Neural Networks for rainfall forecasting by atmospheric downscaling

Summary, in English

Several studies have used artificial neural networks (NNs) to estimate local or regional recipitation/rainfall on the basis of relationships with coarse-resolution atmospheric variables. None of these experiments satisfactorily reproduced temporal intermittency and variability in rainfall. We attempt to improve performance by using two approaches: (1) couple two NNs in series, the first to determine rainfall occurrence, and the second to determine rainfall intensity during rainy periods; and (2) categorize rainfall into intensity categories and train the NN to reproduce these rather than the actual intensities. The experiments focused on estimating 12-h mean rainfall in the Chikugo River basin, Kyushu Island, southern Japan, from large-scale values of wind speeds at 850 hPa and precipitable water. The results indicated that (1) two NNs in series may greatly improve the reproduction of intermittency; (2) longer data series are required to reproduce variability; (3) intensity categorization may be useful for probabilistic forecasting; and (4) overall performance in this region is better during winter and spring than during summer and autumn.

• Author: J. Olsson; Cintia Bertacchi Uvo; K. Jinno; A. Kawamura; K. Nishiyama; N. Koreeda; T. Nakashima; O. Morita
• Department/s: Division of Water Resources Engineering
• Publishing year: 2004
• Language: English
• Pages: 1-12
• Publication/Series: Journal of Hydrologic Engineering
• Volume: 9
• Issue: 1
• Links: http://dx.doi.org/10.1061/(ASCE)1084-0699(2004)9:1(1)
• Document type: Journal article
• Publisher: American Society of Civil Engineers (ASCE)
• Topic: Water Engineering
• Status: Published
• ISBN/ISSN/Other: ISSN: 1084-0699