Advanced

Impact of complexity on daily and multi-step forecasting of streamflow with chaotic, stochastic, and black-box models

Tongal, Hakan and Berndtsson, Ronny LU (2016) In Stochastic Environmental Research and Risk Assessment p.1-22
Abstract

Despite significant research advances achieved during the last decades, seemingly inconsistent forecasting results related to stochastic, chaotic, and black-box approaches have been reported. Herein, we attempt to address the entropy/complexity resulting from hydrological and climatological conditions. Accordingly, mutual information function, correlation dimension, averaged false nearest neighbor with E1 and E2 quantities, and complexity analysis that uses sample entropy coupled with iterative amplitude adjusted Fourier transform were employed as nonlinear deterministic identification tools. We investigated forecasting of daily streamflow for three climatologically different Swedish rivers, Helge, Ljusnan, and Kalix Rivers using... (More)

Despite significant research advances achieved during the last decades, seemingly inconsistent forecasting results related to stochastic, chaotic, and black-box approaches have been reported. Herein, we attempt to address the entropy/complexity resulting from hydrological and climatological conditions. Accordingly, mutual information function, correlation dimension, averaged false nearest neighbor with E1 and E2 quantities, and complexity analysis that uses sample entropy coupled with iterative amplitude adjusted Fourier transform were employed as nonlinear deterministic identification tools. We investigated forecasting of daily streamflow for three climatologically different Swedish rivers, Helge, Ljusnan, and Kalix Rivers using self-exciting threshold autoregressive (SETAR), k-nearest neighbor (k-nn), and artificial neural networks (ANN). The results suggest that the streamflow in these rivers during the 1957–2012 period exhibited dynamics from low to high complexity. Specifically, (1) lower complexity lead to higher predictability at all lead-times and the models’ worst performances were obtained for the most complex streamflow (Ljusnan River), (2) ANN was the best model for 1-day ahead forecasting independent of complexity, (3) SETAR was the best model for 7-day ahead forecasting by means of performance indices, especially for less complexity, (4) the largest error propagation was obtained with the k-nn and ANN and thus these models should be carefully used beyond 2-day forecasting, and (5) higher number input variables except for the dominant variables made insignificant impact on forecasting performances for ANN and k-nn models.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
epub
subject
keywords
Artificial neural networks, Averaged false nearest neighbor (AFN), Correlation dimension, k-Nearest neighbor, Sample entropy, Self-exciting threshold autoregressive
in
Stochastic Environmental Research and Risk Assessment
pages
22 pages
publisher
Springer
external identifiers
  • scopus:84961131314
  • wos:000398003000005
ISSN
1436-3240
DOI
10.1007/s00477-016-1236-4
language
English
LU publication?
yes
id
f1ecc1cb-e9c3-45c2-bae4-f130c1f4c843
date added to LUP
2017-02-09 09:47:32
date last changed
2017-09-18 11:37:41
@article{f1ecc1cb-e9c3-45c2-bae4-f130c1f4c843,
  abstract     = {<p>Despite significant research advances achieved during the last decades, seemingly inconsistent forecasting results related to stochastic, chaotic, and black-box approaches have been reported. Herein, we attempt to address the entropy/complexity resulting from hydrological and climatological conditions. Accordingly, mutual information function, correlation dimension, averaged false nearest neighbor with E1 and E2 quantities, and complexity analysis that uses sample entropy coupled with iterative amplitude adjusted Fourier transform were employed as nonlinear deterministic identification tools. We investigated forecasting of daily streamflow for three climatologically different Swedish rivers, Helge, Ljusnan, and Kalix Rivers using self-exciting threshold autoregressive (SETAR), k-nearest neighbor (k-nn), and artificial neural networks (ANN). The results suggest that the streamflow in these rivers during the 1957–2012 period exhibited dynamics from low to high complexity. Specifically, (1) lower complexity lead to higher predictability at all lead-times and the models’ worst performances were obtained for the most complex streamflow (Ljusnan River), (2) ANN was the best model for 1-day ahead forecasting independent of complexity, (3) SETAR was the best model for 7-day ahead forecasting by means of performance indices, especially for less complexity, (4) the largest error propagation was obtained with the k-nn and ANN and thus these models should be carefully used beyond 2-day forecasting, and (5) higher number input variables except for the dominant variables made insignificant impact on forecasting performances for ANN and k-nn models.</p>},
  author       = {Tongal, Hakan and Berndtsson, Ronny},
  issn         = {1436-3240},
  keyword      = {Artificial neural networks,Averaged false nearest neighbor (AFN),Correlation dimension,k-Nearest neighbor,Sample entropy,Self-exciting threshold autoregressive},
  language     = {eng},
  month        = {03},
  pages        = {1--22},
  publisher    = {Springer},
  series       = {Stochastic Environmental Research and Risk Assessment},
  title        = {Impact of complexity on daily and multi-step forecasting of streamflow with chaotic, stochastic, and black-box models},
  url          = {http://dx.doi.org/10.1007/s00477-016-1236-4},
  year         = {2016},
}