An artificial neural network technique for downscaling GCM outputs to RCM spatial scale
An Artificial Neural Network (ANN) approach is used to downscale ECHAM5 GCM temperature (<i>T</i>) and rainfall (<i>R</i>) fields to RegCM3 regional model scale over Europe. The main inputs to the neural network were the ECHAM5 fields and topog...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2011-12-01
|
| Series: | Nonlinear Processes in Geophysics |
| Online Access: | http://www.nonlin-processes-geophys.net/18/1013/2011/npg-18-1013-2011.pdf |
| _version_ | 1819044308081180672 |
|---|---|
| author | R. Chadwick E. Coppola F. Giorgi |
| author_facet | R. Chadwick E. Coppola F. Giorgi |
| author_sort | R. Chadwick |
| collection | DOAJ |
| description | An Artificial Neural Network (ANN) approach is used to downscale ECHAM5 GCM temperature (<i>T</i>) and rainfall (<i>R</i>) fields to RegCM3 regional model scale over Europe. The main inputs to the neural network were the ECHAM5 fields and topography, and RegCM3 topography. An ANN trained for the period 1960–1980 was able to recreate the RegCM3 1981–2000 mean <i>T</i> and <i>R</i> fields with reasonable accuracy. The ANN showed an improvement over a simple lapse-rate correction method for <i>T</i>, although the ANN <i>R</i> field did not capture all the fine-scale detail of the RCM field. An ANN trained over a smaller area of Southern Europe was able to capture this detail with more precision. The ANN was unable to accurately recreate the RCM climate change (CC) signal between 1981–2000 and 2081–2100, and it is suggested that this is because the relationship between the GCM fields, RCM fields and topography is not constant with time and changing climate. An ANN trained with three ten-year "time-slices" was able to better reproduce the RCM CC signal, particularly for the full European domain. This approach shows encouraging results but will need further refinement before becoming a viable supplement to dynamical regional climate modelling of temperature and rainfall. |
| first_indexed | 2024-12-21T10:10:37Z |
| format | Article |
| id | doaj.art-9e4ecc1c0a384f54bf8e948153135a9b |
| institution | Directory Open Access Journal |
| issn | 1023-5809 1607-7946 |
| language | English |
| last_indexed | 2024-12-21T10:10:37Z |
| publishDate | 2011-12-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Nonlinear Processes in Geophysics |
| spelling | doaj.art-9e4ecc1c0a384f54bf8e948153135a9b2022-12-21T19:07:44ZengCopernicus PublicationsNonlinear Processes in Geophysics1023-58091607-79462011-12-011861013102810.5194/npg-18-1013-2011An artificial neural network technique for downscaling GCM outputs to RCM spatial scaleR. ChadwickE. CoppolaF. GiorgiAn Artificial Neural Network (ANN) approach is used to downscale ECHAM5 GCM temperature (<i>T</i>) and rainfall (<i>R</i>) fields to RegCM3 regional model scale over Europe. The main inputs to the neural network were the ECHAM5 fields and topography, and RegCM3 topography. An ANN trained for the period 1960–1980 was able to recreate the RegCM3 1981–2000 mean <i>T</i> and <i>R</i> fields with reasonable accuracy. The ANN showed an improvement over a simple lapse-rate correction method for <i>T</i>, although the ANN <i>R</i> field did not capture all the fine-scale detail of the RCM field. An ANN trained over a smaller area of Southern Europe was able to capture this detail with more precision. The ANN was unable to accurately recreate the RCM climate change (CC) signal between 1981–2000 and 2081–2100, and it is suggested that this is because the relationship between the GCM fields, RCM fields and topography is not constant with time and changing climate. An ANN trained with three ten-year "time-slices" was able to better reproduce the RCM CC signal, particularly for the full European domain. This approach shows encouraging results but will need further refinement before becoming a viable supplement to dynamical regional climate modelling of temperature and rainfall.http://www.nonlin-processes-geophys.net/18/1013/2011/npg-18-1013-2011.pdf |
| spellingShingle | R. Chadwick E. Coppola F. Giorgi An artificial neural network technique for downscaling GCM outputs to RCM spatial scale Nonlinear Processes in Geophysics |
| title | An artificial neural network technique for downscaling GCM outputs to RCM spatial scale |
| title_full | An artificial neural network technique for downscaling GCM outputs to RCM spatial scale |
| title_fullStr | An artificial neural network technique for downscaling GCM outputs to RCM spatial scale |
| title_full_unstemmed | An artificial neural network technique for downscaling GCM outputs to RCM spatial scale |
| title_short | An artificial neural network technique for downscaling GCM outputs to RCM spatial scale |
| title_sort | artificial neural network technique for downscaling gcm outputs to rcm spatial scale |
| url | http://www.nonlin-processes-geophys.net/18/1013/2011/npg-18-1013-2011.pdf |
| work_keys_str_mv | AT rchadwick anartificialneuralnetworktechniquefordownscalinggcmoutputstorcmspatialscale AT ecoppola anartificialneuralnetworktechniquefordownscalinggcmoutputstorcmspatialscale AT fgiorgi anartificialneuralnetworktechniquefordownscalinggcmoutputstorcmspatialscale AT rchadwick artificialneuralnetworktechniquefordownscalinggcmoutputstorcmspatialscale AT ecoppola artificialneuralnetworktechniquefordownscalinggcmoutputstorcmspatialscale AT fgiorgi artificialneuralnetworktechniquefordownscalinggcmoutputstorcmspatialscale |