{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T08:27:28Z","timestamp":1784104048070,"version":"3.55.0"},"reference-count":43,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:00:00Z","timestamp":1768867200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"MUST IV Grant at the University of Massachusetts Dartmouth","award":["N00014-23-1\u20132141"],"award-info":[{"award-number":["N00014-23-1\u20132141"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate prediction of marine visibility is critical for ensuring safe and efficient maritime operations, particularly in dynamic and data-sparse ocean environments. Although visibility reduction is a natural and unavoidable atmospheric phenomenon, improved short-term prediction can substantially enhance navigational safety and operational planning. While deep learning methods have demonstrated strong performance in land-based visibility prediction, their effectiveness in marine environments remains constrained by the lack of fixed observation stations, rapidly changing meteorological conditions, and pronounced spatiotemporal variability. This paper introduces SeADL, a self-adaptive deep learning framework for real-time marine visibility forecasting using multi-source time-series data from onboard sensors and drone-borne atmospheric measurements. SeADL incorporates a continuous online learning mechanism that updates model parameters in real time, enabling robust adaptation to both short-term weather fluctuations and long-term environmental trends. Case studies, including a realistic storm simulation, demonstrate that SeADL achieves high prediction accuracy and maintains robust performance under diverse and extreme conditions. These results highlight the potential of combining self-adaptive deep learning with real-time sensor streams to enhance marine situational awareness and improve operational safety in dynamic ocean environments.<\/jats:p>","DOI":"10.3390\/s26020676","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T11:27:58Z","timestamp":1768908478000},"page":"676","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SeADL: Self-Adaptive Deep Learning for Real-Time Marine Visibility Forecasting Using Multi-Source Sensor Data"],"prefix":"10.3390","volume":"26","author":[{"given":"William","family":"Girard","sequence":"first","affiliation":[{"name":"Computer and Information Science Department, University of Massachusetts Dartmouth, Dartmouth, MA 02747, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1104-1257","authenticated-orcid":false,"given":"Haiping","family":"Xu","sequence":"additional","affiliation":[{"name":"Computer and Information Science Department, University of Massachusetts Dartmouth, Dartmouth, MA 02747, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5131-1509","authenticated-orcid":false,"given":"Donghui","family":"Yan","sequence":"additional","affiliation":[{"name":"Mathematics Department, University of Massachusetts Dartmouth, Dartmouth, MA 02747, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,20]]},"reference":[{"key":"ref_1","unstructured":"Cahir, J. (2024, July 01). History of Weather Forecasting, Britannica. Available online: https:\/\/www.britannica.com\/science\/weather-forecasting\/History-of-weather-forecasting."},{"key":"ref_2","unstructured":"IPCC (2024, October 01). Climate Change 2021: The Physical Science Basis, IPCC Sixth Assessment Report, Working Group 1. Available online: https:\/\/www.ipcc.ch\/report\/ar6\/wg1\/."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Song, M., Wang, J., and Li, R. (2024). The importance of weather factors in the resilience of airport flight operations based on Kolmogorov-Arnold Networks (KANs). Appl. Sci., 14.","DOI":"10.20944\/preprints202409.0800.v1"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.trc.2016.11.022","article-title":"Assessing the impact of reduced visibility on traffic crash risk using microscopic data and surrogate safety measures","volume":"74","author":"Peng","year":"2017","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1017\/S0373463324000377","article-title":"Review of ship navigation safety in fog","volume":"77","author":"Ding","year":"2024","journal-title":"J. Navig."},{"key":"ref_6","first-page":"82","article-title":"Safety measures and practice of ship navigation in restricted visibility base on collision case study","volume":"8","author":"Hu","year":"2023","journal-title":"Am. J. Traffic Transp. Eng."},{"key":"ref_7","unstructured":"UNCTAD (2024, November 15). Review of Maritime Transport 2021, UN Trade & Development. Available online: https:\/\/unctad.org\/publication\/review-maritime-transport-2021."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Jonnalagadda, J., and Hashemi, M. (2020, January 11\u201313). Forecasting atmospheric visibility using auto regressive recurrent neural network. Proceedings of the 2020 IEEE 21st International Conference on Information Reuse and Integration for Data Science (IRI), Las Vegas, NV, USA.","DOI":"10.1109\/IRI49571.2020.00037"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Yang, J., Cui, J., and Huang, M. (2023, January 21\u201323). Extreme weather prediction for highways based on LSTM-CNN. Proceedings of the 2023 5th International Conference on Applied Machine Learning (ICAML), Dalian, China.","DOI":"10.1109\/ICAML60083.2023.00045"},{"key":"ref_10","unstructured":"Gultepe, E., Wang, S., Blomquist, B., Harindra, F., Kreidl, O.P., Delene, D.J., and Gultepe, I. (2024). Generative nowcasting of marine fog visibility in the grand banks area and sable island in Canada. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Hwang, S.-H., Park, S.-K., Park, S.-H., Kwon, K.-W., and Im, T.-H. (2023). RDCP: A real time sea fog intensity and visibility estimation algorithm. J. Mar. Sci. Eng., 12.","DOI":"10.20944\/preprints202311.0319.v1"},{"key":"ref_12","unstructured":"NOAA (2025, August 28). What Is an Operational Forecast System? National Ocean Service, National Oceanic and Atmospheric Administration, Available online: https:\/\/oceanservice.noaa.gov\/facts\/ofs.html."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Girard, W., Xu, H., and Yan, D. (2025, January 5\u20136). Real-time forecasting of marine visibility with self-adaptive deep learning. Proceedings of the 4th IEEE International Conference on Computing and Machine Intelligence (ICMI 2025), Mt. Pleasant, MI, USA.","DOI":"10.1109\/ICMI65310.2025.11141248"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1730","DOI":"10.1016\/j.aap.2011.04.003","article-title":"A study on crashes related to visibility obstruction due to fog and smoke","volume":"43","author":"Ekram","year":"2011","journal-title":"Accid. Anal. Prev."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Niu, W., Gong, B., Mao, X., Zhang, H., Wang, H., He, J., Yang, Q., and Zhang, H. (2024, January 25\u201327). A study on short-term visibility prediction model in Jiangsu province based on random forest. Proceedings of the 2024 9th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA 2024), Chengdu, China.","DOI":"10.1109\/ICCCBDA61447.2024.10569175"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Dabhade, A., Roy, S., Moustafa, M.S., Mohamed, S.A., El Gendy, R., and Barma, S. (2021, January 16\u201317). Extreme weather event (cyclone) detection in India using advanced deep learning techniques. Proceedings of the 2021 9th International Conference on Orange Technology (ICOT), Tainan, Taiwan.","DOI":"10.1109\/ICOT54518.2021.9680663"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1016\/j.engappai.2006.11.016","article-title":"Machine-learning paradigms for selecting ecologically significant input variables","volume":"20","author":"Muttil","year":"2007","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kim, K.-S., Lee, J.-B., Roh, M.-I., Han, K.-M., and Lee, G.-H. (2020). Prediction of ocean weather based on denoising autoencoder and convolutional LSTM. J. Mar. Sci. Eng., 8.","DOI":"10.3390\/jmse8100805"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Krestenitis, M., Orfanidis, G., Ioannidis, K., Avgerinakis, K., Vrochidis, S., and Kompatsiaris, I. (2019). Oil spill identification from satellite images using deep neural networks. Remote Sens., 11.","DOI":"10.3390\/rs11151762"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Khoo, J.J., Lim, K.H., and Pang, P.K. (2022, January 26\u201328). Deep learning super resolution of sea surface temperature on south China sea. Proceedings of the 2022 International Conference on Green Energy, Computing and Sustainable Technology (GECOST), Miri, Malaysia.","DOI":"10.1109\/GECOST55694.2022.10010371"},{"key":"ref_22","first-page":"103975","article-title":"Advanced ship detection and ocean monitoring with satellite imagery and deep learning for marine science applications","volume":"81","author":"Bakirci","year":"2025","journal-title":"Reg. Stud. Mar. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Singhal, M., and Ahmad, G. (2023, January 29\u201331). Deep learning based real time face recognition for university attendance system. Proceedings of the 2023 International Symposium on Devices, Circuits and Systems (ISDCS), Higashihiroshima, Japan.","DOI":"10.1109\/ISDCS58735.2023.10153549"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1093\/comjnl\/bxs025","article-title":"A real-time self-adaptive classifier for identifying suspicious bidders in online auctions","volume":"56","author":"Ford","year":"2012","journal-title":"Comput. J."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Girard, W., Xu, H., and Yan, D. (2024, January 13\u201314). Real-time evolving deep learning models for predicting hydropower generation. Proceedings of the 3rd IEEE International Conference on Computing and Machine Intelligence (ICMI 2024), Mt. Pleasant, MI, USA.","DOI":"10.1109\/ICMI60790.2024.10585701"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1162\/coli_a_00524","article-title":"Bias and fairness in large language models: A survey","volume":"50","author":"Gallegos","year":"2024","journal-title":"Comput. Linguist."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Garrido-Mu\u00f1oz, I., Montejo-R\u00e1ez, A., Mart\u00ednez-Santiago, F., and Ure\u00f1a-L\u00f3pez, L.A. (2021). A survey on bias in deep NLP. Appl. Sci., 11.","DOI":"10.20944\/preprints202103.0049.v1"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1145\/3571070","article-title":"On the implicit bias in deep-learning algorithms","volume":"66","author":"Vardi","year":"2023","journal-title":"Commun. ACM"},{"key":"ref_29","unstructured":"NOAA (2025, January 22). International Comprehensive Ocean-Atmosphere Data Set (ICOADS), National Centers for Environmental Information, Available online: https:\/\/icoads.noaa.gov\/."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"120085","DOI":"10.1016\/j.atmosenv.2023.120085","article-title":"Challenges in detecting clouds in polar regions using a drone with onboard low-cost particle counter","volume":"314","author":"Inoue","year":"2023","journal-title":"Atmos. Environ."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Van Houdt, G., Mosquera, C., and N\u00e1poles, G. (2020). A review on the long short-term memory model. Artif. Intell. Rev., 53.","DOI":"10.1007\/s10462-020-09838-1"},{"key":"ref_32","unstructured":"Staudemeyer, R.C., and Morris, E.R. (2019). Understanding LSTM\u2014A Tutorial into Long Short-Term Memory Recurrent Neural Networks. arXiv."},{"key":"ref_33","unstructured":"(2025, January 22). Climate Data Store, Programme of the European Union. Available online: https:\/\/cds.climate.copernicus.eu\/."},{"key":"ref_34","unstructured":"DECKEE (2025, August 15). What is the Maximum Visibility at Sea? DECKEE Waterway Management Platform. Available online: https:\/\/deckee.com\/blog\/what-is-the-maximum-visibility-at-sea."},{"key":"ref_35","unstructured":"Gupta, S.S., and Panchapakesan, S. (1980). Some Statistical Techniques for Climatological Data, Purdue University."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1002\/env.905","article-title":"Generation of synthetic sequences of half-hourly temperature","volume":"19","author":"Magnano","year":"2008","journal-title":"Environmetrics"},{"key":"ref_37","unstructured":"NOAA (2025, July 20). Historical Hurricane Tracks, NOAA Office for Coastal Management, Available online: https:\/\/coast.noaa.gov\/hurricanes\/#map=4\/32\/-80."},{"key":"ref_38","unstructured":"NWS (2026, January 09). Tropical Cyclone Definitions, National Weather Service (NWS), Available online: https:\/\/www.weather.gov\/mob\/tropical_definitions."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Mahmood, H.N., and Ismail, W. (2020). Visibility parameter in sand\/dust storms\u2019 radio wave attenuation equations: An approach for reliable visibility estimation based on existing empirical equations to minimize potential biases in calculations. Appl. Sci., 10.","DOI":"10.3390\/app10217530"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Liu, L., Wang, Y., and Wang, H. (2021). The performance of three exponential decay models in estimating tropical cyclone intensity change after landfall over China. Front. Earth Sci., 9.","DOI":"10.3389\/feart.2021.792005"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"107750","DOI":"10.1016\/j.rineng.2025.107750","article-title":"A comprehensive review of path planning algorithms for autonomous navigation","volume":"28","author":"Venu","year":"2025","journal-title":"Results Eng."},{"key":"ref_42","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"3668","DOI":"10.1109\/TCYB.2019.2950779","article-title":"A survey of optimization methods from a machine learning perspective","volume":"50","author":"Sun","year":"2020","journal-title":"IEEE Trans. Cybern."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/676\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T11:32:11Z","timestamp":1768908731000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/676"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,20]]},"references-count":43,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26020676"],"URL":"https:\/\/doi.org\/10.3390\/s26020676","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,20]]}}}