Urban flood prediction using ensemble artificial neural network: an investigation on improving model uncertainty

Reducing the impact of artificial neural networks (ANN) affected by sources of uncertainty is crucial to improving the reliability of the flood prediction model. This study proposes an ensemble artificial neural network (EANN) model to predict the degree of flooding in coastal cities. Combined metho...

Full description

Saved in:
Bibliographic Details
Published in:Applied water science 2024-06, Vol.14 (6), p.144-10, Article 144
Main Authors: Dai, Weijun, Tang, Yanni, Liao, Ning, Zou, Shujie, Cai, Zhiming
Format: Article
Language:English
Subjects:
Aquatic Pollution
Artificial neural networks
Cities
Comparative Law
Datasets
EANN
Earth and Environmental Science
Earth Sciences
Flood forecasting
Flood predictions
Floods
Floods prediction
HNPSFS
Hurricanes
Hydrogeology
Industrial and Production Engineering
International & Foreign Law
Intervals
Nanotechnology
Neural networks
Original Article
Prediction models
Private International Law
Training
Typhoon event
Typhoons
Uncertainty
Uncertainty analysis
Waste Water Technology
Water Industry/Water Technologies
Water Management
Water Pollution Control
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Reducing the impact of artificial neural networks (ANN) affected by sources of uncertainty is crucial to improving the reliability of the flood prediction model. This study proposes an ensemble artificial neural network (EANN) model to predict the degree of flooding in coastal cities. Combined methods are used to reduce the model’s uncertainty, heuristic neural pathway strength feature selection is used to select inputs, the coupling method is used to optimize network architecture and parameters, and the integration method which paralleling three ANN models with different predicted lead periods ensemble together is used to capture output uncertainty. The EANN model has successfully predicted flooding in the Chinese coastal city of Macao during a typhoon, with convincing accuracy. The study also analyzed the impacts of both long and short training datasets with appropriate time intervals on ANN modeling performance. It was found that the performance of short training datasets, with appropriate time intervals, was similar to or better than models with long training datasets.
ISSN:2190-5487
2190-5495
DOI:10.1007/s13201-024-02201-7