Physics-Informed Neural Network

The video explores hybrid machine learning methods that combine physics-based models with machine learning techniques. It discusses various approaches to integrate these methods, including using residuals and constraints. A case study on predicting thermophysical properties is presented, demonstrating the effectiveness of adding constraints to improve model validation. The video also covers linear regression and neural networks, highlighting the impact of constraints on model performance.

Discuss the impact of overfitting in machine learning models as highlighted in the case study.

What methods were proposed to adjust the physics-based models using data?

How does the use of constraints affect the performance of machine learning models on validation data?

What are some examples of machine learning methods that can be used in conjunction with physics-based models?