3/15/2023 0 Comments Interval international keyweThe presence of the particularly strong 1997–1998 El Nin˜o event, and the short time span of the base period (1992–2006), limits the determination of other spatial teleconnections and then the reconstruction over preceding epochs. To understand some of the weaknesses we found, we tested the influence of the spatial distribution of tide gauges as well as the ability to properly reconstruct sea level in certain frequencies bands. We use sea level height fields obtained by satellite altimeters between 19, sea level height fields from recent reanalyses of oceanic circulation (SODA) and worldwide tide gauges series for the time interval 1958–2006, to investigate the limitations inherent in reconstructing the past ~50 years of sea level variation using empirical orthogonal function (EOF) decomposition. Understanding present-day global sea level rise requires a correct evaluation of past sea level field variability. Finally we forecast the water table up to the year 2015 and concluded that the forecasting behavior of water table in kushtia region of Bangladesh is slow but continuously fall down over time. Using model selection criteria and checking model adequacy it was found that, the SARIMA((1,2,10), 0, 0)(3, 1, 0)12 outperforms the candidate models considered in adequately capturing the behavior of water table. F-test, Granger-Newbold test and Diebold-Mariano test were used to compare the models. Standardized residual plot was used to check the outliers and histogram, probability plot, Q-Q plot and Jarque-Bera test were used to check normality of residuals. Correlogram and Ljung-Box test were performed to check the white noise property of residuals. ![]() In the succession of time series modeling multiplicative seasonal autoregressive integrated moving average (SARIMA) models were fitted for water table series. The tests suggested that the series is nonstationary and the seasonally differenced series is stationary. To test the stationary condition of the series we used the DF, ADF and Perron test in presence of structural change. The phase diagram shows the water table rise up in rainy season and fall down in dry season. The time series plot shows that the water table series is seasonal and it contains a structural change for the year 1987, but there is no trend over time. First exploratory data analysis (EDA) was used to uncover the hidden information carried by the observed data. The monthly water table data were collected from Bangladesh Water Development Board (BWDB). ![]() This study seeks to identify an appropriate univariate time series model that can be used for forecasting the ground water table in Kushtia region of Bangladesh.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |