Performance evaluation of artificial neural networks in statistical downscaling of monthly precipitation (Case study: Minab watershed)
Assessment of the impacts of climate change on water resources has been obtainedsignificant attentions in the past decade. This paper assesses the climate change impacts onprecipitation in the Minab basin, in the Hormozgan province in Iran. Two monthlyprecipitation downscaling methods were proposed...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Gorgan University of Agricultural Sciences and Natural Resources
2017-07-01
|
| Series: | Environmental Resources Research |
| Subjects: | |
| Online Access: | https://ijerr.gau.ac.ir/article_3874_c322607129e6effb79e94ae0b2691445.pdf |
| Summary: | Assessment of the impacts of climate change on water resources has been obtainedsignificant attentions in the past decade. This paper assesses the climate change impacts onprecipitation in the Minab basin, in the Hormozgan province in Iran. Two monthlyprecipitation downscaling methods were proposed based on multi-layer perceptron (MLP)and radial basis function (RBF) neural networks. The downscaling models were calibratedand validated using the large scale climatic parameters (predictors) derived from NationalCenter for Environmental Prediction (NCEP)/ National Centre for Atmospheric Research(NCAR) reanalysis data set for downscaling monthly precipitation in the Minab basin inIran. Pearson correlation was employed to choose the predictors among the NCEP/ NCARreanalysis data set and final predictor combination for each station is assigned. The resultsof the downscaling models revealed that the MLP model produced more accurate andconsistent results by downscaling the large scale climatic parameters compared to the RBFmodel. The proposed model can be reliably utilized for developing future projections ofprecipitation using the general circulation models outputs which can be employed also asthe inputs in hydrological models. |
|---|---|
| ISSN: | 2783-4832 2783-4670 |