Abstract
Rainfall being a complex phenomenon governed by various meteorological parameters is difficult to model and forecast with high precision. For hilly regions such as state of Sikkim and adjoining areas of West Bengal, rainfall acts as lifeline. Several parametric models such as seasonal autoregressive integrated moving average (SARIMA) and exponential autoregressive (EXPAR) are very popular and extensively used to model and forecast rainfall. Owning to complex nature of rainfall series, non-parametric time delay neural network (TDNN) model has also gained substantial amount of attention by researchers. This study uses these two broad class of models and applies them to the monthly rainfall of Sub-Himalayan West Bengal and Sikkim. The models were compared based on their forecasting efficiencies and pattern prediction ability.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Availability of data and material
Rainfall series was collected from Open Government Data (OGD) Platform India (www.data.gov.in).
Code availability
Code will be made available if asked for.
References
Akpanta AC, Okorie IE, Okoye NN (2015) SARIMA modelling of the frequency of monthly rainfall in Umuahia, Abia state of Nigeria. Am J Math Stat 5:82–87
Ali S, Shahbaz M (2020) Streamflow forecasting by modeling the rainfall–streamflow relationship using artificial neural networks. Model Earth Syst Environ 6:645–1656
Ansley CF, Spivey WA, Wrobleski WJ (1977) A class of transformation for Box Jenkins seasonal models. Appl Stat J Roy ST C 26:73–178
Baragona R, Battaglia F, Cucina D (2002) A note on estimating autoregressive exponential models. Quaderni di Statistica e Matematica Applicata alle Scienze Economico-Sociali 4:71–88
Box GEP, Jenkins GM (1970) Time series analysis, forecasting and control. Holden-Day, Okland
Chattopadhyay S, Chattopadhyay G (2010) Univariate modelling of summer-monsoon rainfall time series: comparison between ARIMA and ARNN. C R Geosci 342:100–107
Dabral PP, Murry MZ (2017) Modelling and forecasting of rainfall time series using SARIMA. Environ Process 4:399–419
Darbellay GA, Slama M (2000) Forecasting the short-term demand for electricity: Doneural networks stand a better chance? Int J Forecast 16:71–83
Demuth H, Beale M (2002) Neural network toolbox user’s guide. Mathworks, Natick
Elman J (1990) Finding structure in time. Cogn Sci 14:179–211
Ghazal MA, Elhassanein A (2009) Dynamics of EXPAR models for high frequency data. Int J Appl Math Stat 14:88–96
Gurung B (2013) An application of exponential autoregressive (EXPAR) nonlinear time-series model. Int J Inf Comput Technol 3:261–266
Gurung B, Paul RK, Singh KN, Panwar S, Lama A, Lepcha L (2016) An alternative approach to capture cyclical and volatile phenomena in time-series data. Mod Assist Stat Appl 11:221–230
Haykin S (1999) Neural networks: a comprehensive foundation, 2nd edn. Prentice- Hall, Englewood Cliffs
Islam S, Talukdar B (2016) Performance improvement of a rainfall prediction model using particle swarm optimization. Int J Comput Eng Res 6:39–42
Jha GK, Sinha K (2012) Time-delay neural networks for time series prediction: an application to the monthly wholesale price of oilseeds in India. Neural Comput Appl 24:563–571
Katsiampa P (2014) A new approach to modelling nonlinear time series: introducing the ExpAR-ARCH and ExpAR-GARCH models and applications. In: OASIcs-OpenAccess series in informatics, vol 37. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik
Kulkarni GE, Muley AA, Deshmukh NK, Bhalchandra PU (2018) Autoregressive integrated moving average time series model for forecasting air pollution in Nanded city, Maharashtra, India. Model Earth Syst Environ 4:1435–1444
Luk KC, Ball JE, Sharma A (2000) A study of optimal model lag and spatial inputs to artificial neural network for rainfall forecasting. J Hydrol 227:56–65
Luk KC, Ball JE, Sharma A (2001) An application of artificial neural networks for rainfall forecasting. Math Comput Model 33:683–693
Murthy KVN, Saravana R, Vijaya K (2018) Modeling and forecasting rainfall patterns of southwest monsoons in North-East India as a SARIMA process. Meteorol Atmos Phys 130:99–106
Nanda SK, Tripathy DP, Nayak SK, Mohapatra S (2013) Prediction of rainfall in India using artificial neural network (ANN) models. Int J Intell Syst Appl 12:1–22
Patowary A, Pathak B, Hazarika J (2017) Studying monthly rainfall over Dibrugarh, Assam: use of SARIMA approach. Mausam 68:349–356
Somvanshi VK, Pandey OP, Agrawal PK, Kalanker N, Ravi PM, Chand R (2006) Modelling and prediction of rainfall using artificial neural network and ARIMA techniques. J Ind Geophys Union 10:141–151
Wang S, Fenga J, Liu G (2013) Application of seasonal time series model in the precipitation forecast. Math Comput Model 58:677–683
Wu CL, Chau KW, Fan C (2010) Prediction of rainfall time series using modular artificial neural networks coupled with data preprocessing techniques. J Hydrol 389:146–167
Yesmin M, Akhter Y, Begum M (2012) Modeling rainfall in Dhaka division of Bangladesh using time series analysis. J Math Model Appl 1:67–73
Author information
Authors and Affiliations
Contributions
Preparation of original manuscript: AL, BG. Data compilation: HS, PM. Coding and analysis: AL, BG. Results and discussion: AL, HS, RSS. Finalization of manuscript: AL, KNS.
Corresponding author
Ethics declarations
Conflict of interest
Authors declare no known conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lama, A., Singh, K.N., Singh, H. et al. Forecasting monthly rainfall of Sub-Himalayan region of India using parametric and non-parametric modelling approaches. Model. Earth Syst. Environ. 8, 837–845 (2022). https://doi.org/10.1007/s40808-021-01124-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40808-021-01124-5