Day–Night All-Sky Scene Classification with an Attention-Enhanced EfficientNet

Simple item page
dc.contributor.authorBoonpook, Wuttichai
dc.contributor.authorTorteeka, Peerapong
dc.contributor.authorTorsri, Kritanai
dc.contributor.authorKamthonkiat, Daroonwan
dc.contributor.authorTan, Yumin
dc.contributor.authorSitthi, Asamaporn
dc.contributor.authorKamsing, Patcharin
dc.contributor.authorArunplod, Chomchanok
dc.contributor.authorSawangwit, Utane
dc.contributor.authorNgamcharoensuktavorn, Thanachot
dc.contributor.authorSuksod, Kijnaphat
dc.date.accessioned2026-08-06T10:54:33Z
dc.date.available2026-08-06T10:54:33Z
dc.date.issued2026-02-01
dc.description.abstractAll-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.
dc.identifier.citationISPRS International Journal of Geo Information, 15(2), 2026
dc.identifier.doi10.3390/ijgi15020066
dc.identifier.issn22209964
dc.identifier.other2-s2.0-105031215459
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/17857
dc.sourceISPRS International Journal of Geo Information
dc.subjectall-sky image classification
dc.subjectatmospheric monitoring
dc.subjectdeep learning
dc.subjectEASMNet
dc.subjectEfficientNet
dc.titleDay–Night All-Sky Scene Classification with an Attention-Enhanced EfficientNet
dc.typeArticle

Files

Collections

Research