AI-powered Predictive Mobility Modeling Course
Online course of 300 hours in AI predictive models for mobility. 6 modules covering data and prediction problems, statistical models and machine learning, deep learning for mobility, prediction applications, deployment and operation, and a final project, with an assigned technical tutor.
AI-powered Predictive Mobility Modeling Course — studying from Malta
Malta's civil engineering sector is active, driven by ongoing construction, infrastructure upgrades, coastal works and urban regeneration projects across the islands. Demand for civil engineers is closely linked to public works, land development and the modernisation of transport networks. Smart city initiatives, including digital mapping, traffic management and sustainable urban planning, are increasingly relevant. Engineers typically find employment with contractors, consultancies, government departments and utility providers managing infrastructure in a densely populated environment.
Fees for Malta: €743 (Euro), with instalments and employer sponsorship available.
Relevant bodies in Malta
Typical roles
Questions from Malta
Which Maltese bodies regulate civil engineering and related professional practice?
The Chamber of Engineers (KSU) regulates the use of the title 'engineer' in Malta under the Engineering Profession Act. Planning and development matters fall under the Planning Authority, and public works and transport infrastructure involve government agencies including Transport Malta. A SEIUM qualification does not itself grant a regulated title; recognition is decided by employers or the relevant body.
What employers in Malta would value civil, rail or smart city engineering skills?
Malta's construction, infrastructure, consultancy and public sector firms are the main employers, along with transport and utilities bodies. Smart city and digital infrastructure work is growing in some areas. Employers typically look for chartered-level experience and licensing, so a private qualification should be seen as supporting your professional development rather than a substitute for those requirements.
How can I study this while working on site, and what support is there?
The programme is delivered entirely online in English, so you can study from anywhere in Malta without a student visa. Each student has an assigned technical tutor, and the course ends with a final project. Time commitment depends on the programme length, from 300 to 1,900 hours. Ask about instalment payments and employer sponsorship to help manage costs.
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
Formulate mobility prediction problems with real data.
Apply statistical and machine learning models to traffic series.
Develop spatio-temporal deep learning models.
Evaluate models with appropriate metrics and validation.
Interpret results to support management decisions.
Deploy and monitor models in operational environments.
Meet the ethical and regulatory requirements for artificial intelligence.
Who it's for
- Mobility data scientists.
- Machine learning engineers moving into transport applications.
- Transport analysts who want to add predictive modelling to their toolkit.
- Urban AI consultants.
- MLOps engineers.
- Transport planning officers.
- Engineering or science graduates aiming to join transport operators.
What you'll work with
- Regulation (EU) 2024/1689 (EU Artificial Intelligence Act)
- Regulation (EU) 2016/679 (General Data Protection Regulation)
- ISO/IEC 23894 (AI risk management)
- ISO/IEC 42001 (AI management systems)
- Directive (EU) 2019/1024 (open data and re-use of public sector information)
- Delegated Regulation (EU) 2022/670 (EU-wide real-time traffic information services)
- Python (scikit-learn)
- PyTorch
- XGBoost
- MLflow
- Apache Spark
6 modules
1.1Types of prediction in mobility1.2Short-, medium- and long-term horizons1.3Traffic and transport data sources1.4Mobile phone, GPS and ticket validation data1.5Preparing time series1.6Exogenous variables: weather, events and calendar1.7Representing networks as graphs1.8Data bias and representativeness1.9Ethics and privacy in mobility data1.10Case study: data inventory of a city
2.1ARIMA and SARIMA models2.2Regression and generalised linear models2.3Decision trees and random forests2.4Gradient boosting with XGBoost and LightGBM2.5Cross-validation for time series2.6Temporal feature engineering2.7MAE, RMSE and MAPE metrics2.8Interpretability with SHAP2.9Probabilistic forecasting and intervals2.10Lab: traffic count prediction with XGBoost
3.1LSTM and GRU recurrent networks3.2Temporal convolutional networks3.3Graph neural networks3.4DCRNN and STGCN spatio-temporal models3.5Transformers for time series3.6METR-LA and PeMS benchmark datasets3.7Transfer learning between cities3.8Training and hyperparameter tuning3.9Computational cost and efficiency3.10Practical: LSTM network for traffic speed
4.1Public transport demand forecasting4.2Vehicle and station occupancy4.3Bike-sharing demand4.4Journey times and congestion4.5Incident detection4.6Mode choice with machine learning4.7Electric vehicle charging demand4.8Parking occupancy prediction4.9Generating origin-destination matrices4.10Case study: hourly demand at bike-sharing stations
5.1The MLOps life cycle5.2Real-time data pipelines5.3Monitoring data and model drift5.4Retraining and versioning5.5Integration with control centres5.6Explainability for public managers5.7Requirements of the EU AI Act5.8Assessing algorithmic fairness5.9Documentation and model cards5.10Workshop: deploying a model with MLflow
6.1Problem formulation6.2Data acquisition and cleaning6.3Exploratory data analysis6.4Model selection and training6.5Validation and comparison6.6Interpreting results6.7Deployment proposal6.8Conclusions for management6.9Report and presentation6.10Final project: final review with your tutor
How you'll learn
Delivered 100% online on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within the intake, so the programme fits around full-time work.
Each module combines theory, guided reading of the original standards and applied exercises. The working software is Python (scikit-learn), PyTorch, XGBoost, MLflow and Apache Spark, in free, academic or evaluation versions. Exercises are based on real procedures: demand forecasting with real data, model comparison on benchmark datasets and model deployment in test environments. Assessment is continuous by module, plus a final capstone project.
Standards covered: Regulation (EU) 2024/1689; Regulation (EU) 2016/679; ISO/IEC 23894; ISO/IEC 42001; Directive (EU) 2019/1024; Delegated Regulation (EU) 2022/670.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Where this takes you
Requirements
- No prior qualification is required.
- An internet connection and a computer capable of running the programme's software.
- English sufficient to read technical standards.
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 totals 300 hours over 3 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with Python (scikit-learn), PyTorch, XGBoost, MLflow and Apache Spark, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.
A SEIUM Institute certificate, awarded on passing the continuous assessment and the final project. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.
Yes. Modules passed are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.
No prior qualification is required: you only need an internet connection, a computer capable of running the programme's software and English sufficient to read technical standards.
Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.
Related programmes
Innovation Course in Desalination Plants
Online course of 300 hours in innovation in desalination plants, structured in 6 modules covering the state of desalination, membrane and process innovation, energy and decarbonisation,…
Urban Lighting and Nightscape Course
Online course of 300 hours in urban lighting and the night-time landscape, structured in 6 modules covering light and urban perception, lighting technology, functional lighting design,…
Course on Soil-Structure Interaction in Underground Works
Online course of 300 hours in soil-structure interaction in underground works, structured in 6 modules covering ground behaviour around excavations, the convergence-confinement method, interaction models for…
More in Civil, Rail & Smart Cities
All Civil, Rail & Smart Cities programmes → · How to apply · Fees & financing · Scholarships