AI-Assisted Optimization

From Bayesian Methods to Physics-Informed Neural Networks

Wednesday 10th & Thursday 11th December 2025 | Online Seminar

(3 hours 15 min each day)

08.30 (Los Angeles) | 11:30 (New York)
16:30 (London) | 17:30 (Berlin)

We know that traditional optimization approaches often struggle with expensive-to-evaluate functions, high-dimensional design spaces, and complex multi-physics problems. Bayesian optimization is, however, particularly well-suited for these functions. Meanwhile, physics-informed neural networks (PINNs) are embedding physical laws governing datasets into the learning process, enhancing information quality while enabling robust predictions even when the training data is limited. AI-assisted optimization is here!

Being held in two 3-hour sessions over two days, this online seminar from NAFEMS will bring together leading researchers and practitioners to explore AI-assisted optimization in engineering design across aerospace, materials science, and computational mechanics.

Why Attend?

During the seminar, we’ll be covering:

• Active Learning Strategies: How Bayesian optimization can intelligently select the next design to evaluate, giving a good balance between exploration and exploitation
• Reliability-Based Design: Incorporating uncertainty and reliability into optimization workflows
• Physics-Informed AI: Leveraging PINNs to solve partial differential equations and inverse problems while respecting the fundamental physical principles

You’ll see how these methods are being implemented in organizations like Boeing and DLR in real-world production environments, enabling you to see how you can integrate them into your own CAE workflows.

Who Should Attend?

Simulation engineers, analysts and academics working in design optimization and exploring AI applications in CAE, and engineering managers evaluating AI-driven design

R​egister Today

Preliminary Agenda

Day 1 - Tuesday, 10th December 2025

W​elcome & Introduction
N​adir Ince, GE Vernova

16:30-17:15 GMT
Bayesian Optimization — Using Machine Learning inside Optimization
Prof. Juergen Branke, University of Warwick

Explore the foundations of Bayesian optimization and active learning, understanding how surrogate models and acquisition functions work together to efficiently navigate expensive design spaces.

17:15-18:00 GMT
Best Uses of Physics AI Methods in Aerospace Engineering
Prof. Juan Jose Alonso, Stanford University

Discover practical applications and best practices for integrating physics-based AI methods into aerospace engineering workflows, from aerodynamic optimization to multidisciplinary design.

18:00-18:45 GMT
Integrating Optimization and Machine Learning: Perspective from Boeing Structures
Dr. Vladimir Balabanov, Boeing

Gain industrial perspective on implementing AI-assisted optimization in aerospace applications.

Day 2 - Wednesday, 11th December 2025

W​elcome & Introduction to Day 2
E​dmondo Minisci, Strathclyde University

16:30-17:15 GMT
Advancing Robust Multidisciplinary Design Optimization Through Multi-Fidelity Surrogate Modelling and Artificial Intelligence
Prof. Melike Nikbay, Istanbul Technical University

Learn how to incorporate uncertainty quantification and reliability analysis into optimization frameworks, ensuring robust designs that perform under real-world variability.

17:15-18:00 GMT
Goal-driven Multi-source Active Learning: Advanced Formulations and Applications
Prof. Laura Mainini, Imperial College London

Understand how PINNs integrate governing equations into neural network training, enabling rapid surrogate modelling that respects physical laws and boundary conditions.

18:00-18:45 GMT
Physics-Informed Neural Networks – Concepts and Potentials for Applied Aerodynamics
Simon Wassing, DLR (German Aerospace Center)

Explore advanced PINN applications and implementation strategies from researchers at one of Europe's premier aerospace research institutions.

This online seminar is being hosted in conjunction with the NAFEMS Optimisation Technical Working Group.

Support us ...

We would like to extend an invitation to your company to be part of this event. There are several outstanding opportunities available for your company to sponsor the seminar, giving you maximum exposure to a highly targeted audience of delegates, who are all directly involved in simulation, analysis, and design.

P​lease contact the event organiser
Jo Potts, for further information
jo.potts@nafems.org; +44 (0)1355 225688