Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks

Tae Woong Kim, Juan B Valdes

Research output: Contribution to journalArticle

277 Citations (Scopus)

Abstract

Droughts are destructive climatic extreme events that may cause significant damage both in natural environments and in human lives. Drought forecasting plays an important role in the control and management of water resources systems. In this study, a conjunction model is presented to forecast droughts. The proposed conjunction model is based on dyadic wavelet transforms and neural networks. Neural networks have shown great ability in modeling and forecasting nonlinear and nonstationary time series in a water resources engineering, and wavelet transforms provide useful decompositions of an original time series. The wavelet-transformed data aid in improving the model performance by capturing helpful information on various resolution levels. Neural networks are used to forecast decomposed subsignals in various resolution levels and reconstruct forecasted subsignals. The model was applied to forecast droughts in the Conchos River Basin in Mexico, which is the most important tributary of the Lower Rio Grande/Bravo. The performance of the conjunction model was measured using various forecast skill criteria. The results indicate that the conjunction model significantly improves the ability of neural networks to forecast the indexed regional drought.

Original languageEnglish (US)
Pages (from-to)319-328
Number of pages10
JournalJournal of Hydrologic Engineering
Volume8
Issue number6
DOIs
StatePublished - Nov 2003

Fingerprint

Drought
Wavelet transforms
wavelet
transform
drought
Neural networks
tetrachloroisophthalonitrile
Water resources
Time series
water resource
time series
extreme event
Catchments
aid
tributary
river basin
Rivers
forecast
decomposition
Decomposition

Keywords

  • Droughts
  • Forecasting
  • Mexico
  • Models
  • Neural networks

ASJC Scopus subject areas

  • Environmental Science(all)
  • Environmental Chemistry
  • Water Science and Technology
  • Civil and Structural Engineering

Cite this

Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. / Kim, Tae Woong; Valdes, Juan B.

In: Journal of Hydrologic Engineering, Vol. 8, No. 6, 11.2003, p. 319-328.

Research output: Contribution to journalArticle

@article{90919fd90621409d89e2faba0f13dbb7,
title = "Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks",
abstract = "Droughts are destructive climatic extreme events that may cause significant damage both in natural environments and in human lives. Drought forecasting plays an important role in the control and management of water resources systems. In this study, a conjunction model is presented to forecast droughts. The proposed conjunction model is based on dyadic wavelet transforms and neural networks. Neural networks have shown great ability in modeling and forecasting nonlinear and nonstationary time series in a water resources engineering, and wavelet transforms provide useful decompositions of an original time series. The wavelet-transformed data aid in improving the model performance by capturing helpful information on various resolution levels. Neural networks are used to forecast decomposed subsignals in various resolution levels and reconstruct forecasted subsignals. The model was applied to forecast droughts in the Conchos River Basin in Mexico, which is the most important tributary of the Lower Rio Grande/Bravo. The performance of the conjunction model was measured using various forecast skill criteria. The results indicate that the conjunction model significantly improves the ability of neural networks to forecast the indexed regional drought.",
keywords = "Droughts, Forecasting, Mexico, Models, Neural networks",
author = "Kim, {Tae Woong} and Valdes, {Juan B}",
year = "2003",
month = "11",
doi = "10.1061/(ASCE)1084-0699(2003)8:6(319)",
language = "English (US)",
volume = "8",
pages = "319--328",
journal = "Journal of Hydrologic Engineering - ASCE",
issn = "1084-0699",
publisher = "American Society of Civil Engineers (ASCE)",
number = "6",

}

TY - JOUR

T1 - Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks

AU - Kim, Tae Woong

AU - Valdes, Juan B

PY - 2003/11

Y1 - 2003/11

N2 - Droughts are destructive climatic extreme events that may cause significant damage both in natural environments and in human lives. Drought forecasting plays an important role in the control and management of water resources systems. In this study, a conjunction model is presented to forecast droughts. The proposed conjunction model is based on dyadic wavelet transforms and neural networks. Neural networks have shown great ability in modeling and forecasting nonlinear and nonstationary time series in a water resources engineering, and wavelet transforms provide useful decompositions of an original time series. The wavelet-transformed data aid in improving the model performance by capturing helpful information on various resolution levels. Neural networks are used to forecast decomposed subsignals in various resolution levels and reconstruct forecasted subsignals. The model was applied to forecast droughts in the Conchos River Basin in Mexico, which is the most important tributary of the Lower Rio Grande/Bravo. The performance of the conjunction model was measured using various forecast skill criteria. The results indicate that the conjunction model significantly improves the ability of neural networks to forecast the indexed regional drought.

AB - Droughts are destructive climatic extreme events that may cause significant damage both in natural environments and in human lives. Drought forecasting plays an important role in the control and management of water resources systems. In this study, a conjunction model is presented to forecast droughts. The proposed conjunction model is based on dyadic wavelet transforms and neural networks. Neural networks have shown great ability in modeling and forecasting nonlinear and nonstationary time series in a water resources engineering, and wavelet transforms provide useful decompositions of an original time series. The wavelet-transformed data aid in improving the model performance by capturing helpful information on various resolution levels. Neural networks are used to forecast decomposed subsignals in various resolution levels and reconstruct forecasted subsignals. The model was applied to forecast droughts in the Conchos River Basin in Mexico, which is the most important tributary of the Lower Rio Grande/Bravo. The performance of the conjunction model was measured using various forecast skill criteria. The results indicate that the conjunction model significantly improves the ability of neural networks to forecast the indexed regional drought.

KW - Droughts

KW - Forecasting

KW - Mexico

KW - Models

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=0344121593&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0344121593&partnerID=8YFLogxK

U2 - 10.1061/(ASCE)1084-0699(2003)8:6(319)

DO - 10.1061/(ASCE)1084-0699(2003)8:6(319)

M3 - Article

AN - SCOPUS:0344121593

VL - 8

SP - 319

EP - 328

JO - Journal of Hydrologic Engineering - ASCE

JF - Journal of Hydrologic Engineering - ASCE

SN - 1084-0699

IS - 6

ER -