Imagen de Portada

A New Custom Deep Learning Model Coupled with a Flood Index for Multi-Step-Ahead Flood Forecasting

Guardado en:
Publicado en:Hydrology vol. 12, no. 5 (2025), p. 104
Autor principal: Shen, Jianming
Otros Autores: Yang Moyuan, Zhang, Juan, Chen, Nan, Li, Binghua
Publicado:
MDPI AG
Materias:
China
Han River
Damage prevention
Warning systems
Resource management
Early warning systems
Artificial neural networks
Flood control
Water depth
Flood damage
Flood forecasting
Machine learning
Uncertainty
Damage
Datasets
Water resources management
Accuracy
Recurrent neural networks
Stream flow
Water resources
Decision making
Flood predictions
Hydrologic data
Flood management
Deep learning
Forecasting
Floods
Hydrology
Lead time
Neural networks
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:Accurate and prompt flood forecasting is essential for effective decision making in flood control to help minimize or prevent flood damage. We propose a new custom deep learning model, IF-CNN-GRU, for multi-step-ahead flood forecasting that incorporates the flood index (<inline-formula>IF</inline-formula>) to improve the prediction accuracy. The model integrates convolutional neural networks (CNNs) and gated recurrent neural networks (GRUs) to analyze the spatiotemporal characteristics of hydrological data, while using a custom recursive neural network that adjusts the neural unit output at each moment based on the flood index. The IF-CNN-GRU model was applied to forecast floods with a lead time of 1–5 d at the Baihe hydrological station in the middle reaches of the Han River, China, accompanied by an in-depth investigation of model uncertainty. The results showed that incorporating the flood index <inline-formula>IF</inline-formula> improved the forecast precision by up to 20%. The analysis of uncertainty revealed that the contributions of modeling factors, such as the datasets, model structures, and their interactions, varied across the forecast periods. The interaction factors contributed 17–36% of the uncertainty, while the contribution of the datasets increased with the forecast period (32–53%) and that of the model structure decreased (32–28%). The experiment also demonstrated that data samples play a critical role in improving the flood forecasting accuracy, offering actionable insights to reduce the predictive uncertainty and providing a scientific basis for flood early warning systems and water resource management.
ISSN:2306-5338
DOI:10.3390/hydrology12050104
Fuente:Agriculture Science Database