An empirical investigation into predicting the volume of water accumulation in dams that supply the Metropolitan Region of Recife

• Rodolfo Amorim C. da Silva UPE
• Rodolfo Viegas de Albuquerque UPE
• Milton Tavares de Melo Neto UPE
• João Fausto Lorenzato de Oliveira UPE

DOI: https://doi.org/10.5753/eniac.2025.11789

Abstract

This article reports an empirical investigation on the prediction of the volume of water accumulated in dams, comparing the performance of traditional statistical methods, machine learning algorithms, and dynamic and static ensemble approaches, applied to volume time series, seeking to understand if there is any model that stands out from the others. The study showed that LSTM networks, isolated or used in ensemble, seem to be a sufficiently robust model to reproduce time series with a hydrological context.

References

APAC, A. P. d. e. C. (2015). Elaboração de Planos de Aproveitamento da Infraestrutura Hídrica do Semiárido - Diagnóstico da Situação Atual das Barragens e Reservatórios, volume 01 of Infraestrutura hídrica Semiárido. APAC, Agência Pernambucana de Águas e Clima, Recife/PE, Brasil.

de Geografia e Estatística IBGE, I. B. (2023). Mapeamento ibge - estado de pernambuco.

Dutta, A., Chakrabarti, A., and Gautam, J. (2020). Application of sarima for prediction of water storage levels for a metropolitan area: Chennai, a case study. In 2020 International Symposium on Advanced Electrical and Communication Technologies (ISAECT), pages 1–8. IEEE.

Fu, M., Fan, T., Ding, Z., Salih, S. Q., Al-Ansari, N., and Yaseen, Z. M. (2020). Deep learning data-intelligence model based on adjusted forecasting window scale: Application in daily streamflow simulation. IEEE Access, 8:32632–32651.

Ghimire, B. N. (2017). Application of arima model for river discharges analysis. Journal of Nepal Physical Society, 4(1):27.

Hai Yen, T. T., Xuan An, N., Dat, N. Q., and Solanki, V. K. (2021). Multi-input lstm for water level forecasting in black river at the border of vietnam-china. In 2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT), pages 1–5. IEEE.

Herbold, S. (2020). Autorank: A python package for automated ranking of classifiers. Journal of Open Source Software, 5(48):2173.

Hyndman, R. J. and Khandakar, Y. (2008). Automatic time series forecasting: The forecast package for r. Journal of Statistical Software, 27(3).

Hyndman, R. J. and Koehler, A. B. (2006). Another look at measures of forecast accuracy. International Journal of Forecasting, 22(4):679–688.

Lukas, P., Melesse, A. M., and Kenea, T. T. (2024). Predicting reservoir sedimentation using multilayer perceptron – artificial neural network model with measured and forecasted hydrometeorological data in gibe-iii reservoir, omo-gibe river basin, ethiopia. Journal of Environmental Management, 359:121018.

Raman, R. and Rathi, T. (2024). Efficient dam water level management using cloud-based data analytics and lstm networks. In 2024 11th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), pages 1–6. IEEE.

Reyes-Baeza, P., Trujillo-Guiñez, R., and Vidal, M. (2023). Long-term water level forecasting for el yeso reservoir using time-series data and satellite images. In 2023 42nd IEEE International Conference of the Chilean Computer Science Society (SCCC), pages 1–7. IEEE.

Sekban, J., Nabil, M. O. M., Alsan, H. F., and Arsan, T. (2022). Istanbul dam water levels forecasting using arima models. In 2022 Innovations in Intelligent Systems and Applications Conference (ASYU), pages 1–7. IEEE.

Velasco, L. C., Estose, A. J., Opon, M., Tabanao, E., and Apdian, F. (2024). Performance evaluation of support vector regression machine models in water level forecasting. Procedia Computer Science, 234:436–447.

Wang, Y., Zhou, J., Chen, K., Wang, Y., and Liu, L. (2017). Water quality prediction method based on lstm neural network. In 2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), pages 1–5. IEEE.

Water, U. W. (2019). The United Nations world water development report 2021: valuing water. Water Politics. UNESCO World Water Assessment Programmer.

Widiasari, I. R., Nugoho, L. E., Widyawan, and Efendi, R. (2018). Context-based hydrology time series data for a flood prediction model using lstm. In 2018 5th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), pages 385–390. IEEE.

Yang, C.-H., Wu, C.-H., and Hsieh, C.-M. (2020). Long short-term memory recurrent neural network for tidal level forecasting. IEEE Access, 8:159389–159401.

Yu, Z., Lei, G., Jiang, Z., and Liu, F. (2017). Arima modelling and forecasting of water level in the middle reach of the yangtze river. In 2017 4th International Conference on Transportation Information and Safety (ICTIS), pages 172–177. IEEE.

Zhou, T., Jiang, Z., Liu, X., and Tan, K. (2020). Research on the long-term and short-term forecasts of navigable river’s water-level fluctuation based on the adaptive multilayer perceptron. Journal of Hydrology, 591.