Next Article in Journal
Effects of Chlorpyrifos Ethyl on Cholinesterase and Growth of Silver Barb (Barbonymus gonionotus)
Previous Article in Journal
Effect of Biochar Amendment in Woodchip Denitrifying Bioreactors for Nitrate and Phosphate Removal in Tile Drainage Flow
Previous Article in Special Issue
3D GIS Platform for Flood Wargame: A Case Study of New Taipei City, Taiwan
Article

A Strategy to Optimize the Implementation of a Machine-Learning Scheme for Extreme Meiyu Rainfall Prediction over Southern Taiwan

1
National Science and Technology Center for Disaster Reduction, New Taipei 23143, Taiwan
2
Department of Atmospheric Science, Chinese Culture University, Taipei 11114, Taiwan
3
Department of Atmospheric Science, National Taiwan University, Taipei 10617, Taiwan
*
Author to whom correspondence should be addressed.
Academic Editors: Momcilo Markus and Renato Morbidelli
Water 2021, 13(20), 2884; https://doi.org/10.3390/w13202884
Received: 2 September 2021 / Revised: 5 October 2021 / Accepted: 12 October 2021 / Published: 14 October 2021
This study aims to propose a strategy to optimize the performance of the Support Vector Machine (SVM) scheme for extreme Meiyu rainfall prediction over southern Taiwan. Variables derived from Climate Forecast System Reanalysis (CFSR) dataset are the candidates for predictor selection. A series of experiments with different combinations of predictors and domains are designed to obtain the optimal strategy for constructing the SVM scheme. The results reveal that the accuracy (ACC), positive predictive values (PPV), probability of detection (POD), and F1-score can exceed 0.6 on average. Choosing the predictors associated with the Meiyu system and determine the domain associated with the correlations between selected predictors and predictand can improve the forecast performance. Our strategy shows the potential to predict extreme Meiyu rainfall in southern Taiwan with lead times from 16 h to 64 h. The F1-score analysis further demonstrates that the forecast performance of our scheme is stable, with slight inter-annual fluctuations from 1990 to 2019. Higher performance would be expected when the north of the South China Sea is characterized by stronger southwesterly flow and abundant low-level moisture for a given year. View Full-Text
Keywords: support vector machine; machine learning; extreme Meiyu rainfall support vector machine; machine learning; extreme Meiyu rainfall
Show Figures

Figure 1

MDPI and ACS Style

Chu, J.-L.; Chiang, C.-C.; Hsu, L.-H.; Hwang, L.-R.; Yu, Y.-C.; Lin, K.-L.; Wang, C.-J.; Su, S.-H.; Yo, T.-S. A Strategy to Optimize the Implementation of a Machine-Learning Scheme for Extreme Meiyu Rainfall Prediction over Southern Taiwan. Water 2021, 13, 2884. https://doi.org/10.3390/w13202884

AMA Style

Chu J-L, Chiang C-C, Hsu L-H, Hwang L-R, Yu Y-C, Lin K-L, Wang C-J, Su S-H, Yo T-S. A Strategy to Optimize the Implementation of a Machine-Learning Scheme for Extreme Meiyu Rainfall Prediction over Southern Taiwan. Water. 2021; 13(20):2884. https://doi.org/10.3390/w13202884

Chicago/Turabian Style

Chu, Jung-Lien, Chou-Chun Chiang, Li-Huan Hsu, Li-Rung Hwang, Yi-Chiang Yu, Kuan-Ling Lin, Chieh-Ju Wang, Shih-Hao Su, and Ting-Shuo Yo. 2021. "A Strategy to Optimize the Implementation of a Machine-Learning Scheme for Extreme Meiyu Rainfall Prediction over Southern Taiwan" Water 13, no. 20: 2884. https://doi.org/10.3390/w13202884

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop