Bias correction of global circulation model outputs using artificial neural networks

dc.contributor.advisor Bras, Rafael L.
dc.contributor.advisor Georgakakos, Aristidis P.
dc.contributor.advisor Wang, Jingfeng
dc.contributor.advisor Hsu, Kuo-lin
dc.contributor.advisor Deng, Yi
dc.contributor.author Moghim, Sanaz
dc.contributor.department Civil and Environmental Engineering
dc.date.accessioned 2016-08-22T12:19:35Z
dc.date.available 2016-08-22T12:19:35Z
dc.date.created 2015-08
dc.date.issued 2015-05-01
dc.date.submitted August 2015
dc.date.updated 2016-08-22T12:19:35Z
dc.description.abstract Climate studies and effective environmental management plans require unbiased climate datasets. This study develops a new bias correction approach using a three layer feedforward neural network to reduce the biases of climate variables (temperature and precipitation) over northern South America. Air and skin temperature, specific humidity, net longwave and shortwave radiation are used as inputs for the bias correction of temperature. Precipitation at lag zero, one, two, and three, and the standard deviation from 3 by 3 neighbors around the pixel of interest are the inputs into the ANN bias correction of precipitation. The data are provided by the Community Climate System Model (CCSM3). Results show that the trained ANN can markedly reduce the estimation error and improve the correlation and probabilistic structure of the bias-corrected variables for calibration and validation periods. The ANN outperforms linear regression (LR), which is used for comparison purposes. The ability of the regression models (linear and ANN) to regionalize the study domain is investigated by defining the minimum number of training pixels necessary to achieve a good level of bias correction performance over the entire domain. Results confirm that it is possible to identify regions in terms of physical features such as land cover, topography, and climatology over which the trained models at a few pixels can do well. The new approach saves computational demands, time, and memory usage and it can be used for other climate models efficiently.
dc.description.degree Ph.D.
dc.format.mimetype application/pdf
dc.identifier.uri http://hdl.handle.net/1853/55487
dc.language.iso en_US
dc.publisher Georgia Institute of Technology
dc.subject Bias correction
dc.subject Regression models
dc.subject Artificial neural networks
dc.subject Generalization
dc.subject Regionalization
dc.subject Community climate system model
dc.subject Climate data sets
dc.title Bias correction of global circulation model outputs using artificial neural networks
dc.type Text
dc.type.genre Dissertation
dspace.entity.type Publication
local.contributor.advisor Wang, Jingfeng
local.contributor.advisor Bras, Rafael L.
local.contributor.advisor Deng, Yi
local.contributor.advisor Georgakakos, Aristidis P.
local.contributor.corporatename School of Civil and Environmental Engineering
local.contributor.corporatename College of Engineering
relation.isAdvisorOfPublication 46a4e691-2214-4ba6-bff3-7f1f0bf292d8
relation.isAdvisorOfPublication 64e45b8f-3df1-4e41-84d2-0cd91b9a0d61
relation.isAdvisorOfPublication 70fb52a8-0735-4585-b69b-4ef5b24f4f5a
relation.isAdvisorOfPublication ec69ec36-b20e-4231-be3e-cfe0dd51ea86
relation.isOrgUnitOfPublication 88639fad-d3ae-4867-9e7a-7c9e6d2ecc7c
relation.isOrgUnitOfPublication 7c022d60-21d5-497c-b552-95e489a06569
thesis.degree.level Doctoral
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
5.7 MB
Adobe Portable Document Format
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
3.86 KB
Plain Text
No Thumbnail Available
3.86 KB
Plain Text