Time series-based machine learning for forecasting multivariate water quality in full-scale drinking water treatment with various reagent dosages DOI
Hongjiao Pang,

Yawen Ben,

Yong Cao

et al.

Water Research, Journal Year: 2024, Volume and Issue: 268, P. 122777 - 122777

Published: Nov. 9, 2024

Language: Английский

Hyperparameter optimization of regional hydrological LSTMs by random search: A case study from Basque Country, Spain DOI Creative Commons

Fateme Hosseini,

Cristina Prieto, César Álvarez

et al.

Journal of Hydrology, Journal Year: 2024, Volume and Issue: unknown, P. 132003 - 132003

Published: Sept. 1, 2024

Language: Английский

Citations

4
Selection, Planning, and Modelling of Nature-Based Solutions for Flood Mitigation DOI Open Access
James Griffiths, Karine E. Borne, Annette Semádeni-Davies

et al.

Water, Journal Year: 2024, Volume and Issue: 16(19), P. 2802 - 2802

Published: Oct. 1, 2024

The use of nature-based solutions (NBSs) for hazard mitigation is increasing. In this study, we review the NBSs flood using a strengths, weaknesses, opportunities, and threats (SWOT) analysis framework commonly used NBSs. Approaches reviewed include retention detention systems, bioretention landcover soil management, river naturalisation floodplain constructed natural wetlands. Existing tools identification quantification direct benefits co-benefits are then reviewed. Finally, approaches to modelling discussed, including type model parameterisation. After outlining knowledge gaps within current literature research, roadmap development, modelling, implementation presented.

Language: Английский

Citations

4
Hydro-informer: a deep learning model for accurate water level and flood predictions DOI Creative Commons
Wael Almikaeel, Andrej Šoltész, Lea Čubanová

et al.

Natural Hazards, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 16, 2024

Abstract This study aims to develop an advanced deep learning model, Hydro-Informer, for accurate water level and flood predictions, emphasizing extreme event forecasting. Utilizing a comprehensive dataset from the Slovak Hydrometeorological Institute SHMI (2008–2020), which includes precipitation, level, discharge data, model was trained using ladder technique with custom loss function enhance focus on values. The architecture integrates Recurrent Convolutional Neural Networks (RNN, CNN), Multi-Head Attention layers. Hydro-Informer achieved significant performance, Coefficient of Determination (R 2 ) 0.88, effectively predicting levels 12 h in advance river environment free human regulation structures. model’s strong performance identifying events highlights its potential enhancing management disaster preparedness. By integrating diverse data sources, can be used well-functioning warning system mitigate impacts. work proposes novel suitable locations without

Language: Английский

Citations

4
Explainable Artificial Intelligence for Reliable Water Demand Forecasting to Increase Trust in Predictions DOI Creative Commons
Claudia Maußner, Martin Oberascher,

Arnold Autengruber

et al.

Water Research, Journal Year: 2024, Volume and Issue: 268, P. 122779 - 122779

Published: Nov. 9, 2024

Language: Английский

Citations

4
Time series-based machine learning for forecasting multivariate water quality in full-scale drinking water treatment with various reagent dosages DOI
Hongjiao Pang,

Yawen Ben,

Yong Cao

et al.

Water Research, Journal Year: 2024, Volume and Issue: 268, P. 122777 - 122777

Published: Nov. 9, 2024

Language: Английский

Citations

4