67507 - Integrated Modelling: Advancing Physics-Based Approaches with Data-Driven Techniques (Pilot)

Type of course:

Digital learning, Lesson

Language:

Duration:

30 minutes

Workload:

Array hour

Proficiency:

Intermediate

Target:

Professionals, Students

SUMMARY

Welcome to “Integrated Modelling: Advancing Physics-Based Approaches with Data-Driven Techniques”!

This course is designed to provide you with a deep dive into the world of integrated modelling, where we combine the power of traditional physics-based models with the flexibility and predictive capabilities of data-driven techniques. Whether you’re a researcher, engineer, or scientist, this course will equip you with the tools and knowledge to create more accurate, reliable, and adaptable models.

We’ll begin by laying the foundation, exploring the fundamental concepts behind both physics-based models and data-driven models, and discussing their individual strengths and limitations. You’ll then learn how to integrate these approaches into hybrid models, taking advantage of their combined strengths to address complex challenges in various domains, such as engineering, climate science, and healthcare.

Throughout the course, we’ll cover essential topics like model validation, uncertainty quantification, and the latest tools and frameworks that facilitate hybrid modelling. Real-world examples will help connect theory to practice, showcasing how integrated models are transforming industries and pushing the frontiers of scientific discovery.

By the end of this course, you’ll have a strong understanding of integrated modelling techniques and be ready to apply them to real-world problems, ensuring your models are both accurate and trustworthy.

Let’s get started on this exciting journey to mastering the future of modelling!

About The Author

Ioannis Astli is a Data Scientist at the CORE Innovation Centre, with a strong academic foundation holding an MSci in Computer Engineering. Driven by a deep passion for Artificial Intelligence, he consistently advocates for advancing AI knowledge and its practical applications across various domains.

Learning outcomes

By the end of this course, students will be able to integrate physics-based and data-driven models to develop hybrid models for solving complex problems in at least two application areas (e.g., engineering, healthcare) with 90% accuracy in prediction.
Students will demonstrate proficiency in validating hybrid models using at least two different techniques, including cross-validation and residual analysis, as measured by successful completion of a hands-on activity and quiz with a score of 80% or higher.
By the conclusion of the course, students will be able to apply uncertainty quantification methods (e.g., Monte Carlo simulation, Bayesian inference) to evaluate the robustness of hybrid models, with a clear presentation of uncertainty analysis.