<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Several activities regarding water resources management are dependent on accurate monthly streamflow forecasting, such as flood control, reservoir operation, water supply planning, hydropower generation, energy matrix planning, among others. Most of the literature is focused on propose, compare, and evaluate the forecasting models. However, the decision on forecasting approaches plays a significant role in such models’ performance. In this paper, we are focused on investigating and confront the following forecasting approaches: i) use of a single model for the whole series (annual approach) versus using 12 models, each one responsible for predicting each month (monthly approach); ii) for multistep forecasting, the use of direct and recursive methods. The forecasting models addressed are the linear Autoregressive (AR) and Periodic Autoregressive (PAR) models, from the Box &amp; Jenkins family, and the Extreme Learning Machines (ELM), an artificial neural network architecture. The computational analysis involves 20 time series associated with hydroelectric plants indicated that the monthly approach with the direct multistep method achieved the best overall performances, except for the cases in which the coefficient of variation is higher than two. In this case, the recursive approach stood out. Also, the ELM overcame the linear models in most cases.</p>
</abstract>

Several activities regarding water resources management are dependent on accurate monthly streamflow forecasting, such as flood control, reservoir operation, water supply planning, hydropower generation, energy matrix planning, among others. Most of the literature is focused on propose, compare, and evaluate the forecasting models. However, the decision on forecasting approaches plays a significant role in such models’ performance. In this paper, we are focused on investigating and confront the following forecasting approaches: i) use of a single model for the whole series (annual approach) versus using 12 models, each one responsible for predicting each month (monthly approach); ii) for multistep forecasting, the use of direct and recursive methods. The forecasting models addressed are the linear Autoregressive (AR) and Periodic Autoregressive (PAR) models, from the Box & Jenkins family, and the Extreme Learning Machines (ELM), an artificial neural network architecture. The computational analysis involves 20 time series associated with hydroelectric plants indicated that the monthly approach with the direct multistep method achieved the best overall performances, except for the cases in which the coefficient of variation is higher than two. In this case, the recursive approach stood out. Also, the ELM overcame the linear models in most cases.

Comparative study of forecasting approaches in monthly streamflow series from Brazilian hydroelectric plants using Extreme Learning Machines and Box &amp; Jenkins models

Federal University of Technology – Paraná (UTFPR), Rua Doutor Washington Subtil Chueire

Journal of Hydrology and Hydromechanics

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Comparative study of forecasting approaches in monthly streamflow series from Brazilian hydroelectric plants using Extreme Learning Machines and Box & Jenkins models

Several activities regarding water resources management are dependent on accurate monthly streamflow forecasting, such as flood control, reservoir operation,...

Comparative study of forecasting approaches in monthly streamflow series from Brazilian hydroelectric plants using Extreme Learning Machines and Box & Jenkins models

Publié en ligne: 21 mai 2021

Pages: 180 - 195

Reçu: 24 mars 2020

Accepté: 29 nov. 2020

DOI: https://doi.org/10.2478/johh-2021-0001

Mots clés
Streamflow series prediction, Multistep forecasting, Monthly approach, Box & Jenkins models, Extreme Learning Machines

© 2021 Jonatas Belotti et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Comparative study of forecasting approaches in monthly streamflow series from Brazilian hydroelectric plants using Extreme Learning Machines and Box & Jenkins models

Publié en ligne: 21 mai 2021

Pages: 180 - 195

Reçu: 24 mars 2020

Accepté: 29 nov. 2020

DOI: https://doi.org/10.2478/johh-2021-0001

Mots clésStreamflow series prediction, Multistep forecasting, Monthly approach, Box & Jenkins models, Extreme Learning Machines

© 2021 Jonatas Belotti et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Mots clés
Streamflow series prediction, Multistep forecasting, Monthly approach, Box & Jenkins models, Extreme Learning Machines