Intelligent Flood Forecasting Using a Delay-Aware Terrain- Informed Graph Network

DOI

10.2991/978-94-6239-693-7_64How to use a DOI?

Keywords

Flood forecasting; spatio-temporal graph neural networks; terrain-sensitive modeling; asynchronous propagagation; time-serie of hydrology

Abstract

Accurate flood forecasting is required for disaster risk mitigation. Risk mitigation, however, a lot of data-driven models are based on synchronous spatio-temporal assumptions which cannot reflect the inherent asynchronous character of flooding propagation. In hydrological systems, stream indicators run off downstream with topography-dependent slop delays, elevation delays, and river delays length. In an effort to overcome this weakness, this research paper offers a Delay- An Aware Terrain Informed Flood Propagation Network (DT-FPN) that explicitly models terrain conditioned propagation delays in a directed hydrological graph. Unlike conventional spatio- DT-FPN, it allows message asynchronous communication delays, so that downstream nodes can update only on delay. Information coming upstream is received and a more physical outcome is reached. Reliable modeling of the dynamics of floods. Experiments on empirical hydrological field tests indicate that DT-FPN out- executes LSTM, ConvLSTM and synchronous graph-based baselines, with a maximum RMSE and MAE decrease of 22% and 25% respectively and also substantially enhanced prediction of peak flood arrival-time accuracy.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ankush Naru
AU  - Abhishek Poonia
AU  - Vikash Chahar
AU  - Aryan Gupta
AU  - Muskan Duhan
AU  - Prabhjot Kaur
PY  - 2026
DA  - 2026/06/16
TI  - Intelligent Flood Forecasting Using a Delay-Aware Terrain- Informed Graph Network
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 647
EP  - 659
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_64
DO  - 10.2991/978-94-6239-693-7_64
ID  - Naru2026
ER  -