Our Team 

Steve WaiChing Sun

JS Chen


Nikolas Vlassis

Lab Instructor

Qing Yin 

Lab Instructor

Kristen Susuki 

Lab Instructor

Karan Taneja

Lab Instructor

Course objectives

This course will be offered online to graduate students and researchers to introduce the practical data analytics, dimension reduction, and machine learning techniques, for a variety of science and engineering applications in materials, structures, and systems. This course is designed for the audience with a background in mechanics and/or applied physics. The course will provide an overview of four major categories of machine learning techniques (dimensional reduction of manifold data, geometric learning of graphs, manifold embedding, and deep reinforcement learning) and a data-driven model-free framework. Case studies will be used to demonstrate how these learning techniques have enhanced research and technology advancements. These application problems will include a data-driven model-free paradigm for complex material systems, reduced-order modeling of fracture and thermal fatigue analysis, geometric learning for polycrystal and granular systems, and reinforcement learning-enabled multiscale modeling for decision-making for design-of-experiments. Lecture materials and lab handouts will be provided before the short course.

Course Audience

Graduate students, researchers with an understanding of continuum mechanics. A course website will be set up for course materials and sample codes repository before the short course date.

Scientific/Technical Areas Covered/ Course Content

1. Thermodynamically Consistent Manifold learning enhanced data-driven modeling of path-dependent materials
2. Dimension reduction by manifold learning and autoencoders
3. Geometric learning for predicting path-dependent constitutive responses 
4. Representation learning for high-dimensional data with physics constraints 
5. Reduced-order hyper-reduction modeling of nonlinear materials 


30 July 2022, Eastern Standard Time  

8:00-8:30 AM EST - Opening remarks and logistics (Sun)

8:30-9:30 AM EST - Lecture 1: Graph-based learning and knowledge representation for solid mechanics  (Sun)

 9:30-9:45 AM EST - Break

 9:45-10:45 AM EST - Lecture 2: Manifold based learning and data-driven computing for nonlinear solid mechanics: dimension reduction and thermodynamics (Chen) 

10:45-11:00 AM EST - Break

11:00-12:30 PM EST - Lab Session 1: Artificial Neural Network for Prediction of Failure Envelope of Carbon/Epoxy Composites (UCSD Team)

31 July 2022, Eastern Standard Time  

8:00-9:00 AM EST -  Lecture 3: Deep reinforcement learning for adversarial training of constitutive laws (Sun)

9:00-9:15 AM EST - Break 

9:15-10:15 AM EST - Lecture 4:  Machine learning for digital twins: an example on musculoskeletal digital twin (Chen)

10:15-10:30 AM EST - Break  

10:30-12:00 PM EST - Lab Session 2:  Numerical experiments for worst-case scenario detections (Columbia) 


If you want to register, click to the link and fill out the registration form