Course in Fuel Consumption Prediction Using AI
Online 300-hour course in fuel consumption prediction using AI. 6 modules covering ISO 19030, ISO 15016 and Python with scikit-learn. Assigned tutor and open enrolment.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Identify the physical factors that determine a vessel's fuel consumption.
Prepare and clean operational data from sensors and noon reports.
Train machine learning models to predict fuel consumption.
Interpret predictions using explainability techniques.
Quantify uncertainty and monitor model degradation.
Apply predictions to optimise speed, trim and CII.
Develop a fuel consumption prediction model ready for operation.
Who it's for
- Maritime data scientist looking to specialise in Fuel Consumption Prediction with AI.
- Energy efficiency analyst looking to specialise in Fuel Consumption Prediction with AI.
- Vessel performance engineer looking to specialise in Fuel Consumption Prediction with AI.
- Technical superintendent looking to specialise in Fuel Consumption Prediction with AI.
- MLOps engineer looking to specialise in Fuel Consumption Prediction with AI.
- Shipping decarbonisation consultant looking to specialise in Fuel Consumption Prediction with AI.
- Engineering or science graduates seeking to enter shipping companies.
What you'll work with
- ISO 19030
- ISO 15016
- MARPOL Annex VI
- ISO 8217
- Regulation (EU) 2015/757 on MRV
- ISO 19848
- IMO Resolution MEPC.352(78) on the IIC
6 modules · 300 h
1.1Energy balance of the vessel1.2Hydrodynamic resistance and propulsion1.3Effect of draught and trim1.4Hull and propeller fouling1.5Influence of wind, waves and currents1.6Consumption of auxiliary engines and boilers1.7Properties of marine fuels1.8Consumption measurement with flow meters1.9Common errors in noon reports1.10Practical case study: fuel consumption audit of an oil tanker
2.1Sources: sensors, noon reports and AIS2.2Integration with ERA5 reanalysis meteorological data2.3Outlier removal2.4Filtering of steady states2.5Physical variable engineering2.6Sampling and temporal aggregation2.7Time-based partitioning for validation2.8Detection of sensor drift2.9Dataset documentation2.10Laboratory: cleaning high-frequency data
3.1Linear and polynomial regression as benchmarks3.2Random forests and gradient boosting3.3XGBoost and LightGBM applied to consumption3.4Dense neural networks3.5LSTM sequential models3.6Hybrid physics-data models3.7Hyperparameter tuning3.8MAE, RMSE and MAPE metrics3.9Temporal cross-validation3.10Practice: daily consumption prediction
4.1SHAP values to explain predictions4.2Partial dependence on draught4.3Uncertainty quantification4.4Prediction intervals with quantile regression4.5Extrapolation outside the domain4.6Detection of model degradation4.7Comparison with sea trial curves4.8Confidence requirements of the superintendent4.9Biases by vessel and route4.10Workshop: explanatory report on a model
5.1Speed and trim optimisation5.2Estimation of the hull cleaning effect5.3Voyage consumption forecasting5.4Fuel supply planning5.5Support for CII calculation5.6Verification of consumption claims5.7Production deployment with MLOps5.8Integration into fleet platforms5.9In-service model monitoring5.10Practical case study: AI-driven trim optimisation
6.1Selection of the vessel and objective6.2Data acquisition and cleaning6.3Physics-based reference model6.4Training of candidate models6.5Evaluation and explanation of results6.6Estimation of potential savings6.7Operational deployment plan6.8Limitations and future work6.9Report and presentation6.10Final review with the tutor
How you'll learn
100% online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: students progress at their own pace within the enrolment period, making it possible to combine the course with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is Python with scikit-learn, XGBoost, TensorFlow, SHAP, MLflow, in free, academic or evaluation versions. The trials are studied through real procedures for training a consumption model using real sensor data, explanation of predictions with SHAP values, and estimation of savings from hull cleaning. Assessment is continuous across each module, plus the final integrative project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Identify the physical factors that determine a vessel's fuel consumption.
Prepare and clean operational data from sensors and noon reports.
Train machine learning models to predict fuel consumption.
Interpret predictions using explainability techniques.
Quantify uncertainty and monitor model degradation.
Where this takes you
Requirements
- No prior degree is required.
- Internet connection and a computer capable of running the programme's software.
- Sufficient command of Spanish to follow technical regulatory texts.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme consists of 300 hours in total, spread over 3 to 5 months. That is between 10 and 15 hours a week on average, compatible with a full-time job.
You work with Python with scikit-learn, XGBoost, TensorFlow, SHAP, MLflow. Free, academic or evaluation versions are used, and the tutor indicates the open-source alternative where one exists.
A SEIUM diploma on passing the continuous assessment and the integrative project. It is in-house training, not an official Ministry qualification.
Yes. Modules passed in a course or Postgraduate Diploma in the same area are recognised towards the higher-level programme. Check the recognition policy when you enrol.
Related programmes
Course in Subsea Welding and Advanced Techniques
Online course of 300 hours in subsea welding and advanced techniques. 6 modules covering wet and dry hyperbaric welding, friction and laser techniques, quality, inspection and…
Course in Process Auditing in Shipyards
Online course of 300 h in process auditing in shipyards. 6 modules covering ISO 19011:2018, ISO 9001:2015 and SafetyCulture. Assigned tutor and open enrolment.
Course in Hydrodynamics of Hydrofoils (Foils)
Online 300 h course in hydrodynamics of hydrofoils (foils). 6 modules with HSC Code 2000, the International Code of Safety for High-Speed Craft, DNV-RU-HSLC Rules for…
More in Naval, Offshore & Sports Nautical
All Naval, Offshore & Sports Nautical programmes → · How to apply · Fees & financing · Scholarships