ملخص الدراسة:

Forecasting is a data mining technique which benefits from a variety of time series data sources to extract actual value from historical data and helps business decision-makers in effective planning. An increase in demand for groundwater associated with uncontrolled well digging and reduced rainfall, which is the primary source of groundwater recharge, has led to the depletion of groundwater wells. As a result, the mixing of seawater with groundwater increases the salinity rate, especially in areas where wells are close to the Mediterranean Sea in Gaza. Wells digging without governmental control, increasing salinity percentages. Therefore, the arching aim of this study was to investigate the relationship between rainfall and groundwater production. In this paper, five forecasting techniques were applied on two real data sets: the rain amounts we gained from the Ministry of Agriculture and the groundwater production amounts from the Coastal Municipalities Water Utility (CMWU) of Deir El-Balah City in the Gaza Strip. The following forecasting algorithms were used: exponential smoothing (ETS); auto-regressive integrated moving average (ARIMA); and ARIMA combined with neural network (NN), (ETS) and state space model with Box–Cox transformation, ARMA errors, and trend and seasonal components (TBATS). The best performance of applied algorithms on rainfall data according to mean absolute percentage error (MAPE) measure was (ARIMA + NN) which gave the MAPE = 21%. On the other hand, ARIMA was the most convenient algorithm to forecast wells production (MAPE = 4.9%). The results demonstrated that within the next 5 years, the amounts of rainfall and groundwater production will decrease by 8.4% and 1.05%, respectively, compared to the amounts of rainfall and groundwater produced over the time span over the period (2013–2017). Based on these results, it was concluded that salinity would continue to increase in the coming years making the groundwater unusable.

توثيق المرجعي (APA)