Author(s): Sungwon Kim; Minsoo Kyoung; Byung Sik Kim; Hung Soo Kim

Linked Author(s): Sungwon Kim

Keywords: Downscaling; Neural networks model; Climate change; Point precipitation

Abstract: The research of climate change impact in hydrometeorology often relies on climate change information. In this paper, neural networks models such as generalized regression neural networks model (GRNNM) and multilayer perceptron neural networks model (MLPNNM) are proposed for the statistical downscaling of point precipitation at daily time scale. The input nodes of neural networks models consist of the atmospheric meteorology and the atmospheric pressure data for 4 grid points including 127.5°E/37.5°N, 127.5°E/35°N, 125°E/37.5°N, and 125°E/35°N, respectively. The output node of neural networks models consist of the daily point precipitation data for Seoul station. For the performances of the neural networks models, they are composed of the training and the testing data, respectively. From this research, we evaluate the impact of GRNNM and MLP-NNM performances for the downscaling of the daily point precipitation data. We should, therefore, construct the credible daily point precipitation data for Seoul station using statistical downscaling method. The proposed methods can be applied to future climate prediction/projection using the various climate change scenarios such as GCMs and RCMs.

DOI:

Year: 2009