Design and Performance Verification of Deep Learning-Based River Flood Prediction System Design and Digital Twin-Based Its Application DOI Creative Commons
Heesang Eom, Young-Hun Kim,

Jong‐Ho Paik

et al.

Mathematics, Journal Year: 2025, Volume and Issue: 13(11), P. 1696 - 1696

Published: May 22, 2025

This paper presents a digital twin-based river management and flood prediction system designed for hydrological environments, including volcanic geology. To address the problems of rapid runoff complex terrain, deep learning-based hybrid model is proposed that integrates Convolutional Neural Network (CNN) spatial feature extraction Recurrent (RNN) with Long Short-Term Memory (LSTM) units temporal sequence modeling. The performance evaluation results show CNN-RNN outperforms individual CNN RNN baselines. achieves macro-average precision 0.97, recall 0.99, an F1 score 0.98, significantly outperforming existing methods. also integrated 3D twin visualization platform to enable real-time monitoring data-driven decision-making.

Language: Английский

Design and Performance Verification of Deep Learning-Based River Flood Prediction System Design and Digital Twin-Based Its Application DOI Creative Commons
Heesang Eom, Young-Hun Kim,

Jong‐Ho Paik

et al.

Mathematics, Journal Year: 2025, Volume and Issue: 13(11), P. 1696 - 1696

Published: May 22, 2025

This paper presents a digital twin-based river management and flood prediction system designed for hydrological environments, including volcanic geology. To address the problems of rapid runoff complex terrain, deep learning-based hybrid model is proposed that integrates Convolutional Neural Network (CNN) spatial feature extraction Recurrent (RNN) with Long Short-Term Memory (LSTM) units temporal sequence modeling. The performance evaluation results show CNN-RNN outperforms individual CNN RNN baselines. achieves macro-average precision 0.97, recall 0.99, an F1 score 0.98, significantly outperforming existing methods. also integrated 3D twin visualization platform to enable real-time monitoring data-driven decision-making.

Language: Английский

Citations

0