Answers are grounded in this paper and cite their sources.
Generating time series data are an important tool in operations research, as this data is often the basis of model decision-makers. In this study, the annual maximum rainfall (AMR) data from three rainfall stations (i.e., Duhok, Erbil, and Sulaymaniya) located in the Kurdistan Region of Iraq have been used to build auto-regressive integrating moving average (ARIMA) models. For this reason, the rainfall data series from the years 1991 to 2021 was used. The Box-Cox transformation was used to make the rainfall time series stationary and normal. Several statistical tests were used to evaluate how well the successful ARIMA models performed. Results revealed that the most suitable model for the Duhok station was ARMA (0, 3), and for both Erbil and Sulaymaniya stations, it was the ARMA (0, 4) model. The AMR data for the following five years was predicted using these models (2022 to 2026). The study found that in a semi-arid region like the Kurdistan Region of Iraq, the ARIMA models were a useful tool for generating future rainfall.
No takes yet. Share an insight, caveat, or question.
Sarma et al. (2023) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: