{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:00:54Z","timestamp":1775073654630,"version":"3.50.1"},"reference-count":46,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T00:00:00Z","timestamp":1750118400000},"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>In the evolving landscape of green shipping, the accurate estimation of shaft power is critical for reducing fuel consumption and greenhouse gas emissions. This study presents an explainable machine learning framework for shaft power prediction, utilising real-world Internet of Things (IoT) sensor data collected from nine (9) Very Large Crude Carriers (VLCCs) over a 36-month period. A diverse set of models\u2014ranging from traditional algorithms such as Decision Trees and Support Vector Machines to advanced ensemble methods like XGBoost and LightGBM\u2014were developed and evaluated. Model performance was assessed using the coefficient of determination (R2) and RMSE, with XGBoost achieving the highest accuracy (R2=0.9490, RMSE 888) and LightGBM being close behind (R2=0.9474, RMSE 902), with both substantially exceeding the industry baseline model (R2=0.9028, RMSE 1500). Explainability was integrated through SHapley Additive exPlanations (SHAP), offering detailed insights into the influence of each input variable. Features such as draft, GPS speed, and time since last dry dock consistently emerged as key predictors. The results demonstrate the robustness and interpretability of tree-based methods, offering a data-driven alternative to traditional performance estimation techniques and supporting the maritime industry\u2019s transition toward more efficient and sustainable operations.<\/jats:p>","DOI":"10.3390\/fi17060264","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T10:45:26Z","timestamp":1750157126000},"page":"264","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["An Explainable Machine Learning Approach for IoT-Supported Shaft Power Estimation and Performance Analysis for Marine Vessels"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6805-3203","authenticated-orcid":false,"given":"Yiannis","family":"Kiouvrekis","sequence":"first","affiliation":[{"name":"Mathematics, Computer Science and Artificial Intelligence Lab, Faculty of Public and One Health, University of Thessaly, 43100 Karditsa, Greece"},{"name":"Department of Information Technologies, University of Limassol, Limassol 3020, Cyprus"},{"name":"Business School, University of Nicosia, Nicosia 2417, Cyprus"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4725-3094","authenticated-orcid":false,"given":"Katerina","family":"Gkirtzou","sequence":"additional","affiliation":[{"name":"Institute for Language and Speech Processing, Athena Research Center, 15125 Athens, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2524-2845","authenticated-orcid":false,"given":"Sotiris","family":"Zikas","sequence":"additional","affiliation":[{"name":"Mathematics, Computer Science and Artificial Intelligence Lab, Faculty of Public and One Health, University of Thessaly, 43100 Karditsa, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2186-4567","authenticated-orcid":false,"given":"Dimitris","family":"Kalatzis","sequence":"additional","affiliation":[{"name":"Mathematics, Computer Science and Artificial Intelligence Lab, Faculty of Public and One Health, University of Thessaly, 43100 Karditsa, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4044-6018","authenticated-orcid":false,"given":"Theodor","family":"Panagiotakopoulos","sequence":"additional","affiliation":[{"name":"Department of Management Science and Technology, University of Patras, 26334 Patras, Greece"}]},{"given":"Zoran","family":"Lajic","sequence":"additional","affiliation":[{"name":"Angelicoussis Group, 17674 Athens, Greece"}]},{"given":"Dimitris","family":"Papathanasiou","sequence":"additional","affiliation":[{"name":"Angelicoussis Group, 17674 Athens, Greece"}]},{"given":"Ioannis","family":"Filippopoulos","sequence":"additional","affiliation":[{"name":"Shipping Operations and Computer Science, University of Limassol, Limassol 3086, Cyprus"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1057\/s41271-016-0002-7","article-title":"Transforming Our World: Implementing the 2030 Agenda Through Sustainable Development Goal Indicators","volume":"37","author":"Lee","year":"2016","journal-title":"J. Public Health Policy"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"102173","DOI":"10.1016\/j.trd.2019.11.002","article-title":"How can the maritime industry meet Sustainable Development Goals? An analysis of sustainability reports from the social entrepreneurship perspective","volume":"78","author":"Wang","year":"2020","journal-title":"Transp. Res. Part D Transp. Environ."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"126428","DOI":"10.1016\/j.jclepro.2021.126428","article-title":"Greenhouse gas emissions reduction potential by using antifouling coatings in a maritime transport industry","volume":"295","author":"Farkas","year":"2021","journal-title":"J. Clean. Prod."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"032702","DOI":"10.1063\/5.0150010","article-title":"A comprehensive review of emission reduction technologies for marine transportation","volume":"15","author":"Huang","year":"2023","journal-title":"J. Renew. Sustain. Energy"},{"key":"ref_5","unstructured":"Morob\u00e9, C. (2025, June 01). 3 Examples of How Improved Ship Performance Modelling Can Save Fuel. White Paper, Torqua AI, 2022. Available online: https:\/\/toqua.ai\/whitepapers\/3-examples-of-how-improved-ship-performance-modelling-can-save-fuel."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"111094","DOI":"10.1016\/j.oceaneng.2022.111094","article-title":"Ship performance monitoring using machine-learning","volume":"254","author":"Gupta","year":"2022","journal-title":"Ocean Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"110387","DOI":"10.1016\/j.oceaneng.2021.110387","article-title":"Comparison of supervised machine learning methods to predict ship propulsion power at sea","volume":"245","author":"Lang","year":"2022","journal-title":"Ocean Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"108886","DOI":"10.1016\/j.oceaneng.2021.108886","article-title":"Machine learning for shaft power prediction and analysis of fouling related performance deterioration","volume":"234","author":"Laurie","year":"2021","journal-title":"Ocean Eng."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Kim, D., Lee, S., and Lee, J. (2020). Data-Driven Prediction of Vessel Propulsion Power Using Support Vector Regression with Onboard Measurement and Ocean Data. Sensors, 20.","DOI":"10.3390\/s20061588"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Kriezis, A.C., Sapsis, T., and Chryssostomidis, C. (2022, January 29). Predicting Ship Power Using Machine Learning Methods. Proceedings of the SNAME Maritime Convention, Houston, TX, USA.","DOI":"10.5957\/SMC-2022-065"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"100592","DOI":"10.1016\/j.ijnaoe.2024.100592","article-title":"Interpretable, data-driven models for predicting shaft power, fuel consumption, and speed considering the effects of hull fouling and weather conditions","volume":"16","author":"Kim","year":"2024","journal-title":"Int. J. Nav. Archit. Ocean Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1007\/s00773-014-0273-2","article-title":"Application of ensemble neural networks to prediction of towboat shaft power","volume":"20","author":"Radonjic","year":"2015","journal-title":"J. Mar. Sci. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.oceaneng.2018.07.060","article-title":"Physics-based shaft power prediction for large merchant ships using neural networks","volume":"166","author":"Parkes","year":"2018","journal-title":"Ocean Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"121130","DOI":"10.1016\/j.energy.2021.121130","article-title":"Real-time power prediction approach for turbine using deep learning techniques","volume":"233","author":"Sun","year":"2021","journal-title":"Energy"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kim, D., Handayani, M.P., Lee, S., and Lee, J. (2023). Feature Attribution Analysis to Quantify the Impact of Oceanographic and Maneuverability Factors on Vessel Shaft Power Using Explainable Tree-Based Model. Sensors, 23.","DOI":"10.3390\/s23031072"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kim, Y.C., Kim, K.S., Yeon, S., Lee, Y.Y., Kim, G.D., and Kim, M. (2023). Power Prediction Method for Ships Using Data Regression Models. J. Mar. Sci. Eng., 11.","DOI":"10.3390\/jmse11101961"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/j.oceaneng.2016.11.058","article-title":"Vessels fuel consumption forecast and trim optimisation: A data analytics perspective","volume":"130","author":"Coraddu","year":"2017","journal-title":"Ocean Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"17379","DOI":"10.1007\/s00521-020-05111-2","article-title":"Applying artificial neural networks for modelling ship speed and fuel consumption","volume":"32","author":"Tarelko","year":"2020","journal-title":"Neural Comput. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1016\/j.trd.2017.09.014","article-title":"Predicting ship fuel consumption based on LASSO regression","volume":"65","author":"Wang","year":"2018","journal-title":"Transp. Res. Part D Transp. Environ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1080\/20464177.2024.2371192","article-title":"A fuel consumption prediction model for ships based on historical voyages and meteorological data","volume":"23","author":"Hajli","year":"2024","journal-title":"J. Mar. Eng. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1080\/20464177.2024.2372888","article-title":"Development of comprehensive models for precise prognostics of ship fuel consumption","volume":"23","author":"Le","year":"2024","journal-title":"J. Mar. Eng. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102389","DOI":"10.1016\/j.trd.2020.102389","article-title":"Machine learning approach to ship fuel consumption: A case of container vessel","volume":"84","year":"2020","journal-title":"Transp. Res. Part D Transp. Environ."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"119497","DOI":"10.1109\/ACCESS.2019.2933630","article-title":"Prediction of fuel consumption for enroute ship based on machine learning","volume":"7","author":"Hu","year":"2019","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kim, Y.R., Jung, M., and Park, J.B. (2021). Development of a fuel consumption prediction model based on machine learning using ship in-service data. J. Mar. Sci. Eng., 9.","DOI":"10.3390\/jmse9020137"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Moreira, L., Vettor, R., and Guedes Soares, C. (2021). Neural network approach for predicting ship speed and fuel consumption. J. Mar. Sci. Eng., 9.","DOI":"10.3390\/jmse9020119"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"106282","DOI":"10.1016\/j.oceaneng.2019.106282","article-title":"Machine learning models for predicting ship main engine Fuel Oil Consumption: A comparative study","volume":"188","author":"Gkerekos","year":"2019","journal-title":"Ocean Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"111642","DOI":"10.1016\/j.oceaneng.2022.111642","article-title":"A machine learning approach to improve sailboat resistance prediction","volume":"257","author":"Fahrnholz","year":"2022","journal-title":"Ocean Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"103181","DOI":"10.1016\/j.marstruc.2022.103181","article-title":"A machine learning-based method for prediction of ship performance in ice: Part I. ice resistance","volume":"83","author":"Sun","year":"2022","journal-title":"Mar. Struct."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"110449","DOI":"10.1016\/j.oceaneng.2021.110449","article-title":"Ship speed prediction based on machine learning for efficient shipping operation","volume":"245","author":"Bassam","year":"2022","journal-title":"Ocean Eng."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"106063","DOI":"10.1016\/j.oceaneng.2019.05.045","article-title":"Data-driven ship digital twin for estimating the speed loss caused by the marine fouling","volume":"186","author":"Coraddu","year":"2019","journal-title":"Ocean Eng."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"104214","DOI":"10.1016\/j.trd.2024.104214","article-title":"Prediction of harbour vessel emissions based on machine learning approach","volume":"131","author":"Chen","year":"2024","journal-title":"Transp. Res. Part D Transp. Environ."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"108709","DOI":"10.1016\/j.oceaneng.2021.108709","article-title":"The hybrid path planning algorithm based on improved A* and artificial potential field for unmanned surface vehicle formations","volume":"223","author":"Sang","year":"2021","journal-title":"Ocean Eng."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1016\/j.asoc.2015.07.002","article-title":"A cloud based architecture capable of perceiving and predicting multiple vessel behaviour","volume":"35","author":"Zissis","year":"2015","journal-title":"Appl. Soft Comput."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"114153","DOI":"10.1016\/j.oceaneng.2023.114153","article-title":"Integrated machine learning and probabilistic degradation approach for vessel electric motor prognostics","volume":"275","author":"Aizpurua","year":"2023","journal-title":"Ocean Eng."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1007\/s00773-018-0574-y","article-title":"Statistical modelling of ship operational performance monitoring problem","volume":"24","author":"Soner","year":"2019","journal-title":"J. Mar. Sci. Technol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1007\/s12541-020-00462-1","article-title":"Misalignment detection of a rotating machine shaft using a support vector machine learning algorithm","volume":"22","author":"Lee","year":"2021","journal-title":"Int. J. Precis. Eng. Manuf."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Panagiotakopoulos, T., Filippopoulos, I., Filippopoulos, C., Filippopoulos, E., Lajic, Z., Violaris, A., Chytas, S.P., and Kiouvrekis, Y. (2022, January 18\u201320). Vessel\u2019s trim optimization using IoT data and machine learning models. Proceedings of the 2022 13th International Conference on Information, Intelligence, Systems and Applications (IISA), Rhodes, Greece.","DOI":"10.1109\/IISA56318.2022.9904361"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Filippopoulos, I., and Stamoulis, G. (2017, January 24\u201326). Collecting and using vessel\u2019s live data from on board equipment using \u201cInternet of Vessels (IoV) platform\u201d (May 2017). Proceedings of the 2017 South Eastern European Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM), Rhodes, Greece.","DOI":"10.23919\/SEEDA-CECNSM.2017.8088242"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Filippopoulos, I., Stamoulis, G., and Sovolakis, I. (2018, January 24\u201326). Transferring Structured Data and applying business processes in remote Vessel\u2019s environments using the \u201cInfoNet\u201d Platform. Proceedings of the 2018 South-Eastern European Design Automation, Computer Engineering, Computer Networks and Society Media Conference (SEEDA-CECNSM), Rhodes, Greece.","DOI":"10.23919\/SEEDA-CECNSM.2018.8544918"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Filippopoulos, I., Panagiotakopoulos, T., Skiadas, C., Triantafyllou, S.M., Violaris, A., and Kiouvrekis, Y. (2022, January 18\u201320). Live Vessels\u2019 Monitoring using Geographic Information and Internet of Things. Proceedings of the 13th International Conference on Information, Intelligence, Systems and Applications, IISA 2022, Corfy, Greece.","DOI":"10.1109\/IISA56318.2022.9904408"},{"key":"ref_41","unstructured":"Kreitner, J. (1939). Heave, pitch, and resistance of ships in a seaway. Trans. R. Inst. Nav. Archit., 87."},{"key":"ref_42","unstructured":"(2015). Ships and Marine Technology\u2014Guidelines for the Assessment of Speed and Power Performance by Analysis of Speed Trial Data (Standard No. ISO 15016:2015). Available online: https:\/\/www.iso.org\/standard\/61902.html."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/BF02478259","article-title":"A logical calculus of the ideas immanent in nervous activity","volume":"5","author":"McCulloch","year":"1943","journal-title":"Bull. Math. Biophys."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Shalev-Shwartz, S., and Ben-David, S. (2014). Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press.","DOI":"10.1017\/CBO9781107298019"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201916, New York, NY, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201916, New York, NY, USA.","DOI":"10.1145\/2939672.2939778"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/6\/264\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:53:38Z","timestamp":1760032418000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/6\/264"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,17]]},"references-count":46,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["fi17060264"],"URL":"https:\/\/doi.org\/10.3390\/fi17060264","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,17]]}}}