TinyFireNet: a lightweight hybrid CNN with physics-constrained spectral gate for on-board wildfire detection in multispectral satellite imagery
Vibroengineering Procedia · 01.11.2026 · 64 · 265-271
DOI: 10.21595/vp.2026.26610 ↗Kurz gefasst
Fachartikel in der Zeitschrift Vibroengineering Procedia, online erschienen am 01.11.2026. Verfasst von Gulmira Zhulamanova. Die Arbeit nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate and timely detection of active wildfires from spaceborne multispectral sensors is impeded by high false-positive (FP) rates on industrially developed land, where elevated shortwave-infrared (SWIR) reflectance and thermal emission from heated structures mimic spectral fire signatures. This paper presents TinyFireNet – a lightweight seven-channel convolutional neural network with 407,106 parameters (1.63 MB float32, 0.41 MB INT8) designed for patch-level three-class classification (background, active fire, burn scar), aggregated into per-pixel maps through overlapping sliding-window inference. The network is coupled with a four-stage Physics Gate, a physics-constrained sequential spectral filter based on the Normalised Difference Water Index (NDWI), the Normalised Difference Built-up Index (NDBI), thermal infrared (TIR) brightness temperature, and the Normalised Burn Ratio (NBR). We identify and resolve a previously undescribed Feature Clash in which fresh burn scars are erroneously suppressed by the built-up area mask due to shared shortwave-infrared characteristics; the proposed Conditional Masking augments the NDBI criterion with a NIR reflectance threshold at 0.12 and a TIR arbiter at 312 K. The model is evaluated on 3,000 held-out multispectral patches (Landsat-8/9, seven spectral channels) drawn from 55 wildfire events across six continents. Ground-truth labels were independently cross-validated against ESA FireCCI51 v5.1 and NASA MCD64A1 burned-area products, yielding 94.3 % pixel-level agreement on 18 overlapping scenes – confirming that the Physics-Gate-derived labels are congruent with established baselines and not subject to circular validation. TinyFireNet achieves an Overall Accuracy of 99.6 %, an F1-score of 0.914 for active fire and 0.935 for burn scar, with mean Intersection-over-Union of 0.904, and outperforms a threshold-only NBR baseline (Precision = 0.48) while approaching the F1 performance of a 5.9 M-parameter trimmed U-Net at one-fifteenth the model footprint. Measured inference latency on an ARM Cortex-A53 processor (1.4 GHz, batch size 1) is 18.3±0.6 ms per 64×64 patch in float32 and 1.5±0.1 ms with NEON vectorisation; post-training INT8 quantisation introduces a F1 drop of less than 0.01, confirming suitability for on-board deployment within the KazEOSat Earth observation programme.
Zitieren
APA
Zhulamanova, G. (2026). TinyFireNet: a lightweight hybrid CNN with physics-constrained spectral gate for on-board wildfire detection in multispectral satellite imagery. Vibroengineering Procedia, 64, 265-271. https://doi.org/10.21595/vp.2026.26610
Vancouver
Zhulamanova G. TinyFireNet: a lightweight hybrid CNN with physics-constrained spectral gate for on-board wildfire detection in multispectral satellite imagery. Vibroengineering Procedia. 2026;64:265-271. doi:10.21595/vp.2026.26610
BibTeX
@article{Zhulamanova2026,
author = {Zhulamanova, Gulmira},
title = {TinyFireNet: a lightweight hybrid CNN with physics-constrained spectral gate for on-board wildfire detection in multispectral satellite imagery},
journal = {Vibroengineering Procedia},
year = {2026},
volume = {64},
pages = {265--271},
doi = {10.21595/vp.2026.26610}
}
EUVIMED