{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T15:01:01Z","timestamp":1765897261785,"version":"3.48.0"},"reference-count":52,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T00:00:00Z","timestamp":1765843200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Accurate weather classification plays a vital role in disaster management and minimizing economic losses. However, satellite-based weather classification remains challenging due to high inter-class similarity; the computational complexity of existing deep learning models, which limits real-time deployment on resource-constrained edge devices; and the limited interpretability of model decisions in practical environments. To address these challenges, this study proposes SatNet-B3, a quantized, lightweight deep learning framework that integrates an EfficientNetB3 backbone with custom classification layers to enable accurate and edge-deployable weather event recognition from satellite imagery. SatNet-B3 is evaluated on the LSCIDMR dataset and demonstrates high-precision performance, achieving 98.20% accuracy and surpassing existing benchmarks. Ten CNN models, including SatNet-B3, were experimented with to classify eight weather conditions, Tropical Cyclone, Extratropical Cyclone, Snow, Low Water Cloud, High Ice Cloud, Vegetation, Desert, and Ocean, with SatNet-B3 yielding the best results. The model addresses class imbalance and inter-class similarity through extensive preprocessing and augmentation, and the pipeline supports the efficient handling of high-resolution geospatial imagery. Post-training quantization reduced the model size by 90.98% while retaining accuracy, and deployment on a Raspberry Pi 4 achieved a 0.3 s inference time. Integrating explainable AI tools such as LIME and CAM enhances interpretability for intelligent climate monitoring.<\/jats:p>","DOI":"10.3390\/fi17120579","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T14:36:53Z","timestamp":1765895813000},"page":"579","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SatNet-B3: A Lightweight Deep Edge Intelligence Framework for Satellite Imagery Classification"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4126-3826","authenticated-orcid":false,"given":"Tarbia","family":"Hasan","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, North South University, Bashundhara R\/A, Dhaka 1229, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9091-9992","authenticated-orcid":false,"given":"Jareen","family":"Anjom","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, North South University, Bashundhara R\/A, Dhaka 1229, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6163-1645","authenticated-orcid":false,"given":"Md. Ishan Arefin","family":"Hossain","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, North South University, Bashundhara R\/A, Dhaka 1229, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1954-1950","authenticated-orcid":false,"given":"Zia Ush","family":"Shamszaman","sequence":"additional","affiliation":[{"name":"Centre for Digital Innovation, Teesside University, Middlesbrough TS1 3BX, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Shen, D., Zuo, Z., Zhang, X., and Zhao, X. (2023). The impact of weather forecast accuracy on the economic value of weather-sensitive industries. Res. Sq.","DOI":"10.21203\/rs.3.rs-3306307\/v1"},{"key":"ref_2","unstructured":"Allianz (2024). Cyclones: Economic Losses and Impact on the Global Economy, Allianz. Available online: https:\/\/www.allianz.com\/content\/dam\/onemarketing\/azcom\/Allianz_com\/economic-research\/publications\/specials\/en\/2024\/october\/2024-10-09-Cyclones-AZ.pdf."},{"key":"ref_3","unstructured":"Toroman, A. (2025, January 01). 10 Reasons Why You Should Be Using Maritime Weather Forecasts. Available online: https:\/\/spire.com\/blog\/maritime\/10-reasons-why-you-should-be-using-maritime-weather-forecasts\/."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"28","DOI":"10.62012\/mp.v3i2.35388","article-title":"Maritime safety in the digital era as the role of weather monitoring and prediction technology","volume":"3","author":"Kadhafi","year":"2024","journal-title":"Marit. Park J. Marit. Technol. Soc."},{"key":"ref_5","unstructured":"Smit, P.B., Houghton, I.A., Jordanova, K., Portwood, T., Shapiro, E., Clark, D., Sosa, M., and Janssen, T.T. (2020). Assimilation of distributed ocean wave sensors. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"106337","DOI":"10.1016\/j.envsoft.2025.106337","article-title":"A real-time and modular weather station software architecture based on microservices","volume":"186","author":"Bonilla","year":"2025","journal-title":"Environ. Model. Softw."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2973","DOI":"10.1098\/rstb.2010.0158","article-title":"Implications of climate change for agricultural productivity in the early twenty-first century","volume":"365","author":"Gornall","year":"2010","journal-title":"Philos. Trans. R. Soc. Lond. B Biol. Sci."},{"key":"ref_8","first-page":"53","article-title":"Application of Weather Forecasting Apps for Agricultural Development in Bangladesh","volume":"30","author":"Khan","year":"2018","journal-title":"Bangladesh J. Ext. Educ."},{"key":"ref_9","unstructured":"(2025, July 10). Promoting ICT Facilities in Developing Early Warning Response Mechanisms for Cyclone-Exposed Seagoing Fishers in Southwest Bangladesh. Available online: https:\/\/give2asia.org\/promoting-ict-facilities-in-developing-early-warning-response-mechanisms-for-cyclone-exposed-seagoing-fishers-in-southwest-bangladesh\/."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.isprsjprs.2015.10.012","article-title":"Geospatial big data handling theory and methods: A review and research challenges","volume":"115","author":"Li","year":"2015","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Yang, R., Chen, Z., Wang, B., Guo, Y., and Hu, L. (2023). A lightweight detection method for remote sensing images and its Energy-Efficient accelerator on edge devices. Sensors, 23.","DOI":"10.3390\/s23146497"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wei, J., and Cao, S. (2019, January 9\u201311). Application of Edge Intelligent Computing in Satellite Internet of Things. Proceedings of the 2019 IEEE International Conference on Smart Internet of Things (SmartIoT), Tianjin, China.","DOI":"10.1109\/SmartIoT.2019.00022"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Boucetta, A.Y., Baziz, M., Hamdad, L., and Allal, I. (2024, January 15\u201317). Optimizing for Edge-AI Based Satellite Image Processing: A Survey of Techniques. Proceedings of the 2024 IEEE Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS), Oran, Algeria.","DOI":"10.1109\/M2GARSS57310.2024.10537575"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"100178","DOI":"10.1016\/j.bdr.2020.100178","article-title":"Deep learning-based weather prediction: A survey","volume":"23","author":"Ren","year":"2020","journal-title":"Big Data Res."},{"key":"ref_15","unstructured":"Racah, E., Beckham, C., Maharaj, T., Kahou, S.E., and Pal, C. (2016). ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yousaf, R., Rehman, H.Z.U., Khan, K., Khan, Z.H., Fazil, A., Mahmood, Z., Qaisar, S.M., and Siddiqui, A.J. (2023). Satellite Imagery-Based Cloud Classification using Deep Learning. Remote Sens., 15.","DOI":"10.3390\/rs15235597"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Shangguan, Z., Fan, W., Cao, Z., and Wang, J. (2020, January 24\u201327). U-Net for Satellite Image Segmentation: Improving the Weather Forecasting. Proceedings of the 2020 5th International Conference on Universal Village (UV), Boston, MA, USA.","DOI":"10.1109\/UV50937.2020.9426212"},{"key":"ref_18","first-page":"12","article-title":"Segmentation of satellite images using machine learning algorithms for cloud classification","volume":"50","author":"Sebastian","year":"2021","journal-title":"Indian J. Radio Space Phys."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"622","DOI":"10.1016\/j.procs.2021.08.064","article-title":"DeePS at: A deep learning model for prediction of satellite images for nowcasting purposes","volume":"192","author":"Ionescu","year":"2021","journal-title":"Procedia Comput. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1080\/2150704X.2021.1978581","article-title":"Detection of weather events in optical satellite data using deep convolutional neural networks","volume":"12","author":"Li","year":"2021","journal-title":"Remote Sens. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.isprsjprs.2023.09.007","article-title":"A large-scale climate-aware satellite image dataset for domain adaptive land-cover semantic segmentation","volume":"205","author":"Liu","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_22","unstructured":"Ship, E., Spivak, E., Agarwal, S., Birman, R., and Hadar, O. (2024). Real-Time Weather Image Classification with SVM. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Minhas, S., Khanam, Z., Ehsan, S., McDonald-Maier, K., and Hern\u00e1ndez-Sabat\u00e9, A. (2022). Weather Classification by Utilizing Synthetic Data. Sensors, 22.","DOI":"10.3390\/s22093193"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Papadimitriou, O., Kanavos, A., Mylonas, P., and Maragoudakis, M. (2023, January 25\u201326). Advancing Weather Image Classification Using Deep Convolutional Neural Networks. Proceedings of the 2023 18th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP 2023), Limassol, Cyprus.","DOI":"10.1109\/SMAP59435.2023.10255190"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Cao, Y., and Yang, H. (2022, January 20\u201322). Weather Prediction using Cloud\u2019s Images. Proceedings of the 2022 International Conference on Big Data, Information and Computer Network (BDICN), Sanya, China.","DOI":"10.1109\/BDICN55575.2022.00157"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e2020EA001604","DOI":"10.1029\/2020EA001604","article-title":"Classification of weather phenomena from images by using deep convolutional neural network","volume":"8","author":"Xiao","year":"2021","journal-title":"Earth Space Sci."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Dritsas, E., and Trigka, M. (2025). Remote Sensing and Geospatial Analysis in the Big Data Era: A Survey. Remote Sens., 17.","DOI":"10.3390\/rs17030550"},{"key":"ref_28","first-page":"89","article-title":"A Big Data Framework for Satellite Images Processing Using Apache Hadoop and RasterFrames: A Case Study of Surface Water Extraction in Phu Tho, Viet Nam","volume":"11","author":"Nguyen","year":"2020","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"12538","DOI":"10.1109\/TCYB.2021.3080121","article-title":"LSCIDMR: Large-scale satellite cloud image database for meteorological research","volume":"52","author":"Bai","year":"2021","journal-title":"IEEE Trans. Cybern."},{"key":"ref_30","unstructured":"Tan, M., and Le, Q. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Baller, S.P., Jindal, A., Chadha, M., and Gerndt, M. (2021, January 4\u20138). DeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devices. Proceedings of the 2021 IEEE International Conference on Cloud Engineering (IC2E), San Francisco, CA, USA.","DOI":"10.1109\/IC2E52221.2021.00016"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Beltr\u00e1n-Escobar, M., Alarc\u00f3n, T.E., Rumbo-Morales, J.Y., L\u00f3pez, S., Ortiz-Torres, G., and Sorcia-V\u00e1zquez, F.D.J. (2024). A Review on Resource-Constrained Embedded Vision Systems-Based Tiny Machine Learning for Robotic Applications. Algorithms, 17.","DOI":"10.3390\/a17110476"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Andreadis, A., Giambene, G., and Zambon, R. (2023). Low-Power IoT for Monitoring Unconnected Remote Areas. Sensors, 23.","DOI":"10.3390\/s23094481"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Nundloll, V., Porter, B., Blair, G.S., Emmett, B., Cosby, J., Jones, D.L., Chadwick, D., Winterbourn, B., Beattie, P., and Dean, G. (2019). The Design and Deployment of an End-To-End IoT Infrastructure for the Natural Environment. Future Internet, 11.","DOI":"10.3390\/fi11060129"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"180","DOI":"10.56532\/mjsat.v4i2.293","article-title":"IoT-enabled Smart Weather Stations: Innovations, Challenges, and Future Directions","volume":"4","author":"Ganesan","year":"2024","journal-title":"Malays. J. Sci. Adv. Technol."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Li, J., Pei, Y., Zhao, S., Xiao, R., Sang, X., and Zhang, C. (2020). A Review of Remote Sensing for Environmental Monitoring in China. Remote Sens., 12.","DOI":"10.3390\/rs12071130"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Ameen, S., Theodoridis, T., and Siriwardana, K. (2023). Efficient Convolutional Neural Networks on Raspberry Pi: Enhancing Performance with Pruning and Quantization. Res. Sq.","DOI":"10.21203\/rs.3.rs-4345141\/v1"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Balemans, D., Vandersmissen, B., Steckel, J., Mercelis, S., Reiter, P., and Oramas, J. (2024). Deep Learning Model Compression for Resource Efficient Activity Recognition on Edge Devices: A Case Study. Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), SciTePress.","DOI":"10.5220\/0012423300003660"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Garcia-Perez, A., Mi\u00f1\u00f3n, R., Torre-Bastida, A.I., and Zulueta-Guerrero, E. (2023). Analysing Edge Computing Devices for the Deployment of Embedded AI. Sensors, 23.","DOI":"10.3390\/s23239495"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Piovesan, D., Maciel, J.N., Zalewski, W., Gimenez Ledesma, J.J., Cavallari, M.R., and Ando Junior, O.H. (2025). Edge Computing: Performance Assessment in the Hybrid Prediction Method on a Low-Cost Raspberry Pi Platform. Eng, 6.","DOI":"10.3390\/eng6100255"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Antonini, M., Vu, T.H., Min, C., Montanari, A., Mathur, A., and Kawsar, F. (2019). Resource Characterisation of Personal-Scale Sensing Models on Edge Accelerators. Proceedings of the First International Workshop on Challenges in Artificial Intelligence and Machine Learning for Internet of Things (AIChallengeIoT\u201919), ACM.","DOI":"10.1145\/3363347.3363363"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Ahn, H., Chen, T., Alnaasan, N., Shafi, A., Abduljabbar, M., Subramoni, H., and Panda, D.K. (2023). Performance Characterization of Using Quantization for DNN Inference on Edge Devices: Extended Version. arXiv.","DOI":"10.1109\/ICFEC57925.2023.00009"},{"key":"ref_43","unstructured":"(2025, September 14). Raspberry Pi. Wikipedia, Available online: https:\/\/en.wikipedia.org\/wiki\/Raspberry_Pi."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Tang, R., Wang, W., Tu, Z., and Lin, J. (2017). An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting. arXiv.","DOI":"10.1109\/ICASSP.2018.8461624"},{"key":"ref_45","unstructured":"Garreau, D., and Von Luxburg, U. (2020). Explaining the Explainer: A First Theoretical Analysis of LIME. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. arXiv.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., and Torralba, A. (2015). Learning Deep Features for Discriminative Localization. arXiv.","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Franceschini, R.G., Liu, J., and Amin, S. (2021). Damage Estimation and Localization from Sparse Aerial Imagery. arXiv.","DOI":"10.1109\/ICMLA52953.2021.00028"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Chen, T.Y. (2022). Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery. arXiv.","DOI":"10.5194\/egusphere-egu21-13873"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Yan, T., Zhang, N., Li, J., Liu, W., and Chen, H. (2022). Automatic Deployment of Convolutional Neural Networks on FPGA for Spaceborne Remote Sensing Application. Remote Sens., 14.","DOI":"10.3390\/rs14133130"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Salazar, C., Gonzalez-Llorente, J., Cardenas, L., Mendez, J., Rincon, S., Rodriguez-Ferreira, J., and Acero, I.F. (2022). Cloud Detection Autonomous System Based on Machine Learning and COTS Components On-Board Small Satellites. Remote Sens., 14.","DOI":"10.3390\/rs14215597"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhang, Z., Zhu, M., Lv, X., Liao, R., Li, X., and Li, D. (2023). Hardware Acceleration of Satellite Remote Sensing Image Object Detection Based on Channel Pruning. Appl. Sci., 13.","DOI":"10.3390\/app131810111"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/12\/579\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T14:40:12Z","timestamp":1765896012000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/12\/579"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,16]]},"references-count":52,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["fi17120579"],"URL":"https:\/\/doi.org\/10.3390\/fi17120579","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,16]]}}}