What question did this study set out to answer?

This research aims to improve the accuracy of AI-based flood forecasting systems using deep learning techniques.

November 11, 2025EarthOpen Access

Case Study on Improvement Measures for Increasing Accuracy of AI-Based River Water-Level Prediction Model

View Full Paper

Ask AI

Bookmark

Authors

SKSooyoung Kim SLSeungho Lee KYKwang Seok Yoon

Discussion

Member takes

Implication

Case study demonstrates reduced root mean square error in flood forecasting using AI models in ASEAN regions, suggesting improvements for disaster preparedness.

Key Points

This research aims to improve the accuracy of AI-based flood forecasting systems using deep learning techniques.
Developed a river water-level prediction model using a long short-term memory (LSTM) algorithm.
Applied water-level differencing to create stationary time-series data.
Utilized repeated k-fold cross-validation for model evaluation across multiple sites.
Achieved a root mean square error of 0.13 m and a coefficient of determination (R2) of 0.866.
Demonstrated a significant improvement in prediction performance compared to non-differenced models by approximately 17%.
Confirmed the effectiveness of temporal stationarity and k-fold validation in enhancing predictive accuracy.

Cite This Study

Kim et al. (2025) studied this question.

synapsesocial.com/papers/69252e9ec0ce034ddc3565be https://doi.org/10.3390/earth6040146

View Full Paper

Ask AI

Bookmark

Implication

Case study demonstrates reduced root mean square error in flood forecasting using AI models in ASEAN regions, suggesting improvements for disaster preparedness.

Case Study on Improvement Measures for Increasing Accuracy of AI-Based River Water-Level Prediction Model

Discussion

Member takes

Implication

Key Points

Cite This Study

Case Study on Improvement Measures for Increasing Accuracy of AI-Based River Water-Level Prediction Model

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider