Medium-term forecasts for groundwater production and rainfall amounts (Deir El-Balah City as a case study)
- PDF / 1,338,519 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 45 Downloads / 142 Views
(2020) 6:82
ORIGINAL ARTICLE
Medium‑term forecasts for groundwater production and rainfall amounts (Deir El‑Balah City as a case study) Ihsan A. Abuamra1 · Ashraf Y. A. Maghari2 · Hussam F. Abushawish3 Received: 6 February 2020 / Accepted: 1 September 2020 © Springer Nature Switzerland AG 2020
Abstract 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); autoregressive 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. Keywords Forecasting · Groundwater · Time series data · Auto-regressive integrated moving average · Exponential smoothing
Introduction
* Ashraf Y. A. Maghari [email protected] Ihsan A. Abuamra [email protected] Hussam F. Abushawish [email protected] 1
Department of Computer, Palestine Technical College, Gaza, Palestine
2
Faculty of Information Technology, Islamic University of Gaza, Gaza, Palestine
3
Department of Business Administration, Palestine Technical College, Gaza, Palestine
Water is regarded as one of Palestine’s scarce resources. Basic reason for this is the constraints imposed by the Israeli government on the Palestinian side to extract and use water. In addition, the economic crisis in the Gaza plays a major role due to the absen
Data Loading...
