{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T18:52:15Z","timestamp":1782240735400,"version":"3.54.5"},"reference-count":21,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T00:00:00Z","timestamp":1714089600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Vin\u010da Institute of Nuclear Sciences through the grants by the H2020 VIDIS project Virtual Centre for Distributed Atmospheric Sensing for Reduction of Pollution Pressures","award":["952433"],"award-info":[{"award-number":["952433"]}]},{"name":"Vin\u010da Institute of Nuclear Sciences through the grants by the H2020 VIDIS project Virtual Centre for Distributed Atmospheric Sensing for Reduction of Pollution Pressures","award":["451-03-66\/2024-03\/200017"],"award-info":[{"award-number":["451-03-66\/2024-03\/200017"]}]},{"name":"Ministry of Science, Technological Development and Innovation of the Republic of Serbia","award":["952433"],"award-info":[{"award-number":["952433"]}]},{"name":"Ministry of Science, Technological Development and Innovation of the Republic of Serbia","award":["451-03-66\/2024-03\/200017"],"award-info":[{"award-number":["451-03-66\/2024-03\/200017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>In this study, the idea of using a fully symmetric U-Net deep learning model for forecasting a segmented image of high global aerosol concentrations is implemented. As the forecast relies on historical data, the model used a sequence of the last eight segmented images to make the prediction. For this, the classic U-Net model was modified to use ConvLSTM2D layers with MaxPooling3D and UpSampling3D layers. In order to achieve complete symmetry, the output data are given in the form of a series of eight segmented images shifted by one image in the time sequence so that the last image actually represents the forecast of the next image of high aerosol concentrations. The proposed model structure was tuned by the new FOX metaheuristic algorithm. Based on our analysis, we found that this algorithm is suitable for tuning deep learning models considering their stochastic nature. It was also found that this algorithm spends the most time in areas close to the optimal value where there is a weaker linear correlation with the required metric and vice versa. Taking into account the characteristics of the used database, we concluded that the model is capable of generating adequate data and finding patterns in the time domain based on the ddc and dtc criteria. By comparing the achieved results of this model using the AUC-PR metric with the previous results of the ResNet3D-101 model with transfer learning, we concluded that the proposed symmetric U-Net model generates data better and is more capable of finding patterns in the time domain.<\/jats:p>","DOI":"10.3390\/sym16050525","type":"journal-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T10:56:32Z","timestamp":1714128992000},"page":"525","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Symmetric U-Net Model Tuned by FOX Metaheuristic Algorithm for Global Prediction of High Aerosol Concentrations"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8885-2683","authenticated-orcid":false,"given":"Du\u0161an P.","family":"Nikezi\u0107","sequence":"first","affiliation":[{"name":"Vin\u010da Institute of Nuclear Sciences, National Institute of the Republic of Serbia, University of Belgrade, 11000 Belgrade, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1959-3152","authenticated-orcid":false,"given":"Du\u0161an S.","family":"Radivojevi\u0107","sequence":"additional","affiliation":[{"name":"Vin\u010da Institute of Nuclear Sciences, National Institute of the Republic of Serbia, University of Belgrade, 11000 Belgrade, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3057-9784","authenticated-orcid":false,"given":"Nikola S.","family":"Mirkov","sequence":"additional","affiliation":[{"name":"Vin\u010da Institute of Nuclear Sciences, National Institute of the Republic of Serbia, University of Belgrade, 11000 Belgrade, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3877-5157","authenticated-orcid":false,"given":"Ivan M.","family":"Lazovi\u0107","sequence":"additional","affiliation":[{"name":"Vin\u010da Institute of Nuclear Sciences, National Institute of the Republic of Serbia, University of Belgrade, 11000 Belgrade, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatjana A.","family":"Miljoj\u010di\u0107","sequence":"additional","affiliation":[{"name":"Vin\u010da Institute of Nuclear Sciences, National Institute of the Republic of Serbia, University of Belgrade, 11000 Belgrade, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,4,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Borka, D., and Borka Jovanovi\u0107, V. (2019). Channeling of Protons through Radial Deformed Double Wall Carbon Nanotubes. Atoms, 7.","DOI":"10.3390\/atoms7030088"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1016\/j.physleta.2017.03.029","article-title":"Channeling of protons through radial deformed carbon nanotubes","volume":"381","author":"Borka","year":"2017","journal-title":"Phys. Lett. A"},{"key":"ref_3","unstructured":"Kunin, D., Sagastuy-Brena, J., Ganguli, S., Yamins, D.L.K., and Tanaka, H. (2021). Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics. arXiv."},{"key":"ref_4","unstructured":"Godfrey, C., Brown, D., Emerson, T., and Kvinge, H. (2022). On the Symmetries of Deep Learning Models and their Internal Representations. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"096031","DOI":"10.1103\/PhysRevD.105.096031","article-title":"Symmetry discovery with deep learning","volume":"105","author":"Desai","year":"2022","journal-title":"Phys. Rev. D"},{"key":"ref_6","first-page":"15171","article-title":"Impacts of the Saharan air layer on the physical properties of the Atlantic tropical cyclone cloud systems: 2003\u20132019, Atmos","volume":"21","author":"Luo","year":"2021","journal-title":"Chem. Phys."},{"key":"ref_7","unstructured":"(2024, April 21). Available online: https:\/\/neo.gsfc.nasa.gov\/view.php?datasetId=MODAL2_E_AER_OD&date=2024-03-01."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Guo, Y., Cao, X., Liu, B., and Gao, M. (2020). Cloud Detection for Satellite Imagery Using Attention-Based U-Net Convolutional Neural Network. Symmetry, 12.","DOI":"10.3390\/sym12061056"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Xu, R., Tao, Y., Lu, Z., and Zhong, Y. (2018). Attention-Mechanism-Containing Neural Networks for High-Resolution Remote Sensing Image Classification. Remote Sens., 10.","DOI":"10.3390\/rs10101602"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ma, W., Yang, Q., Wu, Y., Zhao, W., and Zhang, X. (2019). Double-Branch Multi-Attention Mechanism Network for Hyperspectral Image Classification. Remote Sens., 11.","DOI":"10.3390\/rs11111307"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"102871","DOI":"10.1016\/j.sysarc.2023.102871","article-title":"MEALPY: An open-source library for latest meta-heuristic algorithms in Python","volume":"139","author":"Mirjalili","year":"2023","journal-title":"J. Syst. Archit."},{"key":"ref_13","unstructured":"(2024, March 27). Available online: https:\/\/keras.io\/api\/applications\/."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hoffman, J.P., Rahmes, T.F., Wimmers, A.J., and Feltz, W.F. (2023). The Application of a Convolutional Neural Network for the Detection of Contrails in Satellite Imagery. Remote Sens., 15.","DOI":"10.3390\/rs15112854"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Hoffman, J.P., Ackerman, S.A., Liu, Y., Key, J.R., and McConnell, I.L. (2021). Application of a Convolutional Neural Network for the Detection of Sea Ice Leads. Remote Sens., 13.","DOI":"10.3390\/rs13224571"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Nikezi\u0107, D.P., Ramadani, U.R., Radivojevi\u0107, D.S., Lazovi\u0107, I.M., and Mirkov, N.S. (2022). Deep Learning Model for Global Spatio-Temporal Image Prediction. Mathematics, 10.","DOI":"10.3390\/math10183392"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Nikezi\u0107, D.P., Radivojevi\u0107, D.S., Lazovi\u0107, I.M., Mirkov, N.S., and Markovi\u0107, Z.J. (2024). Transfer Learning with ResNet3D-101 for Global Prediction of High Aerosol Concentrations. Mathematics, 12.","DOI":"10.3390\/math12060826"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1030","DOI":"10.1007\/s10489-022-03533-0","article-title":"FOX: A FOX-inspired optimization algorithm","volume":"53","author":"Mohammed","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Blockeel, H., Kersting, K., Nijssen, S., and \u017delezn\u00fd, F. (2013). Machine Learning and Knowledge Discovery in Databases, Springer.","DOI":"10.1007\/978-3-642-40994-3"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"13187","DOI":"10.1007\/s10462-023-10470-y","article-title":"An exhaustive review of the metaheuristic algorithms for search and optimization: Taxonomy, applications, and open challenges","volume":"56","author":"Rajwar","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_21","unstructured":"(2024, March 27). Available online: https:\/\/www.tensorflow.org\/api_docs\/python\/tf\/config\/experimental\/enable_op_determinism."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/16\/5\/525\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:34:19Z","timestamp":1760106859000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/16\/5\/525"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,26]]},"references-count":21,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["sym16050525"],"URL":"https:\/\/doi.org\/10.3390\/sym16050525","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,26]]}}}