Master’s degree1,500 h · Online · 11 modules
Master's in Machine Learning for Maritime Security
This master's programme equips you to detect anomalous patterns and protect the maritime sector from current threats. You will work with AIS, radar and operational data and anomaly detection methods, including model evaluation and the cost of false alarms.
Duration1,500 h
ModeOnline
Start1 December
Modules11
Programme diagnosis
Prior knowledge check
These are the skills this programme gives you. Tick the ones you already master and we will tell you which part of the syllabus is for you.
Your diagnosis
6of 6 to cover
You are starting from scratch in this subject. The programme is designed precisely for that.
About the programme
What is the Master's in Machine Learning for Maritime Security?
This online master's degree of 1,500 hours prepares you to protect the maritime sector from current threats. You will learn to detect anomalous patterns in navigation data, anticipate cybersecurity risks on ships and in ports, and optimise emergency response. It combines machine learning theory with practical cases.
What makes it different: a focus on maritime applications, access to anonymised datasets, and work with tools such as Python and TensorFlow.
Programme typeMaster’s degree
ModeOnline
Duration1,500 hours
Modules11
Start1 December
Programme highlights
- Advanced predictive analytics for the early detection of threats.
- Comprehensive maritime security: protection of ships, ports and routes.
- Visualisation of geospatial data on interactive maps.
- Practical cases and simulations of real situations in the sector.
- A career boost in maritime security.
Syllabus
Syllabus of the Master's in Machine Learning for Maritime Security
11 modules. Select a module to see its content.
Module 1
Fundamentals of Machine Learning and Data Science for the Maritime Domain
- 1.1. Introduction to Machine Learning in the maritime industry: use cases in safety, surveillance and emergency response
- 1.2. Pre-processing, cleaning and imputation of noisy marine data (radar, sonar, GNSS and IoT sensors)
- 1.3. Applied supervised learning algorithms: Regression, Decision Trees, Random Forest and SVM
- 1.4. Unsupervised learning algorithms: Clustering (K-Means, DBSCAN) for traffic patterns and anomaly detection
- 1.5. Fundamentals of Deep Learning: multilayer perceptron and advanced architectures
- 1.6. Model evaluation and validation: performance metrics (precision, recall, ROC-AUC) for rare risk events
- 1.7. Tools and libraries of the Python ecosystem (Scikit-Learn, TensorFlow, PyTorch, Pandas, GeoPandas)
- 1.8. Ingestion and management of real-time data streams (Data Streaming) for maritime control environments
- 1.9. MLOps principles: deployment, monitoring and updating of models in rescue coordination centres and on ships
- 1.10. Ethics, bias and AI explainability (XAI - SHAP/LIME) in critical navigation decision-making
At this stage
136 hestimated workload11 wkweeks at your paceModule 2
Anomaly Detection and Identification of Irregular Maritime Traffic (AIS/Radar)
- 2.1. Structure and large-scale processing of AIS (Automatic Identification System) and VMS (Vessel Monitoring System) data
- 2.2. Trajectory alignment and reconstruction algorithms using Kalman Filters and Recurrent Neural Networks (RNN/LSTM)
- 2.3. Detection of transponder switch-offs (Dark Vessels) and suspicious behaviour using Machine Learning
- 2.4. Identification of illegal, unreported and unregulated (IUU) fishing through spatio-temporal pattern analysis
- 2.5. Unsupervised models (Isolation Forest, Autoencoders) to identify unintentional or malicious route deviations
- 2.6. Automatic classification of vessel types based on kinematics and manoeuvring patterns
- 2.7. Detection of GPS/AIS identity spoofing and falsification of maritime positions
- 2.8. Traffic density modelling and dynamic heat maps of collision risk
- 2.9. Integration of coastal radar and synthetic aperture radar (SAR) data with telematic signals
- 2.10. Early warning systems for detecting drug trafficking, smuggling and piracy on the high seas
At this stage
136 hestimated workload11 wkweeks at your paceModule 3
Computer Vision and Automatic Target Recognition at Sea
- 3.1. Fundamentals of Computer Vision applied to the marine environment: optical challenges (glare, waves, fog, reflection)
- 3.2. Real-time detection and segmentation of marine objects with YOLO, Faster R-CNN and Mask R-CNN architectures
- 3.3. Vessel classification from electro-optical (EO) and infrared (IR/FLIR) imagery
- 3.4. Processing of optical satellite imagery and Synthetic Aperture Radar (SAR) for global ocean surveillance
- 3.5. Automatic identification of obstacles, castaways, drifting containers and marine fauna
- 3.6. Multi-object tracking (MOT) algorithms in video sequences from on-board cameras
- 3.7. Computer vision applied to autonomous berthing and navigation in narrow channels
- 3.8. Detection of oil spills and plastic pollution using multispectral imagery
- 3.9. Fusion of imagery with kinematic data for immersive situational awareness on the bridge
- 3.10. Optimisation of vision models for execution on Edge devices (Edge AI) installed on drones and buoys
At this stage
136 hestimated workload11 wkweeks at your paceModule 4
Collision Prevention and Zero-Risk Autonomous Navigation (COLREGs)
- 4.1. Mathematical formalisation and interpretation of the COLREG Convention (International Regulations for Preventing Collisions at Sea)
- 4.2. Calculation of the Ship Domain and collision risk metrics (CPA - Closest Point of Approach, TCPA)
- 4.3. Reinforcement Learning for dynamic decision-making in evasive manoeuvres
- 4.4. Safe path planning algorithms under environmental and traffic constraints
- 4.5. Intelligent navigation support and assistance systems (Decision Support Systems - DSS)
- 4.6. Simulation of multi-vessel encounter scenarios and resolution of extreme danger situations
- 4.7. Physics-Informed Neural Networks (PINNs) for modelling the dynamic behaviour of the ship
- 4.8. Assessment of the human factor and fatigue analysis through biometric monitoring and AI visualisation
- 4.9. Integration of AI with the Long-Range Identification and Tracking System (LRIT)
- 4.10. Validation and certification of autonomous navigation algorithms according to IMO guidelines (MASS ships)
At this stage
136 hestimated workload11 wkweeks at your paceModule 5
Weather Forecasting, Sea State Modelling and Safe Routing
- 5.1. Machine Learning models for rapid forecasting of extreme weather events (sudden squalls, hurricanes, fog)
- 5.2. Processing of oceanographic data: sea surface temperature, salinity, currents and significant wave height
- 5.3. Machine learning algorithms for forecasting the drift of objects, disabled vessels and spills
- 5.4. Weather Routing to minimise the risk of heavy-weather damage
- 5.5. Detection and forecasting of sea ice and iceberg formation using SAR imagery and ML
- 5.6. Modelling of rogue waves using deep learning algorithms
- 5.7. Detection of resonance and capsizing risk due to loss of dynamic stability (Parametric Rolling)
- 5.8. Fusion of traditional numerical forecasts (ECMWF, NOAA) with AI-corrected models
- 5.9. Estimation of wave impact forces on offshore structures and ports
- 5.10. Generation of interactive weather risk maps and real-time route recommendations
At this stage
136 hestimated workload11 wkweeks at your paceModule 6
Predictive Maintenance, Ship Health and Operational Safety
- 6.1. Structural Health Monitoring of the hull: detection of fatigue, cracks and deformation
- 6.2. Predictive maintenance of the propulsion plant (main and auxiliary engines and turbochargers) with IoT sensors
- 6.3. Vibration and lubrication data analysis with incipient fault classification algorithms
- 6.4. Estimation of the Remaining Useful Life (RUL) of critical ship components using time-series regression models
- 6.5. Monitoring of the steering gear, servomotors and propellers to prevent loss of manoeuvrability
- 6.6. Fault detection in fire-extinguishing systems, hatch watertightness and bilge pumps
- 6.7. Assessment of the condition of batteries and hybrid/electric propulsion systems in modern ships
- 6.8. Analytics of marine black box data (VDR - Voyage Data Recorder) for safety audits
- 6.9. Automation of preventive maintenance plans and emergency spare parts supply
- 6.10. Data-driven Digital Twins for real-time assessment of ship safety
At this stage
136 hestimated workload11 wkweeks at your paceModule 7
Maritime Cybersecurity and Protection of Critical Infrastructure
- 7.1. Analysis of the cyber threat landscape in the maritime sector: ships, ports and shipping canals
- 7.2. Detection of intrusions and anomalies in on-board OT/IT networks (CAN Bus, NMEA, Modbus) using ML
- 7.3. Protection of positioning systems (GPS/GNSS) against Spoofing and Jamming attacks with AI
- 7.4. Cybersecurity in autonomous and cloud-connected ships using Zero Trust architectures and AI
- 7.5. Analysis of the cyber behaviour of crew members and control centre staff (Phishing and data leak detection)
- 7.6. Predictive models of cyber-physical risk in port infrastructure and automated terminals
- 7.7. Detection of ransomware and malware targeting maritime industrial control systems (ICS/SCADA)
- 7.8. Maritime Cyber Threat Intelligence through text mining and NLP
- 7.9. Automated response protocols for cyber incidents on board during navigation
- 7.10. Maritime cybersecurity regulations (IMO Resolution MSC.428(98), ISO/IEC 27001, NIS 2)
At this stage
136 hestimated workload11 wkweeks at your paceModule 8
Search and Rescue (SAR) and Smart Emergency Management
- 8.1. Optimisation of Search and Rescue (SAR) operations through algorithmic prediction of search areas
- 8.2. Autonomous coordination of drone swarms (UAV) and unmanned surface vehicles (USV) in rescue missions
- 8.3. Thermal and visual detection of persons in the water (MOB - Man Overboard) using Edge AI algorithms
- 8.4. Emergency evacuation planning on passenger ships using agent-based simulation and ML
- 8.5. Algorithms for prioritising and allocating rescue resources in maritime disasters
- 8.6. Analysis of distress calls (Mayday) and voice communications with Natural Language Processing
- 8.7. Fire risk management on board: prediction of fire and smoke spread across decks
- 8.8. Integration of early warning systems with Cospas-Sarsat satellite networks
- 8.9. Damage assessment after collision or grounding using machine learning models
- 8.10. Analysis of historical maritime accident data for the continuous improvement of rescue protocols
At this stage
136 hestimated workload11 wkweeks at your paceModule 9
Port Security, Maritime Border Control and Global Maritime Management
- 9.1. Smart monitoring of port access points and restricted areas using facial and licence plate recognition
- 9.2. Automated container inspection: non-destructive X-ray/gamma analysis using Deep Learning imaging
- 9.3. Detection of stowaways, human trafficking and illicit goods in port facilities
- 9.4. Ship risk assessment prior to port entry (smart Port State Control)
- 9.5. Predictive models of port congestion and accident prevention in anchorage areas
- 9.6. Environmental safety in ports: monitoring of air quality, noise and accidental spills
- 9.7. Security coordination at the ship-port interface (ISPS Code)
- 9.8. Geopolitical intelligence and risk assessment of shipping routes in conflict zones
- 9.9. AI-enhanced Vessel Traffic Services (VTS) information and management systems
- 9.10. International governance, data privacy on the high seas and regulation of Artificial Intelligence in security
At this stage
136 hestimated workload11 wkweeks at your paceModule 10
Ethics, Explainability and Operational Deployment of Machine Learning Models
- 10.1. Maritime data quality for training
- 10.2. Model bias and robustness
- 10.3. Explainability and interpretability
- 10.4. Model validation and testing
- 10.5. MLOps and production deployment
- 10.6. Edge computing on board
- 10.7. Model drift monitoring
- 10.8. AI regulation
- 10.9. Accountability and human oversight
- 10.10. Operational deployment project
At this stage
136 hestimated workload11 wkweeks at your paceModule 11
Master's Final Project: Intelligent Maritime Safety and Security System
- 11.1. Definition of a real case study in the field of maritime safety and security (prevention, surveillance, SAR or cybersecurity)
- 11.2. Selection, collection and structuring of marine datasets (AIS, satellite imagery, sensors)
- 11.3. Design of the Machine Learning or Deep Learning architecture to solve the stated problem
- 11.4. Training, hyperparameter tuning and optimisation of the models developed
- 11.5. Integration of components into a real-time Data Pipeline
- 11.6. Development of the user interface / operational dashboard for rescue coordination centres or ship bridges
- 11.7. Experimental validation of the system using unseen data and simulations of critical scenarios
- 11.8. Assessment of the impact on risk reduction, operating costs and response times
- 11.9. Writing of the technical and executive report in accordance with academic and industry standards
- 11.10. Public presentation, live demonstration of the model and oral defence before the expert panel
At this stage
136 hestimated workload11 wkweeks at your pacePlan your pace
Duration and format of the Master's in Machine Learning for Maritime Security
It is 1,500 hours. Tell us how many you can study each week and we will tell you when you will really finish.
4 h30 h
With 12 h per week
29
months to finish
125 weeks
weeks in total
This is the pace at which most students finish. It fits well with the instalment plan.
Faculty
Academic leadership and faculty
The Navalis teaching team: working professionals who teach and supervise the programmes.
Dra. Marina AlcoverAcademic Director and Head of Quality Assurance
Ing. Diego CifuentesSenior Lecturer in Naval Welding and Non-Destructive Testing; Head of QA/QC for Welded Joints
Cap. Javier Abaroa (MCA)Senior Lecturer in Ship Handling, Electronic Navigation (ECDIS/Radar/ARPA) and GMDSS; STCW Compliance and Bridge Resource Management Coordinator
Dr. Pau FerrerSenior Lecturer in Naval Architecture and Simulation; Director of the Hydrodynamics and CFD Laboratory
Dra. Nuria LlobregatSenior Lecturer in Marine Meteorology, SAR and Operational Safety; Navigation Risk Management Coordinator
Ing. Javier BañulsSenior Lecturer in Electrical Engineering, Automation and ETO Engineering; Electronic Integration and Engine Alarms Coordinator
Ing. Sofía MarquinaSenior Lecturer in Materials, Composites and Corrosion Protection; Coordinator of the Advanced Paints and Coatings Line
Ing. Tomás RieraSenior Lecturer in Propulsion, Alternative Energy and Hybrid Systems; Energy Performance and Vibration CoordinatorObjectives
Objectives of the Master's in Machine Learning for Maritime Security
01Detect and predict suspicious activity in real time.
02Optimise risk management in maritime operations.
03Automate the identification of anomalies in maritime traffic.
04Develop predictive models to prevent maritime incidents.
05Improve the efficiency of maritime emergency response.
06Strengthen the cybersecurity of critical maritime infrastructure.
Careers
Career opportunities after the Master's in Machine Learning for Maritime Security
Frequently asked questions
Questions about the Master's in Machine Learning for Maritime Security
Maritime safety and security
Yes. The programme includes ECDIS/Radar-ARPA/BRM with port, ocean, fog, heavy-weather and SAR scenarios.
Online with live sessions; hybrid option for simulator stays/internships through partnership agreements.
Predicting and preventing collisions by analysing radar, AIS and weather data.
Functional SMCP is recommended. We provide support materials for standard phraseology.
Yes, with a related qualification or experience in maritime/port operations. The admission interview will confirm your suitability.
Optional (3–6 months) through Companies & Partnerships and the Alumni Network.
Simulator exercises (rubrics), passage plans, SOPs, checklists, micro-tests and an applied master's thesis.
Related programmes
More programmes in Innovation and startups
Short course · 300 hCourse in Generative AI for Shipping Companies and Ports₹43,500 · View programme →Master’s degree · 1,500 hMaster's in 3D Modelling and Virtual Reality for Naval Engineering₹179,000 · View programme →Master’s degree · 1,500 hMaster's in Digital Twins for Ships and Ports₹312,000 · View programme →
Online admission
Admission process
No waiting for a call back. If your documents are in order, you can enrol in the same session.
Entry requirements
- Profile: a degree in mathematics, statistics, computer engineering, physics or a related field, or accredited professional experience in data science, software development or maritime security analysis.
- Language: advanced technical English recommended.
- Technical knowledge: basic programming (preferably Python), statistics and linear algebra.
- Documentation: CV, copy of your qualification, academic transcript where applicable, identity document or passport, and a motivation letter.
- Technical requirements for online study: a computer with camera and microphone, a stable connection and access to data analysis and machine learning software (free or open-source alternatives are available).
- 01ApplicationYour details, background and documents.
- 02Instant reviewWe check that everything is complete and in order.
- 03EnrolmentChoose full payment or instalments and reserve your place.
Start my applicationFrom ₹81,000 deposit
Admission is provisional until the committee validates the documents provided. If you do not meet the requirements, the full amount is refunded.
Any questions?
Ask us before you enrol
Leave your details and admissions will write to you to answer any questions. If you are already sure, you can apply and pay in the same session.