Publication: Day–Night All-Sky Scene Classification with an Attention-Enhanced EfficientNet
0
0
Issued Date
2026-02-01
Resource Type
eISSN
22209964
Scopus ID
2-s2.0-105031215459
Journal Title
ISPRS International Journal of Geo Information
Volume
15
Issue
2
Rights Holder(s)
SCOPUS
Bibliographic Citation
ISPRS International Journal of Geo Information Vol.15 No.2 (2026)
Suggested Citation
Boonpook W., Torteeka P., Torsri K., Kamthonkiat D., Tan Y., Sitthi A., Kamsing P., Arunplod C., Sawangwit U., Ngamcharoensuktavorn T., Suksod K. Day–Night All-Sky Scene Classification with an Attention-Enhanced EfficientNet. ISPRS International Journal of Geo Information Vol.15 No.2 (2026). doi:10.3390/ijgi15020066 Retrieved from: https://hdl.handle.net/20.500.14740/55303
Corresponding Author(s)
Other Contributor(s)
Abstract
All-sky cameras provide continuous hemispherical observations essential for atmospheric monitoring and observatory operations; however, automated classification of sky conditions in tropical environments remains challenging due to strong illumination variability, atmospheric scattering, and overlapping thin-cloud structures. This study proposes EfficientNet-Attention-SPP Multi-scale Network (EASMNet), a physics-aware deep learning framework for robust all-sky scene classification using hemispherical imagery acquired at the Thai National Observatory. The proposed architecture integrates Squeeze-and-Excitation (SE) blocks for radiometric channel stabilization, the Convolutional Block Attention Module (CBAM) for spatial–semantic refinement, and Spatial Pyramid Pooling (SPP) for hemispherical multi-scale context aggregation within a fully fine-tuned EfficientNetB7 backbone, forming a domain-aware atmospheric representation framework. A large-scale dataset comprising 122,660 RGB images across 13 day–night sky-scene categories was curated, capturing diverse tropical atmospheric conditions including humidity, haze, illumination transitions, and sensor noise. Extensive experimental evaluations demonstrate that the EASMNet achieves 93% overall accuracy, outperforming representative convolutional (VGG16, ResNet50, DenseNet121) and transformer-based architectures (Swin Transformer, Vision Transformer). Ablation analyses confirm the complementary contributions of hierarchical attention and multi-scale aggregation, while class-wise evaluation yields F1-scores exceeding 0.95 for visually distinctive categories such as Day Humid, Night Clear Sky, and Night Noise. Residual errors are primarily confined to physically transitional and low-contrast atmospheric regimes. These results validate the EASMNet as a reliable, interpretable, and computationally feasible framework for real-time observatory dome automation, astronomical scheduling, and continuous atmospheric monitoring, and provide a scalable foundation for autonomous sky-observation systems deployable across diverse climatic regions.