linear support vector regression (NLSVR). A hybrid modelling framework was employed to integrate linear and non-linear components. Comparative evaluation showed that the ANN model outperformed ARIMA and NLSVR as standalone models, while the ARIMA-ANN hybrid outperformed the ARIMA-NLSVR hybrid for both series. The performances of all models were compared through root mean square error (RMSE) and mean absolute percentage error (MAPE) measures. For pineapple production, ANN model exhibited lowest RMSE and MAPE than among all evaluated models (ARIMA, NLSVR, ARIMA-ANN and ARIMA-NLSVR). On the other hand, hybrid ARIMA-ANN model emerged as best model for pineapple area series than the other four forecasting models. The findings of this study may support agricultural planners, policymakers and stakeholders in developing effective production strategies, resource allocation plans and long-term forecasting frameworks for pineapple cultivation in Assam.

References

  1. 1. Ministry of Agriculture and Farmers Welfare. Horticultural statistics at a glance 2020-21. New Delhi: Government of India; 2021.
  2. 2. Rathod S, Mishra GC, Singh KN. Hybrid time series models for forecasting banana production in Karnataka State. J Indian Soc Agric Stat. 2017;71(3):193–200.
  3. 3. Alam W, Sinha K, Kumar RR, Ray M, Rathod S, Singh KN, et al. Hybrid linear time series approach for long-term forecasting of crop yield. Indian J Agric Sci. 2018;88(8):1275–9.https://doi.org/10.56093/ijas.v88i8.82573
  4. 4. Sujatha P. Hybrid statistical models for forecasting yield of mango and banana in Tamil Nadu, India. Asian J Agric Ext Econ Sociol. 2021;39(11):168–74. https://doi.org/10.9734/ajaees/2021/v39i1130738
  5. 5. Directorate of Economics and Statistics. Statistical handbook of Assam 2023–24. Guwahati: Government of Assam; 2024.
  6. 6. Box GEP, Jenkins GM, Reinsel GC, Ljung GM. Time series analysis: forecasting and control. 5th ed. Hoboken (NJ): John Wiley & Sons; 2015.
  7. 7. Vapnik VG. Support vector method for function approximation, regression estimation and signal processing. In: Mozer M, Jordan M, Petsche T, editors. Adv Neural Inf Process Syst. Cambridge (MA): MIT Press; 1997. p. 281–7.
  8. 8. Zhang GP. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing. 2003;50:159–75. https://doi.org/10.1016/S0925-2312(01)00702-0
  9. 9. Brock WA, Dechert WD, Scheinkman JA, LeBaron B. A test for independence based on the correlation dimension. Econom Rev. 1996;15(3):197–235. https://doi.org/10.1080/07474939608800353
  10. 10. Chatfield C. The analysis of time series: an introduction. 6th ed. Boca Raton (FL): CRC Press; 2004.
  11. 11. Hyndman RJ, Athanasopoulos G. Forecasting: principles and practice. 3rd ed. Melbourne (AU): OTexts; 2018. https://doi.org/10.32614/CRAN.package.fpp3
  12. 12. Gujarati DN, Porter DC. Basic econometrics. 5th ed. New York (US): McGraw-Hill Education; 2009.
  13. 13. Granger CWJ, Newbold P. Forecasting economic time series. 2nd ed. San Diego (US): Academic Press; 1986.
  14. 14. Neog B, Gogoi B, Barua S, Mahanta, Sarma K. Development of hybrid time series models for forecasting autumn rice production in Assam. Pharma Innov J. 2023;12(2):3376–84.
  15. 15. Zhang GP, Patuwo BE, Hu MY. Forecasting with artificial neural networks: the state of the art. Int J Forecast. 1998;14(1):35–62. https://doi.org/10.1016/S0169-2070(97)00044-7
  16. 16. Khashei M, Bijari M. A novel hybridization of artificial neural networks and ARIMA models for time series forecasting. Appl Soft Comput. 2011;11(2):2664–75. https://doi.org/10.1016/j.asoc.2010.10.015
  17. 17. Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Netw. 1989;2(5):359–66. https://doi.org/10.1016/0893-6080(89)90020-8
  18. 18. Varghese E, Gills R, Anuja AR, Jayasankar J, editors. Manual on advanced analytical tools for social science research. Vol. 2. CMFRI Training Manual Series No. 29/2023. Cochin: ICAR-CMFRI; 2023. p. 324.
  19. 19. Pai PF, Lin CS. A hybrid ARIMA and support vector machines model in stock price forecasting. Omega. 2005;33(6):497–505. https://doi.org/10.1016/j.omega.2004.07.024
  20. 20. Vapnik VN. Statistical learning theory. New York (US): Wiley; 1998.
  21. 21. Neog B, Gogoi B, Patowary AN. Development of hybrid time series models for forecasting autumn rice using ARIMAX-ANN and ARIMAX-SVM. Ann For Res. 2022;65(1):9119–33.

Downloads

Download data is not yet available.