Conference paper · 2026 · Open access
Urban Flood Multi-Sensor Data Fusion Early Warning Method Based on Edge Intelligence and Lightweight Deep Learning
International Conference on Advanced Algorithms and Neural Networks (AANN), 447–451 · Published 1 August 2026 · DOI 10.1109/aann71145.2026.11709062
In brief
“Urban Flood Multi-Sensor Data Fusion Early Warning Method Based on Edge Intelligence and Lightweight Deep Learning” is a 2026 conference paper by Liyu Wang, published in International Conference on Advanced Algorithms and Neural Networks (AANN). 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 Advanced Algorithms and Neural Networks (AANN).
- Citations
- 0
- References
- 12
- Authors
- 1
Abstract
Urban surface waterlogging under short-duration heavy rainfall can change within minutes, whereas hydrodynamic models and cloud-based deep learning systems often fail to provide low-latency and reliable on-site warnings. This paper proposes an Edge Spatial-Temporal Lightweight Network (Edge-STLN) for multi-sensor urban flood early warning on edge neural processing units. Rainfall and water-level sequences are aligned by dynamic time warping, while surveillance images are downsampled and converted to HSV space. A temporal branch uses multi-scale dilated one-dimensional convolutions and gated linear units, and a visual branch combines depthwise separable convolution, channel shuffle, and learnable channel shrinkage. Cross-modal features are fused through an outer product and Tucker decomposition. Quantization-aware training and memory rearrangement are then applied for INT8 deployment. On a 5-TOPS edge module, Edge-STLN achieves 50-ms latency, 3.2-MB storage, 2.3-W power consumption, 96.7% recall, a 6.2% false-alarm rate, and only 0.51% accuracy drift after 12 h of continuous operation.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wang, L. (2026). Urban Flood Multi-Sensor Data Fusion Early Warning Method Based on Edge Intelligence and Lightweight Deep Learning. International Conference on Advanced Algorithms and Neural Networks (AANN), 447–451. https://doi.org/10.1109/aann71145.2026.11709062
MLA 9
Wang, Liyu. “Urban Flood Multi-Sensor Data Fusion Early Warning Method Based on Edge Intelligence and Lightweight Deep Learning.” International Conference on Advanced Algorithms and Neural Networks (AANN), 2026, pp. 447–451. https://doi.org/10.1109/aann71145.2026.11709062.
Chicago
Wang, Liyu. 2026. “Urban Flood Multi-Sensor Data Fusion Early Warning Method Based on Edge Intelligence and Lightweight Deep Learning.” International Conference on Advanced Algorithms and Neural Networks (AANN): 447–451. https://doi.org/10.1109/aann71145.2026.11709062.
Harvard
Wang, L. (2026) ‘Urban Flood Multi-Sensor Data Fusion Early Warning Method Based on Edge Intelligence and Lightweight Deep Learning’, International Conference on Advanced Algorithms and Neural Networks (AANN), pp. 447–451. doi:10.1109/aann71145.2026.11709062.
IEEE
L. Wang, “Urban Flood Multi-Sensor Data Fusion Early Warning Method Based on Edge Intelligence and Lightweight Deep Learning,” International Conference on Advanced Algorithms and Neural Networks (AANN), pp. 447–451, 2026, doi: 10.1109/aann71145.2026.11709062.
BibTeX
@inproceedings{wang2026urban,
title = {{Urban Flood Multi-Sensor Data Fusion Early Warning Method Based on Edge Intelligence and Lightweight Deep Learning}},
author = {Wang, Liyu},
booktitle = {International Conference on Advanced Algorithms and Neural Networks (AANN)},
year = {2026},
pages = {447--451},
doi = {10.1109/aann71145.2026.11709062},
url = {https://doi.org/10.1109/aann71145.2026.11709062}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Environmental Science › Global and Planetary Change › Flood Risk Assessment and Management
- sensor fusion
- edge computing
- lightweight deep learning
- dynamic time warping
- surveillance video analysis
- cross-modal feature fusion
- Tucker decomposition
- quantization-aware training
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?
Wang, L. (2026). Urban Flood Multi-Sensor Data Fusion Early Warning Method Based on Edge Intelligence and Lightweight Deep Learning. International Conference on Advanced Algorithms and Neural Networks (AANN), 447–451. https://doi.org/10.1109/aann71145.2026.11709062
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 Advanced Algorithms and Neural Networks (AANN): sign in and open the full text from this page.
Who wrote this paper?
Liyu Wang.
What is the DOI of this paper?
10.1109/aann71145.2026.11709062, permanently at https://doi.org/10.1109/aann71145.2026.11709062. 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.