Machine Learning for Aircraft Applications – Online Short Course (Starts 8 September 2025) 8 September 2025 0000 - 0000 Online

Register Now

machine-learning-for-aircraft-applications














  • From 8 September – 13 October 2025 (5.5 Weeks, 11 Classes, 33 Total Hours)
  • Every Monday and Wednesday at 12–3 p.m. Eastern Time (UTC-5) (all sessions will be recorded and available for replay; course notes will be available for download)
  • This new essential course covers reduced-order model (ROM) techniques, focusing on aircraft performance and aerodynamic load analysis
  • All students will receive an AIAA Certificate of Completion at the end of the course

OVERVIEW

This course is designed to provide a comprehensive introduction to the application of reduced-order model (ROM) techniques in aerospace engineering, focusing on aircraft performance and aerodynamic load analysis. The ROM techniques are classified into two categories: data-driven methods based on machine learning (ML); and equations-derived methods based on nonlinear projections (NP). The course aims to equip students with a foundational understanding of ML and NP concepts and practical skills for implementing these approaches in aerospace contexts. By the end of the course, participants will gain knowledge of cutting-edge techniques and their relevance to complex aerospace problems, particularly in predicting steady and unsteady aerodynamic loads, and performing aeroelastic analysis.

The course begins with an introduction to core aerospace engineering problems, focusing on aircraft performance and the complexities involved in aerodynamic and aeroelastic load prediction. There is an overview of steady-state and unsteady aerodynamic modeling approaches. These sessions cover critical topics such as the aerodynamic characteristics of steady and transient flows around aircraft, which are essential for understanding the needs of ROM approaches to accelerate the rate of the design process.

A significant portion of the course is devoted to ROM techniques, which simplify complex aerodynamic and aeroelastic problems into manageable computational tasks. Students will learn about two primary types of ROMs: data-driven ROMs that leverage machine learning algorithms and equations-derived ROMs that rely on projection-based methods. The data-driven ROM segment introduces machine learning techniques such as autoencoders and graph neural networks, highlighting their advantages in handling large datasets with minimal computational cost. Meanwhile, the projection-based ROM session covers techniques such as NP of the residual of the coupled system, which reduces computational complexity without compromising accuracy.

Throughout the course, real-world aerospace applications are emphasized to ensure that participants develop skills that are directly transferable to industry settings. By blending ML techniques with aerospace engineering fundamentals, this course provides a unique perspective on modern aerospace challenges and prepares participants to apply innovative solutions in their careers.

LEARNING OBJECTIVES

  • Define key aerospace engineering problems related to aircraft development.
  • Recognize the complexities in predicting steady-state and unsteady aerodynamic loads.
  • Explain the use of ROMs in complex aerospace computational problems.
  • Understand the foundational concepts of ML and NP and their relevance to aerospace engineering.
  • Differentiate between data-driven ROMs and equations-derived ROMs.
  • Discuss the application of ML techniques like autoencoders and graph neural networks to develop data-driven ROMs.
  • Discuss implementation aspects related to projection-based ROMs.
  • Assess the impact of integrating ROM techniques in real-world aerospace applications, demonstrating practical problem-solving skills.
  • Critically assess the benefits and limitations of using ML and projection methods in aerospace contexts for aircraft load analysis.

AUDIENCE
This course is designed for students and researchers in academia and industry who are focused on advanced topics in aerospace engineering, particularly in aerodynamic load prediction and reduced-order modeling. It also caters to technical decision-makers who seek to understand emerging machine learning and projection-based techniques for future development strategies. The content is tailored to equip participants with both foundational knowledge and practical skills, ensuring they can apply modern machine learning and reduced-order model techniques to real-world aerospace challenges and make informed decisions in research and industrial settings.

COURSE FEES (Sign-In To Register)
- AIAA Member Price: $1295 USD
- Non-Member Price: $1495 USD
- AIAA Student Member Price: $695 USD

Classroom Hours / CEUs: 33 classroom hours, 3.3 CEU/PDH

Cancellation Policy: A refund less a $50.00 cancellation fee will be assessed for all cancellations made in writing prior to 7 days before the start of the event. After that time, no refunds will be provided.

Contact: Please contact Lisa Le or Customer Service if you have questions about the course or group discounts (for 5+ participants).

Frequently Asked Questions

Outline
OUTLINE (with approximate times):

Part I: Introduction (11 hours)

Providing background context (Theory, 1 hour)

Aircraft loads analysis (Theory, 1 hour)

Steady-state aerodynamic models (Theory, 2 hours)

Unsteady aerodynamic models (Theory, 2 hours)

Introduction to aeroelasticity (Theory, 2 hours)

Introduction to reduced order models (Theory, 3 hours)

Part II: Data-driven reduced-order model: machine learning (10 hours)

Introduction to machine learning (Theory, 1 hour)

Regression with multiple input variables (Theory, 1 hour)

Unsteady aerofoil problem (Demo, 0.5 hour)

Introduction to Deep Learning (Neural Networks basics) (Theory, 1 hour)

Deep neural networks (Theory, 1 hour)

Convolutional neural networks (Theory, 1 hour)

Autoencoders (Theory, 1 hour)

Recurrent neural networks (Theory, 1 hour)

Graph neural networks (Theory, 1 hour)

Aerofoil problem with graph neural networks (Demo, 0.5 hour)

Realistic examples (Demo, 1 hour)

Part III: Projection-based reduced-order modelling: equation derived (11 hours)

Introduction to projection-based methods (Theory, 1 hour)

Reduced basis for projection (Theory, 1 hour)

Manipulating a linear dynamical system into a ROM using eigen-mode projection (Demo, 1.5 hours)

Interpolating ROM output (Demo, 1.5 hours)

Retaining dynamic nonlinearities in the reduced space (Theory, 2.5 hours)

Computing nonlinear ROM terms (Demo, 1.5 hours)

Large-scale case studies (Theory, 2 hours)

Part IV: Summary and challenges ahead (1 hour)

Materials

Course Delivery and Materials

  • The course lectures will be delivered via Zoom.
  • All sessions will be available on-demand within 1-2 days of the lecture. Once available, you can stream the replay video anytime, 24/7. All slides will be available for download after each lecture.
  • No part of these materials may be reproduced, distributed, or transmitted, unless for course participants. All rights reserved.
  • Between lectures, the instructors will be available via email for technical questions and comments.
Instructors

Dr. Andrea Da Ronch is a Professor of Aeronautics and Astronautics at the University of Southampton (United Kingdom), ranked #78 in the 2024 QS World University Rankings. He earned his Ph.D. in Aerospace Engineering from the University of Liverpool(United Kingdom), 2012 and M.Sc. in Aeronautical Engineering from Polytechnic University of Milan (Italy) in 2008. He is a Senior Member of AIAA, Member of Royal Aeronautical Society (RAeS), and Member of the RAeS Solent Branch Committee. He has published over 40 refereed journal articles and a book on CFD and ROM.

Dr. David Massegur is a Senior Research Assistant at the University of Southampton (United Kingdom), and Engineering and Machine Learning Consultant, DMAE Technologies. He has a Ph.D. in Aerospace Engineering from the University of Southampton (United Kingdom), 2025 and M.Sc. in Aeronautical Engineering from Polytechnic University of Milan (Italy) in 2006.

Mr. Declan Clifford is a senior research assistant at the University of Southampton, experienced in aeroelasticity, flight dynamics, and reduced order modelling. He is an aeroelasticity researcher for the Airbus ONEheart project.

 

AIAA Training Links