Modeling water table depth fluctuation with special reference to iran: the singular spectrum analysis approach

Abstract

This paper presents a statistical analysis of water table depth fluctuations in the Ghahavand plain of Hamedan province, western Iran. The study is based on 49,232 water table depth records collected by the Hamedan regional water authority between October 1988 and March 2016. The data were processed to improve their quality and construct a monthly time series of water table depth. Singular Spectrum Analysis (SSA), a non-parametric technique for time series analysis, was used to analyze the time series. Exponentially Weighted Moving Average (EWMA) was applied to the residuals of the SSA model to monitor management policies and institutions. The EWMA control chart is an effective alternative to the Shewhart control chart when the goal is to detect smaller shifts in the process. One of the key advantages of using EWMA is its robustness to non-normality, making it suitable for real-world applications where data often deviates from the normal distribution. The results indicate that the SSA model fits the data very well. Using EWMA control chart on the residuals of the SSA model revealed three statistically unusual points that need to be examined by water resource management systems. The findings of this study can assist water resource managers in making informed decisions regarding groundwater management policies and practices.