[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123541-en":3,"doc-seo-123541-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123541,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Explainable machine learning-based prediction of fuel consumption in ship main engines using operational data","Maritime transportation contributes a major share of global trade while also driving substantial fuel consumption and greenhouse-gas emissions. Accurate main engine fuel consumption prediction supports environmental compliance, reduced operational costs, and improved economic performance. The study builds multiple machine learning prediction models using error and efficiency metrics such as MSE, R², and KlingGupta efficiency, with grid-search hyperparameter optimization. Random Forest achieves the lowest test MSE and strongest accuracy, while XGBoost remains highly competitive. Explainable AI methods using SHAP and LIME enhance interpretability by identifying key drivers (e.g., main engine speed and wind speed) to support transparent decision-making and sustainable shipping.","[journal homepage: www.brodogradnja.fsb.hr](journal homepage: www.brodogradnja.fsb.hr)  \nBrodogradnja  \nAn International Journal of Naval Architecture and Ocean Engineering for Research and Development  \n| Explainable machine learning-based prediction of fuel consumption in ship main engines using operational data |  |  |\n| --- | --- | --- |\n| Anh Tuan Hoang1,2, ThiAnhEmBui3, Xuan Phuong Nguyen4, Van Hung Bui5, Quang Chien Nguyen6,7, Thanh Hai Truong4, Nghia Chung8,*\u003Cbr>1 Faculty of Engineering, Dong Nai Technology University, Bien Hoa City, Vietnam\u003Cbr>2 Graduate School of Energy and Environment, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 02841, South Korea\u003Cbr>3 Institute of Engineering, HUTECH University, Ho Chi Minh City, Vietnam\u003Cbr>4 PATET Research Group, Ho Chi Minh City University of Transport, Ho Chi Minh City, Vietnam\u003Cbr>5 University of Technology and Education, The University of Danang, Danang, Vietnam\u003Cbr>6 Institute of Research and Development, Duy Tan University, Da Nang, Vietnam\u003Cbr>7 School of Engineering & Technology, Duy Tan University, Da Nang, Vietnam\u003Cbr>8 Institute of Maritime, Ho Chi Minh City University of Transport, Ho Chi Minh City, Vietnam |  |  |\n| ARTI CLE INFO\u003Cbr>Keywords:\u003Cbr>Ship fuel consumption\u003Cbr>Prediction model\u003Cbr>Local interpretable model-agnostic explanations\u003Cbr>Shapley additive explanations Explainable artificial intelligence | AB STRACT\u003Cbr>A significant percentage of fuel consumption and emissions from transportation activities is related to maritime transportation. Hence, accurate prediction models for fuel consumption are quite important. Machine learning offers a data-driven approach to improving fuel consumption prediction, thereby promoting environmental sustainability, lowering operational costs, and enhancing financial viability. This work explores several machine learning approaches by employing statistical measures, including mean squared error (MSE), coefficient of determination (R²), and KlingGupta efficiency (KGE), to develop main engine fuel consumption (MEFC) prediction models. Hyperparameter optimization via grid search was conducted to improve the generalizability and robustness of the models. With the lowest test MSE (0.69), a robust testing R² (0.9867), and a high KGE (0.9681), the Random Forests proved to bethe most appropriate model for MEFC modeling among all others. Extreme Gradient Boosting followed closely with competitive accuracy, with MSE values of 0.75 and a robust testing R² (0.9856). Using Shapley additive explanations and Local interpretable model-agnostic explanations, this study improves model interpretability even more and indicates that main engine speed and wind speed were revealed to be the most important factors controlling MEFC. Explainable artificial intelligence techniques offer transparency in decision-making, thereby helping marine operators maximize fuel economy. Employing reliable and interpretable predictive modeling, this study offers insightful information for sustainable shipping, hence lowering operating costs and emissions. |  |\n\n1. Introduction  \nAs the backbone of international trade, maritime transport accounts for over 80% of global trade volume  \nand plays a crucial part in global commerce and economic growth [1, 2] . However, with the expansion of shipping and maritime activities, annual greenhouse gas emissions (GHG) from vessels have surpassed one billion tons [3, 4] . Therefore, the International Maritime Organization (IMO) has implemented various regulatory measures to mitigate emissions, including the Energy Efficiency Design Index (EEDI), the Energy Efficiency Operational Indicator (EEOI), and the Carbon Intensity Indicator (CII), all aimed at improving ship energy efficiency and decreasing GHGs [5-7] . Since 1997, the IMO has enacted progressive policies to address maritime emissions, culminating in the adoption of the Initial GHG Strategy in 2018, and subsequently, the 2023 Revised GHG Strategy [8, 9] . The updated strate","cbCairtb5TCYlEry","https://ap.wps.com/l/cbCairtb5TCYlEry","pdf",2052490,1,24,"English","en",105,"# Introduction\n## Emissions and regulatory context\n## Modeling needs for fuel economy\n# Machine learning prediction and evaluation\n## Metrics and hyperparameter optimization\n## Explainable AI for interpretability\n# Key findings and implications for sustainable shipping","[{\"question\":\"Why is predicting main engine fuel consumption important for maritime operations?\",\"answer\":\"Accurate predictions support environmental sustainability, reduce operating costs, and improve financial viability by enabling better voyage and energy-efficiency decisions.\"},{\"question\":\"Which evaluation metrics are used to assess the prediction models?\",\"answer\":\"Models are evaluated using mean squared error (MSE), coefficient of determination (R²), and KlingGupta efficiency (KGE) on test performance.\"},{\"question\":\"How do explainable AI methods contribute to the study?\",\"answer\":\"SHAP (Shapley additive explanations) and LIME (local interpretable model-agnostic explanations) improve interpretability by revealing which factors most influence MEFC predictions, such as main engine speed and wind speed.\"}]","Explainable machine learning-based prediction of fuel consumption in ship main engines using operational data | PDF",1785817209,60,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"explainable-machine-learning-based-prediction-of-fuel-consumption-in-ship-main-engines-using-operational-data","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/explainable-machine-learning-based-prediction-of-fuel-consumption-in-ship-main-engines-using-operational-data/123541/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is predicting main engine fuel consumption important for maritime operations?","Question",{"text":75,"@type":76},"Accurate predictions support environmental sustainability, reduce operating costs, and improve financial viability by enabling better voyage and energy-efficiency decisions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which evaluation metrics are used to assess the prediction models?",{"text":80,"@type":76},"Models are evaluated using mean squared error (MSE), coefficient of determination (R²), and KlingGupta efficiency (KGE) on test performance.",{"name":82,"@type":73,"acceptedAnswer":83},"How do explainable AI methods contribute to the study?",{"text":84,"@type":76},"SHAP (Shapley additive explanations) and LIME (local interpretable model-agnostic explanations) improve interpretability by revealing which factors most influence MEFC predictions, such as main engine speed and wind speed.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":29,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]