Apply now
CourseAerospace, UAM, Drones & Space Applications open

AI validation course in aeronautics

Online course of 300 hours in AI validation in aeronautics, structured in 6 modules covering AI in safety-critical aviation systems, learning assurance, verification techniques, explainability and human factors and system safety and certification, with an assigned technical tutor.

Duration3 months
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute certificate
Enrol now View syllabus Ask an advisor
Virtual lab · try it before you enrol

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.

SIM · LIVE ●
Learning outcomes

What you will be able to do

01

Understand the challenges of machine learning in safety-critical systems.

02

Apply the EASA guidance and its classification by AI level.

03

Define the operational design domain and data requirements.

04

Verify models through testing, robustness analysis and formal methods.

05

Incorporate explainability and human oversight.

06

Integrate AI into the system safety assessment.

07

Prepare a validation and certification plan for an AI-based system.

Profile

Who it's for

  • AI certification engineers.
  • Verification and validation engineers facing machine learning components.
  • System safety specialists.
  • Machine learning engineers working on airborne or ground systems.
  • Regulatory compliance consultants.
  • Aviation authority inspectors.
  • Engineering or science graduates aiming to work for aircraft manufacturers.
Standards & tools

What you'll work with

  • EASA Artificial Intelligence Concept Paper Issue 2 (guidance for machine learning applications in aviation)
  • RTCA DO-178C (software considerations in airborne systems)
  • SAE ARP4754B (development of civil aircraft and systems)
  • SAE ARP4761A (safety assessment process for civil aircraft)
  • Regulation (EU) 2024/1689 (EU Artificial Intelligence Act)
  • ISO/IEC 23894:2023 (AI risk management)
  • ISO/IEC TR 24029-1:2021 (assessment of the robustness of neural networks)
  • ISO/IEC 22989:2022 (AI concepts and terminology)
  • Python with PyTorch
  • Marabou
  • Captum
  • Foolbox
  • MLflow
Syllabus

6 modules

  1. 1.1Particular features of machine learning
  2. 1.2Differences from traditional software
  3. 1.3EASA AI levels
  4. 1.4EASA AI Roadmap
  5. 1.5FAA approaches
  6. 1.6Use cases in the cockpit and on the ground
  7. 1.7Risks of non-deterministic behaviour
  8. 1.8The machine learning lifecycle
  9. 1.9Relationship with DO-178C and ARP4754
  10. 1.10Case study: classifying the AI level of a system
  1. 2.1The concept of learning assurance
  2. 2.2Data requirements management
  3. 2.3Operational design domain
  4. 2.4Data quality and representativeness
  5. 2.5Independence of training and test data
  6. 2.6Model and configuration management
  7. 2.7Implementation verification
  8. 2.8Generalisation and stability
  9. 2.9Evidence documentation
  10. 2.10Workshop: defining an ODD
  1. 3.1Requirements-based testing for models
  2. 3.2Neural network coverage
  3. 3.3Adversarial testing
  4. 3.4Formal verification with solvers
  5. 3.5Local robustness analysis
  6. 3.6Out-of-distribution detection
  7. 3.7Uncertainty quantification
  8. 3.8Run-time monitoring
  9. 3.9Stress testing and edge cases
  10. 3.10Lab: formal verification of a small network
  1. 4.1Operational and development explainability
  2. 4.2SHAP, LIME and Grad-CAM methods
  3. 4.3Human-AI interaction in the cockpit
  4. 4.4Trust and complacency
  5. 4.5Human authority and oversight
  6. 4.6Alert and interface design
  7. 4.7User training
  8. 4.8Transparency towards the authority
  9. 4.9Ethics and accountability
  10. 4.10Practical exercise: explaining a visual detector
  1. 5.1Safety assessment with AI components
  2. 5.2Architectural mitigations
  3. 5.3Monitors and backup systems
  4. 5.4Assignment of assurance levels
  5. 5.5Cybersecurity and data poisoning
  6. 5.6Certification plan
  7. 5.7Interaction with the authority
  8. 5.8Continuous learning and changes
  9. 5.9The European AI Act
  10. 5.10Case study: certification plan for a taxi assistant
  1. 6.1Selection of the AI-based system
  2. 6.2AI level and ODD
  3. 6.3Data requirements
  4. 6.4Learning assurance plan
  5. 6.5Verification and robustness
  6. 6.6Explainability
  7. 6.7Safety assessment
  8. 6.8Certification plan
  9. 6.9Report and presentation
  10. 6.10Final project: final review with the tutor
Methodology, software & labs

How you'll learn

The programme is 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 each intake, so you can combine it with your job.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is Python with PyTorch, Marabou, Captum, Foolbox and MLflow, in free, academic or evaluation versions. Exercises are based on real procedures: defining the ODD of a runway detector, verifying the robustness of a classification network and drawing up a certification plan for an AI-based assistant. Assessment is continuous by module plus the final project.

Standards covered: EASA Artificial Intelligence Concept Paper Issue 2, RTCA DO-178C, SAE ARP4754B, SAE ARP4761A, Regulation (EU) 2024/1689, ISO/IEC 23894:2023, ISO/IEC TR 24029-1:2021, ISO/IEC 22989:2022.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of the EASA Artificial Intelligence Concept Paper Issue 2, RTCA DO-178C and SAE ARP4754B applied to real cases, not as a theoretical annex.
Industry software:Python with PyTorch, Marabou, Captum, Foolbox, MLflow, in free, academic or evaluation versions.
Final project:a validation and certification plan for an AI-based aeronautical system, covering AI level, ODD, learning assurance, verification and safety assessment, reviewed by your tutor.
Flexible format:100% online, no fixed timetables, compatible with full-time work.
Capstone project

Build it end to end

Your final project follows the real engineering workflow, step by step, reviewed by your tutor.

Select the AI system
Choose an AI-based aeronautical system and classify its AI level and ODD.
Specify data requirements
Define the data requirements and the learning assurance plan.
Verify and test robustness
Apply testing, robustness analysis and formal methods to the model.
Assess explainability and safety
Analyse explainability and integrate the AI component into the safety assessment.
Final project
Present the certification plan and report for your tutor's final review.
Career opportunities

Where this takes you

AI certification engineerVerification and validation engineerSystem safety specialistMachine learning engineerRegulatory compliance consultantAviation authority inspector
Admissions & scholarships

Requirements

  • No prior qualification is required.
  • An internet connection and a computer capable of running the programme 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.

Apply now Scholarships
FAQ

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 with PyTorch, Marabou, Captum, Foolbox, MLflow, 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 need an internet connection, a computer capable of running the programme 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.

Keep exploring

Related programmes

See all in Aerospace, UAM, Drones & Space
Course830 $

Aeronautical battery course

Online course of 300 hours in aircraft batteries. 6 modules covering battery electrochemistry, performance and ageing, safety and thermal runaway, battery management systems and integration and…

3 monthsOnlineAerospace, UAM, Drones & Space
Course830 $

Electric propulsion course in space

Online course of 300 hours in electric propulsion in space, structured in 6 modules covering electric propulsion in the space context, electrothermal and electromagnetic technologies, the…

3 monthsOnlineAerospace, UAM, Drones & Space
Course610 $

Domain randomization course in aerospace AI

Online course of 300 hours in domain randomization in aerospace AI. 6 modules covering the simulation-to-reality gap, visual randomisation, dynamics randomisation, advanced methods, and validation and…

3 monthsOnlineAerospace, UAM, Drones & Space
AI validation course in aeronauticsEnrol
Related programmes

More in Aerospace, UAM, Drones & Space

Precision agriculture course with dronesView programme →Course on vibrations in Rotorcraft structuresView programme →Demand forecasting course at UAMView programme →3D Metrology Course for AircraftView programme →UAM Route Planning CourseView programme →SIL (software-in-the-loop) courseView programme →

All Aerospace, UAM, Drones & Space programmes → · How to apply · Fees & financing · Scholarships

Scroll to Top
SEIUM – Institute of Advanced Engineering
Powered by  GDPR Cookie Compliance
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.