Effective Use of Ensemble Numerical Weather Predictions in Taiwan by Means of a SOM-Based Cluster Analysis Technique

Abstract

Abstract:Typhoon rainfall is one of the most important water resources in Taiwan. However, heavy rainfall during typhoons often leads to serious disasters. Therefore, accurate typhoon rainfall forecasts are always desired for water resources managers and disaster warning systems. In this study, the quantitative rainfall forecasts from an ensemble numerical weather prediction system in Taiwan are used. Furthermore, a novel strategy, which is based on the use of a self-organizing map (SOM) based cluster analysis technique, is proposed to integrate these ensemble forecasts. By means of the SOM-based cluster analysis technique, ensemble forecasts that have similar features are clustered. That is helpful for users to effectively combine these ensemble forecasts for providing better typhoon rainfall forecasts. To clearly demonstrate the advantage of the proposed strategy, actual application is conducted during five typhoon events. The results indicate that the ensemble rainfall forecasts from numerical weather prediction models are well categorized by the SOM-based cluster analysis technique. Moreover, the integrated typhoon rainfall forecasts resulting from the proposed strategy are more accurate when compared to those from the conventional method (i.e., the ensemble mean of all forecasts). In conclusion, the proposed strategy provides improved forecasts of typhoon rainfall. The improved quantitative rainfall forecasts are expected to be useful to support disaster warning systems as well as water resources management systems during typhoons.

A rainwater control optimization design approach for airports based on a self-organizing feature map neural network model

“…As shown in formula (16), only the output result of the winning neuron is 1, that is, the corresponding parameter combination U reaches the optimal design requirement; Otherwise, the results of other neurons are 0, that is the corresponding parameter combination U does not meet the optimal design requirements. At this time, the output result of the corresponding parameter combination U is the optimal design parameter of the airport rainwater control model, and the best design parameter results are output.…”

“…Yan Meng-ge, Dong Xiao-zhou et al used the SOFM model combined with correlation to identify and classify the LIBS spectra of natural geological samples [15]. Wu, Ming-Chang, Hong, Jing-Shan et al used the SOFM model to analyze and forecast typhoon rainfall in Taiwan [16]. The SOFM model has become one of the most popular neural network algorithms in the data processing and analysis for various engineering purposes.…”

The Impact of Climate on Hydrological Extremes

“…The first group of papers deals with precipitation and weather predictions. In particular, Wu et al [5] propose the use of a self-organizing map (SOM), based on the cluster analysis technique, in order to integrate the ensemble numerical weather prediction system in Taiwan. By means of this technique, ensemble forecasts of similar features were clustered in order to provide better typhoon rainfall forecasts.…”

Typhoon Rainfall Forecasting by Means of Ensemble Numerical Weather Predictions with a GA-Based Integration Strategy

“…This drawback is unfavorable for disaster mitigation and prevention. Therefore, in recent years, considerable concern has arisen over the effective integration of the ensemble forecasts from an EPS (e.g., [27][28][29][30][31][32]). By using various statistically based techniques, the researches confirm the advantage of post-processing of ensemble forecasts in obtaining improved results.…”

“…Kumar et al [30] performed linear programming and weighted mean techniques to select the best combination of five streamflow models. Wu et al [32] applied a neural network-based cluster analysis technique to categorize ensemble forecasts and then calculated the simple average of partial forecasts which are grouped in a specific cluster.…”