Dr. Marina AlcoverAcademic director focused on measurable results and operational excellence in maritime education. Integrates IMO/STCW regulations and ISO 21001/9001 f
Masters · 1500 h · 11 modules
Master's in Artificial Intelligence and Ocean Big Data
The Master's in Artificial Intelligence and Ocean Big Data Prepares you to apply artificial intelligence and large-scale data analysis to understanding and managing the ocean. You will learn to integrate data from satellites, buoy
Duration1500 h
FormatOnline
Starts14 December
Places20 / 20
Prior knowledge
Prior Knowledge Assessment
These are the skills this programme builds. Tick the ones you already have and we will tell you which part of the syllabus is really for you.
Your profile
Tick what you already know to see your result.
Programme overview
What is the Master’s in Artificial Intelligence and Ocean Big Data?
The Master's in Artificial Intelligence and Ocean Big Data
Prepares you to apply artificial intelligence and large-scale data analysis to understanding and managing the ocean. You will learn to integrate data from satellites, buoys, ships, sensors and numerical models, build scalable data pipelines in the cloud, and train and validate machine learning and deep learning models that forecast, classify and detect patterns in the marine environment, with a firm focus on data quality, reproducibility and the responsible use of AI.
Key advantages
- Real ocean data: Hands-on work with open satellite, Argo float, AIS and reanalysis datasets.
- From data to model: Data engineering, machine learning and deployment in one programme.
- Open tools: Python, cloud environments and scientific libraries used in industry.
- Sector case studies: Applications in fisheries, shipping, energy, climate and conservation.
- Your own project: An AI system tackling a real ocean challenge.
Programme type
Master's Degree
Study mode
Online
Duration
1,500 hours
Modules
11
Programme highlights
- Master the data: Manage massive, heterogeneous ocean datasets.
- Train models: Apply machine learning and deep learning to the marine environment.
- Scale in the cloud: Build reproducible data pipelines and platforms.
- Use AI wisely: Assess the uncertainty, bias and limitations of models.
- Boost your career: Open doors to tech companies, research centres and marine agencies.
- Train to turn ocean data into knowledge and decisions with artificial intelligence.
Curriculum
Programme Structure
The programme is structured in 11 modules, listed below in order of study.
01
Foundations of Ocean Data
- The ocean as a data system
- Essential ocean variables
- In situ observation sources
- Remote sensing sources
- Numerical model outputs
- Data on human activity at sea
- NetCDF, HDF5 and Zarr formats
- Metadata and CF conventions
- FAIR principles
- Major international ocean repositories
02
Scientific Programming and Analysis with Python
- Environments and dependency management
- NumPy and vectorised computing
- Pandas for series and tables
- Xarray for multidimensional data
- Geospatial analysis with GeoPandas
- Parallel computing with Dask
- Reproducible Jupyter notebooks
- Version control with Git
- Good practice in scientific code
- Testing and documenting code
03
Data Engineering and Big Data Architectures
- The data lifecycle
- Batch and real-time ingestion
- Data lakes and warehouses
- Cloud object storage
- Analysis-ready data formats
- Data catalogues and STAC
- Workflow orchestration
- Spatial databases
- Streaming sensor data
- Cost and efficiency in the cloud
04
Statistics and Ocean Data Quality
- Applied descriptive statistics
- Automated quality control
- Outlier detection
- Gap filling and interpolation
- Time series analysis
- Spatial statistics and kriging
- Principal component analysis
- Extreme value analysis
- Measurement uncertainty
- Cross-validation against observations
05
Machine Learning for the Ocean
- Types of machine learning
- Feature engineering for ocean variables
- Regression and decision trees
- Random forests and gradient boosting
- Classifying water masses
- Clustering and ocean provinces
- Model selection and tuning
- Evaluation metrics
- Class imbalance
- Model interpretability
06
Deep Learning for Marine Data
- Neural networks and backpropagation
- Convolutional networks for imagery
- Semantic segmentation
- Recurrent networks and LSTMs
- Transformers for time series
- Autoencoders and dimensionality reduction
- Generative models
- Transfer learning
- Training on GPUs
- Regularisation and overfitting
07
Computer Vision for Underwater and Satellite Imagery
- Optical and radar satellite imagery
- Detecting vessels in images
- Mapping coastal habitats
- Detecting oil spills and algal blooms
- Underwater imaging and its limitations
- Automated species identification
- Counting and tracking organisms
- Image labelling and annotation
- Benchmark datasets
- Field validation
08
Physics-Informed and Hybrid AI for Ocean Forecasting
- Limits of purely statistical models
- Emulators of numerical models
- Physics-informed neural networks
- Model bias correction
- AI-based downscaling
- Data assimilation and machine learning
- Wave and current forecasting
- Sea surface temperature forecasting
- Uncertainty quantification
- Emerging Earth system foundation models
09
Sector Applications of Ocean AI
- Fisheries and fleet tracking with AIS
- Detecting illegal fishing
- Ship route optimisation
- Smart port operations
- Offshore renewable energy
- Precision aquaculture
- Monitoring marine protected areas
- Pollution and marine litter
- Coastal climate risk
- Bioacoustics and marine wildlife
10
MLOps, Ethics and AI Governance
- From prototype to production
- Containers and model deployment
- Experiment tracking
- Monitoring and data drift
- APIs and prediction services
- Data security and privacy
- Bias and fairness in models
- Transparency and explainability
- AI regulatory frameworks
- The energy footprint of AI
11
Master's Final Project: An AI System for an Ocean Challenge
- Defining the problem and the users
- State-of-the-art review
- Selecting and sourcing data
- Designing the data architecture
- Data preparation and quality control
- Model development and training
- Evaluation and error analysis
- Deployment prototype
- Writing the dissertation
- Defence before a panel
Workload
Study Time and Workload
1500 hours of study, online and at your own pace. Move the slider to the hours a week you can really put in.
Hours a week8
Weeks to finish—
You finish around—
Who it is for
Graduates in marine science, physics, mathematics, computing or engineering: who want to specialise in AI for the ocean Data scientists and developers: looking to move into the marine and climate sector Oceanographers and researchers: who need advanced data analysis techniques Port, shipping and offshore energy staff: who work with operational data Public body and environmental agency prof
Faculty
Academic direction and faculty
The teaching team at Navalis: working professionals who deliver and oversee the institute's programmes.
Eng. Diego Cifuentes
Cap. Javier Abaroa (MCA)
Dr. Pau Ferrer
Dr. Nuria Llobregat
Eng. Javier Bañuls
Eng. Sofía Marquina
Eng. Tomás Riera
Verified reviews
Student Reviews
Reviews collected and verified by Opynio, not written by us.
Outcomes
Learning Outcomes
- 01Manage ocean big data
- 02Prepare data for AI
- 03Apply machine learning
- 04Develop deep learning models
- 05Deploy solutions in production
- 06Use AI responsibly
Careers
Career Opportunities
01Ocean data scientist: Analysis and modelling at research centres and companies.
02Machine learning engineer: Building models for the marine and climate sector.
03Data engineer: Cloud ocean data platforms and pipelines.
04Maritime intelligence analyst: Monitoring fleets, routes and activity at sea.
05Remote sensing and AI specialist: Products derived from satellite imagery.
06Blue digital transformation consultant: Data projects for ports, energy and public bodies.
Questions
Entry Requirements
Some basic knowledge helps, but the programme includes a scientific Python module that starts from the fundamentals.
Open satellite, buoy, Argo float, AIS and reanalysis data, plus ocean model outputs.
No. The most demanding exercises run in cloud environments and remote notebooks.
Yes, including emulators and hybrid models, presented as a developing field with its own limits and uncertainty.
A complete AI system, from data to a deployed prototype, applied to a real ocean problem.
100% online, with a virtual campus available 24/7, live sessions that are recorded, and tutorials with the teaching staff.
The programme involves 1500 hours of study. You can work at your own pace within the timetable we give you when you enrol.
Each programme has its own start date, shown on this page and confirmed by our admissions team when you enquire.
On completing the programme you receive the Master's in Artificial Intelligence and Ocean Big Data qualification awarded by Navalis Magna Institute.
Online admissions
Admissions Process
No waiting for a phone call. If your documents are complete, you can pay in the same session.
Entry requirements
Academic/professional profile: A degree in marine science, physics, mathematics, statistics, computer science, engineering or a related field; or proven professional experience in data analysis or the marine sector. Language: A good working level of English to follow classes and materials. Technical requirements: A computer with a stable internet connection, an up-to-date browser and a webcam for live sessions and project presentations. Admissions process: Online application, profile review and a short interview with the academic team. We confirm your start date when you enquire.
Questions?
Frequently Asked Questions
Leave your details and admissions will write back. If you already know this is the one, go straight to the application and pay in the same session.