Identifying the Minimum Number of Flood Events for Reasonable Flood Peak Prediction of Ungauged Forested Catchments in South Korea

The severity and incidence of flash floods are increasing in forested regions, causing significant harm to residents the environment. Consequently, accurate estimation flood peaks is crucial. As conventional physically based prediction models reflect traits only a small number areas, applying them ungauged catchments challenging. interrelationship between catchment characteristics features estimate areas remains underexplored, evaluation standards for appropriate events include during data collection ensure effective peak have not been established. Therefore, we developed machine-learning predictive model determined minimum required prediction. We employed rainfall-runoff estimating peaks. applicability machine learning was confirmed by high performance. Even with addition from performance did significantly improve when sufficient were used as input data. This criterion could facilitate determination developing adequate models.