• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.7
• /
• pp.892-903
• /
• 2020

The rapid and accurate prediction of storm-surge height during typhoon attacks is essential in responding to coastal disasters. Most methods used for predicting typhoon data are based on numerical modeling, but numerical modeling takes significant computing resources and time. Recently, various studies on the expeditious production of predictive data based on artificial intelligence have been conducted, and in this study, artificial intelligence-based storm-surge height prediction was performed. Several learning data were needed for artificial intelligence training. Because the number of previous typhoons was limited, many synthesized typhoons were created using the tropical cyclone risk model, and the storm-surge height was also generated using the storm surge model. The comparison of the storm-surge height predicted using artificial intelligence with the actual typhoon, showed that the root-mean-square error was 0.09 ~ 0.30 m, the correlation coefficient was 0.65 ~ 0.94, and the absolute relative error of the maximum height was 1.0 ~ 52.5%. Although errors appeared to be somewhat large at certain typhoons and points, future studies are expected to improve accuracy through learning-data optimization.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.31 no.5
• /
• pp.241-252
• /
• 2019

To choose appropriate countermeasures against potential coastal disaster damages caused by a storm surge, it is necessary to estimate the frequency of storm surge heights estimation. As the coastal populations size in the past was small, the tropical cyclone risk model (TCRM) was used to generate 176,689 synthetic typhoons. In simulation, historical paths and central pressures were incorporated as a probability density function. Moreover, to consider the typhoon characteristics that resurfaced or decayed after landfall on the southeast coast of China, incorporated the shift angle of the historical typhoon as a function of the probability density function and applied it as a damping parameter. Thus, the passing rate of typhoons moving from the southeast coast of China to the south coast has improved. The characteristics of the typhoon were analyzed from the historical typhoon information using correlations between the central pressure, maximum wind speed ($V_{max}$) and the maximum wind speed radius ($R_{max}$); it was then applied to synthetic typhoons. The storm surges were calculated using the ADCIRC model, considering both tidal and synthetic typhoons using automated Perl script. The storm surges caused by the probabilistic synthetic typhoons appear similar to the recorded storm surges, therefore this proposed scheme can be applied to the storm surge simulations. Based on these results, extreme values were calculated using the Generalized Extreme Value (GEV) method, and as a result, the 100-year return period storm surge was found to be satisfactory compared with the calculated empirical simulation value. The method proposed in this study can be applied to estimate the frequency of storm surges in coastal areas.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.31 no.5
• /
• pp.253-264
• /
• 2019

Storm surges caused by a typhoon occur during the summer season, when the sea-level is higher than the annual average due to steric effect. In this study, we analyzed the sea-level pressure and tidal data collected in 1 h intervals at Incheon, Kunsan, Mokpo, Seogwipo stations on the Yellow Sea coast to analyze the summer season storm surge and wave overtopping. According to our analyses, the summer mean sea-level rise on the west and south coasts is approximately 20 cm and 15 to 20 cm higher than the annual mean sea-level rise. Changes in sea-level rise are closely related to changes in seasonal sea-level pressure, within the range of 1.58 to 1.73 cm/hPa. These correlated mechanisms generates a phase difference of one month or more. The 18.6 year long period tidal constituents indicate that in 2090, the amplitude of the $M_2$ basin peaks on the southwest coast. Therefore, there is a need to analyze the target year for global warming and sea-level rise in 2090. Wave overtopping was simulated considering annual mean sea-level rise, summer sea level rise, the combined effect of nodal factor variation, and 100-year frequency storm surge. As a result, flooding by wave overtopping occurs in the area of Suyong Bay, Busan. In 2090, overtopping discharges are more than doubled than those in Marine City by the recent typhoon Chaba. Adequate coastal design is needed to prepare for flood vulnerability.