/print("Welcome!")

Mechanical, chemical, aerospace, civil, and other engineers — this is your place to build up your skills with AI/ML, specific to engineering domains. There are tons of generic resources, but when you filter out only those that focus on our engineering problems, only a fraction remain. After writing a book on this topic, I decided to follow-up with a Substack page.

Sample posts:

• October 21st: Job Postings for AI/ML in Engineering

• Library for Data-Driven Physics Simulation Lectures (Free, on-demand)

• Install-Free Code Tutorial: PINNs in turbulent flow

• Promising AI Foundation Models in Science: Examples with Code and Data

Share

The mantra I strive to sustain for my newsletter is to ‘read what I read - code what I code’. I love applying ai and machine learning to engineering and scientific simulation, and as well on physics measurement and testing data.

My job at Siemens is AI/ML tech specialist for our portfolio of engineering software, and I initially thought I could be better suited in my technical activities by trying to read more.

So, my 2025 challenge emerges— read 1,000 papers on AI/ML for mechanical & aerospace engineering and blog about it along the way here on Substack. Literature reviews, code, tutorials/guides, etc.