International Journal of Statistics and Reliability Engineering

No Publication Cost

Vol 9, No 3:

subscription

The Rainfall Forecast Models Analysis and Their Volatility

Abstract

Many realistic domains have a lot of time-series data. Rainfall dependence structures are generally complicated in both time and space. The analysis of such data is highly significant in a wide range of applications where there are trends that alter over time or where there is a specific seasonality. Nonlinear variance features, also known as variance clustering or volatility, affect rainfall series, where large changes tend to follow large changes and subtle changes tend to follow slight changes. The focus of most empirical hydrological time series modeling was on modeling and predicting the mean trend of the time series using the traditional Autoregressive Moving Average (ARMA) modeling method proposed by the Box - Jenkins methodology. Forecasting is the government's major plan of action for monitoring and controlling the territory's outcomes. This research examines ARMA (Autoregressive Moving Averages), ARIMA (Autoregressive Integrated Moving Average), SARIMA (Seasonal Autoregressive Integrated Moving Average), and ARCH – GARCH modeling as realistic methods for forecasting rainfall time series. The comparison demonstrates the models' disparities accuracy. In terms of the efficiency criterion, all models are compared. As a whole, the composite ARIMA-GARCH model resembles the dynamics of daily rainfall series. Seasonal ARIMA, on the other hand, has become a suitable model for the monthly average rainfall series.

Full Text

PDF

References

1. A. Srihari; P. Mousumi and S. Krishnaswamy; A Comparative Study and Analysis of Time Series Forecasting Techniques. SN Computer Science, 1(3), 1-7 (2020).

2. E. Szolgayova; Modelling and Forecasting Daily River Discharge Considering Autoregressive Heteroskedasticity. Geophysical Research Abstract, 13, EGU2011-10681-1, (2011).

3. G.E.P. Box and G.M. Jenkins; Time Series Analysis: Forecasting and Control. Holden-Day, Boca Raton, (1976).

4. H. Altaf and M. Nasser; Comparison of GARCH and Neural Network Methods in Financial Time Series Prediction. Proceedings of the International Conference on Computer and Information Technology, 25-27 December 2008, Khulna, Bangladesh (2008).

5. J. Suhaila and J. AbdulAziz; Fitting the Statistical Distributions to the Daily Rainfall Amount in Peninsular Malaysia. Jurnal Teknologi, Universiti Teknologi Malaysia, 46(C), 33–48 (2007).

6. O. Margaretha and Herena, P; Arima Model for Forecasting the Price of Medium Quality Rice to Anticipate Price Fluctuations. Procedia Computer Science, 135, 707-711 (2018).

7. R.F. Engle; Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation. Econometrica, 50(4), 987–1007 (1982).

8. T. Bollerslev; Generalized Autoregressive Conditional Heteroscedasticity. Journal of Econometrics, 31(3), 307-327 (1986).

9. W. Fang,; Li. Menggang,; Mei. Yiduo and Li. Wenrui; Time Series Data Mining: A Case Study with Big Data Analytics Approach. IEEE Access, (2017), DOI:10.1109/ACCESS.2017.

10. W. Wang; P. H. A. J. M. Van Gelder; J. K. Vrijling and J. Ma; Testing and Modeling Autoregressive Conditional Heteroskedasticity of Streamflow Processes, Nonlinear Processes in Geophysics, 12(1), 55–66 (2005).

11. Y. Fadhilah and L.K. Ibrahim; Hybrid of ARIMA-GARCH Modeling in Rainfall Time Series. Jurnal Teknologi, 63(2), 27-34 (2013).

ISSN(P) 2350-0174

ISSN(O) 2456-2378

Journal Content