@inproceedings{scholars17429,
         journal = {4th IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2022},
       publisher = {Institute of Electrical and Electronics Engineers Inc.},
           title = {Application Water Level Prediction Through Seasonal Autoregressive Integrated Moving Average: Red Hills Reservoir Case Study},
            note = {cited By 0; Conference of 4th IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2022 ; Conference Date: 13 September 2022 Through 15 September 2022; Conference Code:184212},
            year = {2022},
             doi = {10.1109/IICAIET55139.2022.9936784},
          author = {Azad, A. S. and Sokkalingam, R. and Daud, H. and Adhikary, S. K.},
            isbn = {9781665468374},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85142280202&doi=10.1109\%2fIICAIET55139.2022.9936784&partnerID=40&md5=b4d160d65b4df7aa17e9ab7d03fd2def},
        keywords = {Climate change; Mean square error; Reservoirs (water); Time series; Water levels, Auto-regressive; Autoregressive integrated moving average; Moving average model; Moving averages; Red Hills; Reservoir water level; Seasonal autoregressive integrated moving averages; Seasonality; Times series; Water level prediction, Forecasting},
        abstract = {Predicting water levels has become difficult because of spatiotemporal variations in meteorological circumstances and complex physical processes. The Red Hill Reservoir (RHR) serves as an essential derivation of the water system in its locality. It is also anticipated that it would be transformed into other useful services. Climate change in the region, on the other hand, is predicted to have an impact on the RHR's prospects. In a nutshell, accurate water level forecasting is crucial for the reservoir to meet the needs of the population. In this paper, the time series modeling technique is suggested for the water level prediction in RHR using Box-Jenkins autoregressive integrated moving average (ARIMA) and seasonal autoregressive integrated moving average (SARIMA) models. The models were trained using average monthly water level data from January 2004 to November 2020. The models' performance was analysed with the Akaike information criterion (AIC), mean absolute error (MAE), root mean square error (RMSE), and correlation coefficient (R2). The results revealed that among the models, the SARIMA model performed better than the ARIMA model. The selected SARIMA model was further used for forecasting the water level in RHR for 25 months starting from December 2020 to December 2022. The model well predicted the future reservoir levels data. {\^A}{\copyright} 2022 IEEE.}
}