A water level prediction using ARMA and ARIMA models: a case study of the river Niger

Flooding is one of the most frequently occurring natural hazards globally, studies on how to reduce or prevent this extreme event were carried out using various approaches. Recent studies proposed water level forecast as an important technique which provides effective water resources management and prevent flood disasters. In this article, we propose a novel approach to predict monthly water level discharges between (2010-2016), the data were collected from Nigeria Hydrological Services Agency for three different water stations along river Niger, namely Baro, Jebba and Kainji water stations using Autoregressive Moving Averages (ARMA) and Autoregressive Integrated Moving Averages (ARIMA) models. The performance of these time series models were tested using three different performance measures including mean absolute error, root mean square error and Nash Sutcliffe efficiency to find appropriate model which will be utilise to predict the water level discharges from the three water stations, this will provides information to the populace of what to expect in future to mitigate the impact of flood disasters when it occurs, some descriptive statistics were also presented.