Conference paper · 2026 · Open access
Explainable Urban Flood Prediction by Explainable Spatio-Temporal Graph Neural Network with Interpretable Risk Alerts
International Conference on Inventive Computation and Information Technologies (ICICIT), 1309–1316 · Published 1 July 2026 · DOI 10.1109/icicit69063.2026.11634177
In brief
“Explainable Urban Flood Prediction by Explainable Spatio-Temporal Graph Neural Network with Interpretable Risk Alerts” is a 2026 conference paper by Minnal Kumar Sathiyamoorthy, published in International Conference on Inventive Computation and Information Technologies (ICICIT). OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at International Conference on Inventive Computation and Information Technologies (ICICIT).
- Citations
- 0
- References
- 10
- Authors
- 1
Abstract
Urban flooding has become a major challenge to cities across the globe and there is need to have proper prediction systems that have interpretable risk warnings to manage the disaster effectively. The provided paper introduces an explainable spatio-temporal graph neural network (EST-GNN) architecture that combines Graph Convolutional Networks (GCN) with Gated Recurrent Units (GRU) and attention-based explainability modules of urban flood forecasting. The suggested methodology exploits the spatial connections among the drainage systems of cities in the form of graphs whilst representing the temporal changes of the patterns of rainfall and water flows. We use Shapley Additive Explanations (SHAP) and visualization of attention to give interpretable risk alerts to stakeholders to make them learn which aspects contributed to flood predictions. The model was tested on a comprehensive dataset of 300 storm events that have multi-source data in terms of rainfall intensity, water elevation, the topology of the drainage network and measurements of the IoT sensor. In experiments, it has better performance with an accuracy of 0.89, a precision of 0.90, a recall of 0.88, F1-score of 0.89, and AUC-ROC of 0.94. Nash Sutcliffe Efficiency (NSE) coefficient was 0.97, which is very high predictive power. The proposed EST-GNN demonstrated 15-44% improvements in accuracy when compared to baseline models, such as LSTM, standard GCN, and Random Forest, especially when predicting over a longer horizon of up to 24 hours. The explainability module has been able to determine the important spatial nodes and temporal patterns in flood risk that contribute to flood risk, with the attention weights identifying upstream drainage relationship and rainfall intensity as the most important contributor to flood risk. The framework is computationally efficient (82x faster than physics-based models) and interpretable, and is applicable in real-time flood forecasting and early warning systems in urban settings.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Sathiyamoorthy, M. K. (2026). Explainable Urban Flood Prediction by Explainable Spatio-Temporal Graph Neural Network with Interpretable Risk Alerts. International Conference on Inventive Computation and Information Technologies (ICICIT), 1309–1316. https://doi.org/10.1109/icicit69063.2026.11634177
MLA 9
Sathiyamoorthy, Minnal Kumar. “Explainable Urban Flood Prediction by Explainable Spatio-Temporal Graph Neural Network with Interpretable Risk Alerts.” International Conference on Inventive Computation and Information Technologies (ICICIT), 2026, pp. 1309–1316. https://doi.org/10.1109/icicit69063.2026.11634177.
Chicago
Sathiyamoorthy, Minnal Kumar. 2026. “Explainable Urban Flood Prediction by Explainable Spatio-Temporal Graph Neural Network with Interpretable Risk Alerts.” International Conference on Inventive Computation and Information Technologies (ICICIT): 1309–1316. https://doi.org/10.1109/icicit69063.2026.11634177.
Harvard
Sathiyamoorthy, M. K. (2026) ‘Explainable Urban Flood Prediction by Explainable Spatio-Temporal Graph Neural Network with Interpretable Risk Alerts’, International Conference on Inventive Computation and Information Technologies (ICICIT), pp. 1309–1316. doi:10.1109/icicit69063.2026.11634177.
IEEE
M. K. Sathiyamoorthy, “Explainable Urban Flood Prediction by Explainable Spatio-Temporal Graph Neural Network with Interpretable Risk Alerts,” International Conference on Inventive Computation and Information Technologies (ICICIT), pp. 1309–1316, 2026, doi: 10.1109/icicit69063.2026.11634177.
BibTeX
@inproceedings{sathiyamoorthy2026explainable,
title = {{Explainable Urban Flood Prediction by Explainable Spatio-Temporal Graph Neural Network with Interpretable Risk Alerts}},
author = {Sathiyamoorthy, Minnal Kumar},
booktitle = {International Conference on Inventive Computation and Information Technologies (ICICIT)},
year = {2026},
pages = {1309--1316},
doi = {10.1109/icicit69063.2026.11634177},
url = {https://doi.org/10.1109/icicit69063.2026.11634177}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI
- urban flood forecasting
- explainable AI
- spatio-temporal graph neural networks
- graph convolutional networks
- gated recurrent unit
- attention mechanism
- SHAP
- drainage network
Work with this paper
Most-cited papers in Environmental Science
- Biodiversity hotspots for conservation prioritiesNorman Myers, Russell A. Mittermeier, Cristina Goettsch Mittermeier and 2 more · Nature · 2000 · 32,720 citations
- The Tragedy of the CommonsGarrett Hardin · Science · 1968 · 26,194 citations
- River flow forecasting through conceptual models part I — A discussion of principlesJ.E. Nash, John V. Sutcliffe · Journal of Hydrology · 1970 · 24,625 citations
- The value of the world's ecosystem services and natural capitalRobert Costanza, Ralph C. d’Arge, R.S. de Groot and 10 more · Nature · 1997 · 23,508 citations
- Climate change 2007: the physical science basisSusan Solomon, Dahe Qin, Martin Manning and 5 more · 2007 · 23,383 citations
Questions about this paper
How do I cite this paper in APA style?
Sathiyamoorthy, M. K. (2026). Explainable Urban Flood Prediction by Explainable Spatio-Temporal Graph Neural Network with Interpretable Risk Alerts. International Conference on Inventive Computation and Information Technologies (ICICIT), 1309–1316. https://doi.org/10.1109/icicit69063.2026.11634177
How many times has this paper been cited?
0 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at International Conference on Inventive Computation and Information Technologies (ICICIT): sign in and open the full text from this page.
Who wrote this paper?
Minnal Kumar Sathiyamoorthy.
What is the DOI of this paper?
10.1109/icicit69063.2026.11634177, permanently at https://doi.org/10.1109/icicit69063.2026.11634177. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.