One Day Ahead Stream Flow Forecasting

DOI

10.2991/ifsa-eusflat-15.2015.165How to use a DOI?

Keywords

Stream flow forecasting, One step-ahead forecasting, ANFIS, Artificial Neural Networks, Support Vector Machines.

Abstract

Short-term stream flow forecasts are required for simulation, optimization, and decision-making purposes in applications ranging from hydropower planning to flood prevention. The particular case of one-day ahead stream flow forecasting is an important but difficult problem that has been increasingly studied using hybrid computational intelligence and machine learning techniques. However, these studies present several limitations. In this work we attempt to address those limitations by (1) replicating and validating previous works; (2) using more objective evaluation criteria; (3) applying several computational intelligence techniques to datasets representative of diverse geographic areas; (4) preprocessing data and performing an extensive parameter optimization in order to improve previous results.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Joao P. Carvalho
AU  - Filipe V. Camelo
PY  - 2015/06
DA  - 2015/06
TI  - One Day Ahead Stream Flow Forecasting
BT  - Proceedings of the 2015 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and Technology
PB  - Atlantis Press
SP  - 1168
EP  - 1175
SN  - 1951-6851
UR  - https://doi.org/10.2991/ifsa-eusflat-15.2015.165
DO  - 10.2991/ifsa-eusflat-15.2015.165
ID  - Carvalho2015/06
ER  -