Toggle Main Menu Toggle Search

Open Access padlockePrints

The Newcastle University research output collection, currently available on ePrints, will shortly be moving to a new open repository platform, Figshare. To prepare for the data migration we have paused adding new content to ePrints, and will resume once the new repository is launched. During this time you will continue to have access to ePrints (but no new content will appear). We will share updates here when available.

Towards more accurate very short-range flood forecasts with physics-enhanced machine learning models

Lookup NU author(s): Dr Manuel HerreraORCiD

Downloads

Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).

Abstract

Flood-related disasters have become increasingly frequent in recent years, as evidenced by severe events in Brazil, Spain, and Germany. The development of impact-based flood early warning systems (IBFWS) has been an essential tool for minimizing human and economic losses. Recent advances in data-driven models show strong potential for improving flood forecasting capabilities. More promising approach that has emerged is the use of physics-enhanced machine learning models. These models incorporate physical and hydrological concepts into data-driven frameworks, which enhance their interpretability and robustness. This paper proposes a physics-enhanced Long Short-Term Memory (LSTM) model to incorporate inter-station lag times into the model’s feature selection and temporal configuration, improving flood forecasts. The framework is applied to a flood-prone urban basin using high-resolution (10-minute) rainfall and streamflow data, assessing both overall forecast skill and the accuracy of flood events, particularly the peak magnitude and timing errors. Results demonstrate that the physics-enhanced configuration consistently increases prediction accuracy by reducing redundancy among inputs. Moreover, it maintains the physical coherence of the hydrological processes, supporting the transition from black-box to grey-box modeling. The resulting architecture remained computationally efficient, highlighting the potential of physics-enhanced neural networks for operational and impact-based flood forecasting.

Publication metadata

Author(s): Bezerra RPG, Eleutério JC, Solha PB, Brentan BM, de Mello CR, Herrera M, Rodrigues AF

Publication type: Article

Publication status: Published

Journal: Journal of Hydroinformatics

Year: 2026

Volume: 28

Issue: 5

Pages: 495-517

Online publication date: 06/05/2026

Acceptance date: 20/04/2026

Date deposited: 22/04/2026

ISSN (print): 1464-7141

ISSN (electronic): 1465-1734

Publisher: IWA Publishing

URL: https://doi.org/10.2166/hydro.2026.180

DOI: 10.2166/hydro.2026.180

Data Access Statement: All relevant data are included in the paper or its Supplementary Information.

Altmetrics

Altmetrics provided by Altmetric

Share