Imagem da capa

Performance Improvement of a Multiple Linear Regression-Based Storm Surge Height Prediction Model Using Data Resampling Techniques

Na minha lista:
Publicado no:Journal of Marine Science and Engineering vol. 13, no. 11 (2025), p. 2173-2196
Autor principal: Jung-A, Yang
Outros Autores: Lee, Yonggwan
Publicado em:
MDPI AG
Assuntos:
Korean Peninsula
Islands
Tidal waves
Accuracy
Coastal zone
Typhoons
Global warming
Deep learning
Storm surges
Regression analysis
Sampling techniques
Resampling
Regression models
Hurricanes
Sea level
Climate change
Sampling
Sea level changes
Coastal hazards
Statistical analysis
Prediction models
Coasts
Storms
Tide gauges
Sampling methods
Root-mean-square errors
Regions
Variables
Height
Environmental
Acesso em linha:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
Resumo:Storm surges present a major hazard to coastal areas worldwide, a risk that is further amplified by ongoing sea-level rise associated with climate warming. The purpose of this study is to enhance the prediction performance of a storm surge height model by incorporating data resampling techniques into a multiple linear regression framework. Typhoon-related predictors, such as location and intensity-related parameters, were used to estimate observed storm surge heights at eleven tide gauge stations in southeastern Korea. To address the data imbalance inherent in storm surge height distributions, we applied combinations of over- and under-sampling methods across various threshold levels and evaluated them using four statistical metrics: root mean square error (RMSE), mean absolute error (MAE), mean squared error (MSE), and the coefficient of determination (R2). The results demonstrate that both threshold selection and sampling configuration significantly influence model accuracy. In particular, station-specific sampling strategies improved R2 values by up to 0.46, even without modifying the regression model itself, underscoring the effectiveness of data-level balancing. These findings highlight that adaptive resampling strategies—tailored to local surge characteristics and data distribution—can serve as a powerful tool for improving regression-based coastal hazard prediction models.
ISSN:2077-1312
DOI:10.3390/jmse13112173
Fonte:Engineering Database