A neural network approach to local downscaling of GCM output for assessing wind power implications of climate change

David Sailor, T. Hu, X. Li, J. N. Rosen

Research output: Contribution to journalArticle

62 Citations (Scopus)

Abstract

A methodology is presented for downscaling General Circulation Model (GCM) output to predict surface wind speeds at scales of interest in the wind power industry under expected future climatic conditions. The approach involves a combination of Neural Network tools and traditional weather forecasting techniques. A Neural Network transfer function is developed to relate local wind speed observations to large scale GCM predictions of atmospheric properties under current climatic conditions. By assuming the invariability of this transfer function under conditions of doubled atmospheric carbon dioxide, the resulting transfer function is then applied to GCM output for a transient run of the National Center for Atmospheric Research coupled ocean-atmosphere GCM. This methodology is applied to three test sites in regions relevant to the wind power industry-one in Texas and two in California. Changes in daily mean wind speeds at each location are presented and discussed with respect to potential implications for wind power generation.

Original languageEnglish (US)
Pages (from-to)359-378
Number of pages20
JournalRenewable Energy
Volume19
Issue number3
DOIs
StatePublished - 2000
Externally publishedYes

Fingerprint

Climate change
Wind power
Neural networks
Transfer functions
Weather forecasting
Power generation
Industry
Carbon dioxide

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment

Cite this

A neural network approach to local downscaling of GCM output for assessing wind power implications of climate change. / Sailor, David; Hu, T.; Li, X.; Rosen, J. N.

In: Renewable Energy, Vol. 19, No. 3, 2000, p. 359-378.

Research output: Contribution to journalArticle

@article{b6d308403c454371955773a7f5d00e90,
title = "A neural network approach to local downscaling of GCM output for assessing wind power implications of climate change",
abstract = "A methodology is presented for downscaling General Circulation Model (GCM) output to predict surface wind speeds at scales of interest in the wind power industry under expected future climatic conditions. The approach involves a combination of Neural Network tools and traditional weather forecasting techniques. A Neural Network transfer function is developed to relate local wind speed observations to large scale GCM predictions of atmospheric properties under current climatic conditions. By assuming the invariability of this transfer function under conditions of doubled atmospheric carbon dioxide, the resulting transfer function is then applied to GCM output for a transient run of the National Center for Atmospheric Research coupled ocean-atmosphere GCM. This methodology is applied to three test sites in regions relevant to the wind power industry-one in Texas and two in California. Changes in daily mean wind speeds at each location are presented and discussed with respect to potential implications for wind power generation.",
author = "David Sailor and T. Hu and X. Li and Rosen, {J. N.}",
year = "2000",
doi = "10.1016/S0960-1481(99)00056-7",
language = "English (US)",
volume = "19",
pages = "359--378",
journal = "Renewable Energy",
issn = "0960-1481",
publisher = "Elsevier BV",
number = "3",

}

TY - JOUR

T1 - A neural network approach to local downscaling of GCM output for assessing wind power implications of climate change

AU - Sailor, David

AU - Hu, T.

AU - Li, X.

AU - Rosen, J. N.

PY - 2000

Y1 - 2000

N2 - A methodology is presented for downscaling General Circulation Model (GCM) output to predict surface wind speeds at scales of interest in the wind power industry under expected future climatic conditions. The approach involves a combination of Neural Network tools and traditional weather forecasting techniques. A Neural Network transfer function is developed to relate local wind speed observations to large scale GCM predictions of atmospheric properties under current climatic conditions. By assuming the invariability of this transfer function under conditions of doubled atmospheric carbon dioxide, the resulting transfer function is then applied to GCM output for a transient run of the National Center for Atmospheric Research coupled ocean-atmosphere GCM. This methodology is applied to three test sites in regions relevant to the wind power industry-one in Texas and two in California. Changes in daily mean wind speeds at each location are presented and discussed with respect to potential implications for wind power generation.

AB - A methodology is presented for downscaling General Circulation Model (GCM) output to predict surface wind speeds at scales of interest in the wind power industry under expected future climatic conditions. The approach involves a combination of Neural Network tools and traditional weather forecasting techniques. A Neural Network transfer function is developed to relate local wind speed observations to large scale GCM predictions of atmospheric properties under current climatic conditions. By assuming the invariability of this transfer function under conditions of doubled atmospheric carbon dioxide, the resulting transfer function is then applied to GCM output for a transient run of the National Center for Atmospheric Research coupled ocean-atmosphere GCM. This methodology is applied to three test sites in regions relevant to the wind power industry-one in Texas and two in California. Changes in daily mean wind speeds at each location are presented and discussed with respect to potential implications for wind power generation.

UR - http://www.scopus.com/inward/record.url?scp=0343384269&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0343384269&partnerID=8YFLogxK

U2 - 10.1016/S0960-1481(99)00056-7

DO - 10.1016/S0960-1481(99)00056-7

M3 - Article

VL - 19

SP - 359

EP - 378

JO - Renewable Energy

JF - Renewable Energy

SN - 0960-1481

IS - 3

ER -