Sign in Subscribe
Periodical publishing

Developing a Storm Surge Prediction Model for Coastal Regions

Strategic Insights

— 1 min read

Researchers from Konkuk University in Seoul, South Korea, have made significant strides in predicting storm surges, a major threat to coastal regions worldwide, especially with rising sea levels due to climate change. The study, supported by the Korea Meteorological Administration and the National Research Foundation of Korea, aimed to develop a storm surge height prediction model using a multiple linear regression approach. The model's performance was evaluated using various metrics, including the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R^2).

Key Takeaways:

  • The researchers developed a storm surge height prediction model using a multiple linear regression approach, focusing on typhoon characteristics and observed storm surge heights.
  • The model's predictive performance was assessed using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Squared Error (MSE), and the coefficient of determination (R^2).
  • The results showed that restricting typhoon events to within 900-1000 km of the observation site and segmenting surge heights into low and high ranges significantly improved predictive skill, especially for extreme surge events.
  • The model achieved an R^2 of 0.82 for high storm surge height (∼ 0.2 m) at Masan station and R^2 of 0.57 at a 500 km distance threshold at Gwangyang station.
  • The study suggests the need for future research incorporating nonlinear and ensemble methods to capture the variability of lower-magnitude surges.
  • The development of this storm surge prediction model contributes to the improvement of coastal hazard prediction and the development of more effective early warning systems and risk management strategies.

Statistics:

  • The researchers used a multiple linear regression approach to develop the storm surge height prediction model.
  • The model's performance was evaluated using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Squared Error (MSE), and the coefficient of determination (R^2).
  • The results showed that the model achieved an R^2 of 0.82 for high storm surge height (∼ 0.2 m) at Masan station.
  • The model showed an R^2 of 0.57 at a 500 km distance threshold at Gwangyang station.

Sources:

  • VerticalNews, "Storm Surges Pose Significant Threat to Coastal Regions Worldwide," Journal of Engineering, 2025,10
  • Journal of Marine Science and Engineering, "Development of a Storm Surge Prediction Model Using Typhoon Characteristics and Multiple Linear Regression," 2025,13(9):1655, http://www.mdpi.com/journal/jmse
  • Korea Meteorological Administration, National Research Foundation of Korea, Konkuk University

Read more