Research Article
Water Level Forecasting in Reservoirs Using Time Series Analysis – Auto ARIMA Model
@INPROCEEDINGS{10.1007/978-3-031-28975-0_16, author={Avinash Reddy Kovvuri and Padma Jyothi Uppalapati and Sridevi Bonthu and Narasimha Rao Kandula}, title={Water Level Forecasting in Reservoirs Using Time Series Analysis -- Auto ARIMA Model}, proceedings={Cognitive Computing and Cyber Physical Systems. Third EAI International Conference, IC4S 2022, Virtual Event, November 26-27, 2022, Proceedings}, proceedings_a={IC4S}, year={2023}, month={3}, keywords={Water Level Forecasting ARIMA Time Series Analysis Auto ARIMA}, doi={10.1007/978-3-031-28975-0_16} }- Avinash Reddy Kovvuri
Padma Jyothi Uppalapati
Sridevi Bonthu
Narasimha Rao Kandula
Year: 2023
Water Level Forecasting in Reservoirs Using Time Series Analysis – Auto ARIMA Model
IC4S
Springer
DOI: 10.1007/978-3-031-28975-0_16
Abstract
Forecasting the upcoming water level of a dam or reservoir is the goal of water level forecasting in reservoirs. In order to predict the water level of the dam or reservoir for the subsequent consecutive time interval, this paper proposes a method based on the ARIMA (Auto Regressive Integrated Moving Averages) machine learning model, which fed on historical data of water levels with respect to consecutive time intervals. Additionally, the anticipated output, whether it be in TMC or MFTC units, is depending on the data that is given. The model’s performance is further examined in the study using certain machine learning metrics.
Copyright © 2022–2025 ICST
