eprintid: 17117
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/71/17
datestamp: 2023-12-19 03:23:34
lastmod: 2023-12-19 03:23:34
status_changed: 2023-12-19 03:07:29
type: article
metadata_visibility: show
creators_name: Azad, A.S.
creators_name: Sokkalingam, R.
creators_name: Daud, H.
creators_name: Adhikary, S.K.
creators_name: Khurshid, H.
creators_name: Mazlan, S.N.A.
creators_name: Rabbani, M.B.A.
title: Water Level Prediction through Hybrid SARIMA and ANN Models Based on Time Series Analysis: Red Hills Reservoir Case Study
ispublished: pub
keywords: artificial neural network; climate change; hydrological modeling; prediction; reservoir; seasonal variation; time series analysis; water level; water supply, India; Tamil Nadu; Tiruvallur
note: cited By 32
abstract: Reservoir water level (RWL) prediction has become a challenging task due to spatiotemporal changes in climatic conditions and complicated physical process. The Red Hills Reservoir (RHR) is an important source of drinking and irrigation water supply in Thiruvallur district, Tamil Nadu, India, also expected to be converted into the other productive services in the future. However, climate change in the region is expected to have consequences over the RHR�s future prospects. As a result, accurate and reliable prediction of the RWL is crucial to develop an appropriate water release mechanism of RHR to satisfy the population�s water demand. In the current study, time series modelling technique was adopted for the RWL prediction in RHR using Box�Jenkins autoregressive seasonal autoregressive integrated moving average (SARIMA) and artificial neural network (ANN) hybrid models. In this research, the SARIMA model was obtained as SARIMA (0, 0, 1) (0, 3, 2)12 but the residual of the SARIMA model could not meet the autocorrelation requirement of the modelling approach. In order to overcome this weakness of the SARIMA model, a new SARIMA�ANN hybrid time series model was developed and demonstrated in this study. The average monthly RWL data from January 2004 to November 2020 was used for developing and testing the models. Several model assessment criteria were used to evaluate the performance of each model. The findings showed that the SARIMA�ANN hybrid model outperformed the remaining models considering all performance criteria for reservoir RWL prediction. Thus, this study conclusively proves that the SARIMA�ANN hybrid model could be a viable option for the accurate prediction of reservoir water level. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
date: 2022
publisher: MDPI
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124068728&doi=10.3390%2fsu14031843&partnerID=40&md5=a8543a1cb1c902703d188d610a0270d4
id_number: 10.3390/su14031843
full_text_status: none
publication: Sustainability (Switzerland)
volume: 14
number: 3
refereed: TRUE
issn: 20711050
citation:   Azad, A.S. and Sokkalingam, R. and Daud, H. and Adhikary, S.K. and Khurshid, H. and Mazlan, S.N.A. and Rabbani, M.B.A.  (2022) Water Level Prediction through Hybrid SARIMA and ANN Models Based on Time Series Analysis: Red Hills Reservoir Case Study.  Sustainability (Switzerland), 14 (3).   ISSN 20711050