Abstract
Storm surge induced by severe typhoons has caused many catastrophic tragedies to coastal communities over past decades. Accurate and efficient prediction/assessment of storm surge is still an important task in order to achieve coastal disaster mitigation especially under the influence of climate change. This study revisits storm surge predictions using artificial neural networks (ANN) and effective typhoon parameters. Recent progress of storm surge modeling and some remaining unresolved issues are reviewed. In this paper, we chose the northeastern region of Taiwan as the study area, where the largest storm surge record (over 1.8 m) has been observed. To develop the ANN-based storm surge model for various lead-times (from 1 to 12 h), typhoon parameters are carefully examined and selected by analogy with the physical modeling approach. A knowledge extraction method (KEM) with backward tracking and forward exploration procedures is also proposed to analyze the roles of hidden neurons and typhoon parameters in storm surge prediction, as well as to reveal the abundant, useful information covered in the fully-trained artificial brain. Finally, the capability of ANN model for long-lead-time predictions and influences in controlling parameters are investigated. Overall, excellent agreement with observations (i.e., the coefficient of efficiency CE > 0.95 for training and CE > 0.90 for validation) is achieved in one-hour-ahead prediction. When the typhoon affects coastal waters, contributions of wind speed, central pressure deficit, and relative angle are clarified via influential hidden neurons. A general pattern of maximum storm surge under various scenarios is also obtained. Moreover, satisfactory accuracy is successfully extended to a much longer lead time (i.e., CE > 0.85 for training and CE > 0.75 for validation in 12-h-ahead prediction). Possible reasons for further accuracy improvement compared to earlier works are addressed.
Highlights
Storm surge, an abnormal rise of water driven by meteorological conditions, has been an important research topic since the 1950s [1] due to its devastating impact on coastal communities
We revisit the topic of storm surge prediction using artificial neural networks and effective typhoon parameters with the main purpose of extending further applicability and gaining a deeper insight
A knowledge extraction method based on backward tracking and forward exploration procedures is proposed to analyze the roles of hidden neurons and controlling parameters in storm surge prediction as well as to reveal abundant, useful information from the fully-trained artificial brain
Summary
An abnormal rise of water driven by meteorological conditions, has been an important research topic since the 1950s [1] due to its devastating impact on coastal communities. The data-driven ANNs outperform statistical approaches and process-based models, e.g., RMSE (root-mean-square error) < 10 cm and CC (correlation coefficient) > 0.90 [64] Another type of application is to predict storm surge using a dynamic and neural network hybrid model [57,65]. For the areas with frequent typhoon invasions from variable paths (e.g., 10 major paths in Taiwan), accurate long-lead-time surge prediction (defined by a lead time up to 12 h in this study) is still challenging For the latter, like the black box, complex mathematical processes inside the artificial neural networks are difficult to interpret [68,69] despite their capability for solving various nonlinear problems. The capability of the ANN model for long-lead-time predictions and the influences of controlling parameters are investigated and discussed
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
