Agricultural Research Management Information System

Home
Research Summary
Search
About Us
- ARMIS
- Brochure
Contact Us
Report
User Request
Data Input
Help
- Operation Manual
  - PDF
  - Video
- Program Area & Commodity
We have reached 37600 number of research entries at this moment.

- Logout

Research Detail

Home
Research
Detail

On Identifying the Sarima Model to Forecast the Humidity of Some Selected Stations in Bangladesh

Md. Moyazzem Hossain
Department of Statistics, Jahangirnagar University, Savar, Dhaka-1342, Bangladesh

Abstract/ Executive Summary:

Bangladesh is predominantly an agricultural country. Crop agriculture is highly influenced by climatic change and the majority of the population is dependent on the agricultural crop in Bangladesh. The cultivation mainly depends on natural calamities like rainfall, humidity and temperature. Humidity affects crops through evaporation, transpiration and condensation. This paper attempts to identify the appropriate SARIMA model and check the statistical properties of the fitted model for the humidity for selected stations. Finally, forecast some future monthly humidity of the stations considered in this study. The forecasted series is really a better representation of the original humidity series of the selected stations in Bangladesh. Thus the fitted models are used to forecasting the monthly humidity for the upcoming two years to help decision-makers to establish priorities in terms of water demand management.

Keywords: Humidity, Model Selection, Jarqu-Bera Test, Ljung-Box Test, Bangladesh.

Location: Barisal, Bogra, Chittagong, Dhaka, Khulna, Rajshahi, Rangpur and Sylhet.

Start Date: 00-01-1972

End Date: 00-07-2015

Program Area: Knowledge Management

Non-commodity: Modeling

Objectives:

This paper attempts to identify the appropriate SARIMA model and check the statistical properties of the fitted model for the humidity for selected stations. Finally, forecast some future monthly humidity of the stations considered in this study.

Methodology:

3.1 Study area This study purposively selected eight stations from different part of Bangladesh. They are Barisal, Bogra, Chittagong, Dhaka, Khulna, Rajshahi, Rangpur and Sylhet. 3.2 Data source The necessary secondary data have been taken from the website of Bangladesh Agricultural Research Council (BARC) and http://en.tutiempo.net/climate/10-1982/ws-418830.html for measuring the humidity pattern. 3.3 Study period The necessary data of monthly humidity were collected for the selected meteorological stations in Bangladesh over the period January, 1972 to July, 2015. 3.4 SARIMA model Box and Jenkins (1976) suggested the use of seasonal autoregressive (SAR) and seasonal moving average (SMA) terms for monthly or quarterly data with systematic seasonal movements. The Box-Jenkins approach for modeling and forecasting has the advantage in analyze the seasonal time series data.

Source of Information: INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCES Volume 6, No 6, 2016

Article Link (Online Journal): doi: 10.6088/ijes. 6102

Funding Source:

Budget:

Total Budget (Tk.) :

Achievement/Findings:

The prediction of atmospheric parameters is essential for climate monitoring, drought detection, severe weather prediction, agriculture and production, planning in energy and industry, communication, pollution dispersal etc. The original Time Series of humidity for all stations selected for this study are stationary at 5 percent level of significance. Also, to check the seasonal variation we compute the seasonal index. From the seasonal index we may conclude that there is a seasonal variation of the humidity series for all stations considered in the study.

These models are selected on the basis of model selection criteria like AIC, AICC and BIC. We check the normality and autocorrelation of errors of the fitted model. Ljung-Box test is used to check the autocorrelation and Jarque-Bera test is used to check the normality assumption of the error of the fitted model. It is observed that the errors of the fitted model are normally distributed at 5 percent level of significance for all stations considered in this study. Also, there is no autocorrelation among the residuals of the fitted model for Barisal, Chittagong, Dhaka, Khulna and Sylhet at a 5 percent level of significance. The autocorrelation is present in Bogra, Rajshahi and Rangpur stations.

From the graphical comparison, it is observed that the forecasted series fluctuated from the original series with a very small amount which shows the fitted series has the same manner as the original series for all stations considered in this study. Therefore, the forecasted series is really a better representation of the original humidity series of the selected stations in Bangladesh. Thus the fitted models are used to forecasting the monthly humidity for the upcoming two years to help decision-makers to establish priorities in terms of water demand management.

Knowledge Management: Journal