Predicting the flood peak arrival time via a comprehensive machine learning framework: case studies in Changhua and Tunxi basins, China DOI Creative Commons
Shi Zhou, Xiaona Liu

Journal of Water and Climate Change, Journal Year: 2024, Volume and Issue: 16(1), P. 142 - 159

Published: Dec. 10, 2024

ABSTRACT Floods are becoming increasingly frequent and severe due to climate change urbanization, thereby increasing risks lives, property, the environment. This necessitates development of precise flood forecasting systems. study addresses critical task predicting peak arrival times, which is essential for timely warnings preparations, by introducing a comprehensive machine-learning framework. Our approach integrates interpretable feature engineering, individual model design, novel ensembles enhance prediction accuracy. We extract informative features from historical flow rainfall data, design suite models, develop ensemble technique combine predictions. conducted case studies on Tunxi Changhua basins in China. Numerical experiments reveal that our method significantly benefits engineering ensembles, achieving mean absolute error (MAE) errors 1.524 h 2.192 Changhua. These results notably outperform best baseline method, achieves MAE 1.727 2.737

Language: Английский

A Comprehensive Review of Methods for Hydrological Forecasting Based on Deep Learning DOI Open Access
Xinfeng Zhao, Hongyan Wang,

Mingyu Bai

et al.

Water, Journal Year: 2024, Volume and Issue: 16(10), P. 1407 - 1407

Published: May 15, 2024

Artificial intelligence has undergone rapid development in the last thirty years and been widely used fields of materials, new energy, medicine, engineering. Similarly, a growing area research is use deep learning (DL) methods connection with hydrological time series to better comprehend expose changing rules these series. Consequently, we provide review latest advancements employing DL techniques for forecasting. First, examine application convolutional neural networks (CNNs) recurrent (RNNs) forecasting, along comparison between them. Second, made basic enhanced long short-term memory (LSTM) analyzing their improvements, prediction accuracies, computational costs. Third, performance GRUs, other models including generative adversarial (GANs), residual (ResNets), graph (GNNs), estimated Finally, this paper discusses benefits challenges associated forecasting using techniques, CNN, RNN, LSTM, GAN, ResNet, GNN models. Additionally, it outlines key issues that need be addressed future.

Language: Английский

Citations

10
Peak flow forecasting in Mahanadi River Basin using a novel hybrid VMD-FFA-RNN approach DOI
Sanjeev Sharma, Sangeeta Kumari

Acta Geophysica, Journal Year: 2025, Volume and Issue: unknown

Published: March 12, 2025

Language: Английский

Citations

0
Predicting split tensile strength in Portland and geopolymer concretes using machine learning algorithms: a comparative study DOI

Rajesh Kumar Paswan,

Abhilash Gogineni,

Sanjay Sharma

et al.

Journal of Building Pathology and Rehabilitation, Journal Year: 2024, Volume and Issue: 9(2)

Published: Aug. 17, 2024

Language: Английский

Citations

3
River flood prediction through flow level modeling using multi-attention encoder-decoder-based TCN with filter-wrapper feature selection DOI

G. Selva Jeba,

P. Chitra

Earth Science Informatics, Journal Year: 2024, Volume and Issue: 17(6), P. 5233 - 5249

Published: Aug. 22, 2024

Language: Английский

Citations

2
Forecasting Rainfall: Evaluating Machine Learning Models on Australian Weather Data DOI
Suraj Kumar Gupta,

Ravish Sharma,

Shivani Trivedi

et al.

Published: May 9, 2024

Language: Английский

Citations

0
An alert system for flood forecasting based on multiple seasonal holt-winters models: a case study of southeast Brazil DOI

Franciele R. Leandro,

Eliane da Silva Christo, Kelly Alonso Costa

et al.

Sustainable Water Resources Management, Journal Year: 2024, Volume and Issue: 10(5)

Published: Sept. 5, 2024

Language: Английский

Citations

0
Impact Assessment of Coupling Mode of Hydrological Model and Machine Learning Model on Runoff Simulation: A Case of Washington DOI Creative Commons
Junqi Zhang, Jing Li, Hua Zhao

et al.

Atmosphere, Journal Year: 2024, Volume and Issue: 15(12), P. 1461 - 1461

Published: Dec. 7, 2024

The inherent uncertainties in traditional hydrological models present significant challenges for accurately simulating runoff. Combining machine learning with is an essential approach to enhancing the runoff modeling capabilities of models. However, research on impact mixed simulation capability limited. Therefore, this study uses model Simplified Daily Hydrological Model (SIMHYD) and Long Short Term Memory (LSTM) construct two coupled models: a direct coupling dynamically improved predictive validity hybrid model. These were evaluated using US CAMELS dataset assess combination methods capabilities. results indicate that both compared individual models, combined forecasting dynamic prediction effectiveness (DPE) demonstrating optimal capability. Compared LSTM, showed median increase 12.8% Nash Sutcliffe efficiency (NSE) daily during validation period, 12.5% SIMHYD. In addition, LSTM model, high flow increased by 23.6%, SIMHYD, it 28.4%. At same time, stability low was significantly improved. performance testing involving varying training period lengths, DPE trained 12 years exhibited best performance, showing 3.5% 1.5% NSE periods 6 18 years, respectively.

Language: Английский

Citations

0
Predicting the flood peak arrival time via a comprehensive machine learning framework: case studies in Changhua and Tunxi basins, China DOI Creative Commons
Shi Zhou, Xiaona Liu

Journal of Water and Climate Change, Journal Year: 2024, Volume and Issue: 16(1), P. 142 - 159

Published: Dec. 10, 2024

ABSTRACT Floods are becoming increasingly frequent and severe due to climate change urbanization, thereby increasing risks lives, property, the environment. This necessitates development of precise flood forecasting systems. study addresses critical task predicting peak arrival times, which is essential for timely warnings preparations, by introducing a comprehensive machine-learning framework. Our approach integrates interpretable feature engineering, individual model design, novel ensembles enhance prediction accuracy. We extract informative features from historical flow rainfall data, design suite models, develop ensemble technique combine predictions. conducted case studies on Tunxi Changhua basins in China. Numerical experiments reveal that our method significantly benefits engineering ensembles, achieving mean absolute error (MAE) errors 1.524 h 2.192 Changhua. These results notably outperform best baseline method, achieves MAE 1.727 2.737

Language: Английский

Citations

0