{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T03:41:00Z","timestamp":1770176460674,"version":"3.49.0"},"reference-count":51,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Faculty of Social Science, Srinakharinwirot University","award":["313\/2566"],"award-info":[{"award-number":["313\/2566"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>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\u2013semantic 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\u2013night 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.<\/jats:p>","DOI":"10.3390\/ijgi15020066","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T13:58:49Z","timestamp":1770127129000},"page":"66","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Day\u2013Night All-Sky Scene Classification with an Attention-Enhanced EfficientNet"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5267-9380","authenticated-orcid":false,"given":"Wuttichai","family":"Boonpook","sequence":"first","affiliation":[{"name":"Department of Geography, Faculty of Social Sciences, Srinakharinwirot University, Bangkok 10110, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7454-6776","authenticated-orcid":false,"given":"Peerapong","family":"Torteeka","sequence":"additional","affiliation":[{"name":"National Astronomical Research Institute of Thailand, Chiang Mai 50180, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2795-806X","authenticated-orcid":false,"given":"Kritanai","family":"Torsri","sequence":"additional","affiliation":[{"name":"Hydro-Informatics Institute, Ministry of Higher Education, Science, Research and Innovation, Bangkok 10900, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daroonwan","family":"Kamthonkiat","sequence":"additional","affiliation":[{"name":"Department of Geography, Faculty of Liberal Arts, Thammasat University, Rangsit Campus, Pathumthani 12120, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0447-8223","authenticated-orcid":false,"given":"Yumin","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Transportation Science and Engineering, Beihang University, Beijing 100191, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0938-8023","authenticated-orcid":false,"given":"Asamaporn","family":"Sitthi","sequence":"additional","affiliation":[{"name":"Department of Geography, Faculty of Social Sciences, Srinakharinwirot University, Bangkok 10110, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6656-8406","authenticated-orcid":false,"given":"Patcharin","family":"Kamsing","sequence":"additional","affiliation":[{"name":"Air-Space Control, Optimization and Management Laboratory, Department of Aeronautical Engineering, International Academy of Aviation Industry, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok 10520, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6613-5600","authenticated-orcid":false,"given":"Chomchanok","family":"Arunplod","sequence":"additional","affiliation":[{"name":"Department of Geography, Faculty of Social Sciences, Srinakharinwirot University, Bangkok 10110, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Utane","family":"Sawangwit","sequence":"additional","affiliation":[{"name":"National Astronomical Research Institute of Thailand, Chiang Mai 50180, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thanachot","family":"Ngamcharoensuktavorn","sequence":"additional","affiliation":[{"name":"Department of Geography, Faculty of Social Sciences, Srinakharinwirot University, Bangkok 10110, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kijnaphat","family":"Suksod","sequence":"additional","affiliation":[{"name":"Department of Geography, Faculty of Social Sciences, Srinakharinwirot University, Bangkok 10110, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"key":"ref_1","unstructured":"Bettonvil, F. (2005, January 15\u201318). A digital all-sky camera. Proceedings of the International Meteor Conference, 24th IMC, Oostmalle, Belgium."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"120495","DOI":"10.1016\/j.atmosenv.2024.120495","article-title":"An improved approach to determine aerosol properties from all-sky camera imagery: Sensitivity to the partially cloud scenes","volume":"327","author":"Scarlatti","year":"2024","journal-title":"Atmos. Environ."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Scarlatti, F., G\u00f3mez-Amo, J.L., Valdelomar, P.C., Estell\u00e9s, V., and Utrillas, M.P. (2023). A machine learning approach to derive aerosol properties from all-sky camera imagery. Remote Sens., 15.","DOI":"10.3390\/rs15061676"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"03008","DOI":"10.1051\/epjconf\/20158903008","article-title":"Weather and atmosphere observation with the ATOM all-sky camera","volume":"89","author":"Jankowsky","year":"2015","journal-title":"EPJ Web Conf."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2847","DOI":"10.5194\/amt-18-2847-2025","article-title":"Star photometry with all-sky cameras to retrieve aerosol optical depth at night-time","volume":"18","author":"Cachorro","year":"2025","journal-title":"Atmos. Meas. Tech."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"109133","DOI":"10.1016\/j.dib.2023.109133","article-title":"MILAN Sky Survey, a dataset of raw deep sky images captured during one year with a Stellina automated telescope","volume":"48","author":"Parisot","year":"2023","journal-title":"Data Brief."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4717","DOI":"10.1109\/JSTARS.2014.2321433","article-title":"Automatic auroral detection in color all-sky camera images","volume":"7","author":"Rao","year":"2014","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_8","unstructured":"Gon\u00e7alves, J.A., Bastos, L., Pinho, J., and Granja, H. (2011, January 1\u20133). Digital aerial photography to monitor changes in coastal areas based on direct georeferencing. Proceedings of the 5th EARSeL Workshop on Remote Sensing of the Coastal Zone, Prague, Czech Republic."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"012027","DOI":"10.1088\/1742-6596\/2734\/1\/012027","article-title":"Development of an All-sky Camera for The Indonesian Sky Patrol Network","volume":"2734","author":"Muztaba","year":"2024","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_10","first-page":"35","article-title":"Long-term all-sky-camera images and evaluated cloud-cover data at Syowa Station, Antarctica","volume":"7","author":"Hirasawa","year":"2023","journal-title":"Polar Data J."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"035002","DOI":"10.1088\/1538-3873\/ac5316","article-title":"Astrometric calibration for all-sky camera with machine learning","volume":"134","author":"Tian","year":"2022","journal-title":"Publ. Astron. Soc. Pac."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.renene.2023.01.111","article-title":"Photovoltaic power electricity generation nowcasting combining sky camera images and learning supervised algorithms in the Southern Spain","volume":"206","author":"Marzo","year":"2023","journal-title":"Renew. Energy"},{"key":"ref_13","first-page":"2201","article-title":"Relative sky radiance from multi-exposure all-sky camera images","volume":"2020","author":"Cachorro","year":"2020","journal-title":"Atmos. Meas. Tech. Discuss."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sun, S., Ernst, J., Sapkota, A., Ritzhaupt-Kleissl, E., Wiles, J., Bamberger, J., and Chen, T. (2014, January 3\u20136). Short term cloud coverage prediction using ground based all sky imager. Proceedings of the 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm), Venice, Italy.","DOI":"10.1109\/SmartGridComm.2014.7007633"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"110003","DOI":"10.1016\/j.engappai.2025.110003","article-title":"Anomaly detection in all-sky images: An approach using robust ensemble modeling of cloud cover fraction and prediction bounds","volume":"143","author":"Fisch","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"100551","DOI":"10.1016\/j.ascom.2022.100551","article-title":"Development of a new hybrid cloud cover detection method for all sky mapping","volume":"38","author":"Akdemir","year":"2022","journal-title":"Astron. Comput."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1175\/1520-0450(2003)042<1421:CCBOAI>2.0.CO;2","article-title":"Cloud coverage based on all-sky imaging and its impact on surface solar irradiance","volume":"42","author":"Pfister","year":"2003","journal-title":"J. Appl. Meteorol. Climatol."},{"key":"ref_18","first-page":"1","article-title":"Development of objective algorithm for cloudiness using all-sky digital camera","volume":"18","author":"Kim","year":"2008","journal-title":"Atmosphere"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Alonso-Montesinos, J. (2020). Real-time automatic cloud detection using a low-cost sky camera. Remote Sens., 12.","DOI":"10.5194\/amt-2019-484"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"33","DOI":"10.11113\/jurnalteknologi.v84.19328","article-title":"Night Time Clouds Detection Above Permatapintar Observatory Using All-Sky Imagery","volume":"84","author":"Azhar","year":"2022","journal-title":"J. Teknol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"4671","DOI":"10.5194\/amt-8-4671-2015","article-title":"An automated cloud detection method based on the green channel of total-sky visible images","volume":"8","author":"Yang","year":"2015","journal-title":"Atmos. Meas. Tech."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Mondrag\u00f3n, R., Alonso-Montesinos, J., Riveros-Rosas, D., and Bonifaz, R. (2020). Determination of cloud motion applying the Lucas-Kanade method to sky cam imagery. Remote Sens., 12.","DOI":"10.3390\/rs12162643"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.atmosres.2012.05.005","article-title":"Cloud detection and classification with the use of whole-sky ground-based images","volume":"113","author":"Kazantzidis","year":"2012","journal-title":"Atmos. Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1016\/j.energy.2014.02.035","article-title":"Sky camera imagery processing based on a sky classification using radiometric data","volume":"68","author":"Alonso","year":"2014","journal-title":"Energy"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tulpan, D., Bouchard, C., Ellis, K., and Minwalla, C. (2017, January 13\u201316). Detection of clouds in sky\/cloud and aerial images using moment based texture segmentation. Proceedings of the 2017 International Conference on Unmanned Aircraft Systems (ICUAS), Miami, FL, USA.","DOI":"10.1109\/ICUAS.2017.7991380"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"199","DOI":"10.5194\/amt-10-199-2017","article-title":"Cloud detection in all-sky images via multi-scale neighborhood features and multiple supervised learning techniques","volume":"10","author":"Cheng","year":"2017","journal-title":"Atmos. Meas. Tech."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3629","DOI":"10.5194\/amt-15-3629-2022","article-title":"An all-sky camera image classification method using cloud cover features","volume":"15","author":"Li","year":"2022","journal-title":"Atmos. Meas. Tech."},{"key":"ref_28","first-page":"11045","article-title":"Automatic cloud-type classification based on the combined use of a sky camera and a ceilometer","volume":"122","year":"2017","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Krauz, L., Janout, P., Bla\u017eek, M., and P\u00e1ta, P. (2020). Assessing cloud segmentation in the chromacity diagram of all-sky images. Remote Sens., 12.","DOI":"10.3390\/rs12111902"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"178","DOI":"10.3847\/1538-3881\/ab744f","article-title":"Cloud identification from all-sky camera data with machine learning","volume":"159","author":"Mommert","year":"2020","journal-title":"Astron. J."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Bhandari, H., Palit, S., Chowdhury, S., and Dey, P. (2021, January 8\u201310). Can a camera tell the weather?. Proceedings of the 2021 36th International Conference on Image and Vision Computing New Zealand (IVCNZ), Tauranga, New Zealand.","DOI":"10.1109\/IVCNZ54163.2021.9653246"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1016\/j.solener.2021.05.056","article-title":"Benchmarking of deep learning irradiance forecasting models from sky images\u2013An in-depth analysis","volume":"224","author":"Paletta","year":"2021","journal-title":"Sol. Energy"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Rajagukguk, R.A., Kamil, R., and Lee, H.-J. (2021). A deep learning model to forecast solar irradiance using a sky camera. Appl. Sci., 11.","DOI":"10.3390\/app11115049"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Rezk, M., Tiwari, V.K., Manandhar, P., Krishnan, V., and Pomares, L.M. (2024, January 12\u201314). A CNN-Based Classifier for Quality Image Selection from Sky Cameras. Proceedings of the 2024 7th International Conference on Signal Processing and Information Security (ICSPIS), Dubai, United Arab Emirates.","DOI":"10.1109\/ICSPIS63676.2024.10812597"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"119814","DOI":"10.1016\/j.enconman.2025.119814","article-title":"Optimizing spatiotemporal prediction accuracy of regional solar irradiance through multi-angle cloud layer 3D reconstruction","volume":"334","author":"Ma","year":"2025","journal-title":"Energy Convers. Manag."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"119735","DOI":"10.1016\/j.renene.2023.119735","article-title":"Enhanced Convolutional Neural Network for solar radiation nowcasting: All-Sky camera infrared images embedded with exogeneous parameters","volume":"221","author":"Ogliari","year":"2024","journal-title":"Renew. Energy"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Sakaino, H., Gaviphatt, N., Insisiengmay, A., Zamora, L., Ningrum, D.F., and Sumantyo, J.T.S. (2023, January 16\u201321). PanopticBlue: Transformer-based Camera Sky-Cloud-Weather Recognition and Classification. Proceedings of the IGARSS 2023\u20142023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA.","DOI":"10.1109\/IGARSS52108.2023.10282314"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Manandhar, P., Tiwari, V.K., Rezk, M., Krishnan, V., and Pomares, L.M. (2024, January 12\u201314). Convolutional Deep Learning hierarchical classifier to identify synoptic sky conditions based on sky images. Proceedings of the 2024 7th International Conference on Signal Processing and Information Security (ICSPIS), Dubai, United Arab Emirates.","DOI":"10.1109\/ICSPIS63676.2024.10812649"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhoolideh Haghighi, M.H., Ghasrimanesh, A., and Khosroshahi, H. (2025). Deep learning-based identification of precipitation clouds from all-sky camera data for observatory safety. arXiv.","DOI":"10.1016\/j.mlwa.2025.100640"},{"key":"ref_40","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_41","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_44","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201322). Squeeze-and-excitation networks. Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (2018, January 8\u201314). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_48","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_49","unstructured":"Dosovitskiy, A. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_50","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 11\u201317). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/15\/2\/66\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T14:05:16Z","timestamp":1770127516000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/15\/2\/66"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":51,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["ijgi15020066"],"URL":"https:\/\/doi.org\/10.3390\/ijgi15020066","relation":{},"ISSN":["2220-9964"],"issn-type":[{"value":"2220-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,3]]}}}