About MAI
Any intelligent fool can make things bigger, more complex, and more violent. It takes a touch of genius — and a lot of courage — to move in the opposite direction. -- E.F. Schumacher
@MAI we apply 1/3 rule as our guide:
(i)
exploring the frontiers of scientific disciplines to never lose our motivation
and to have a source of inspiration, (ii) actively contribute the development
of our
field of
expertise and (iii) further propagate this know-how with industrial
collaborations and mentoring
activities.
Our current research is centred around five themes: (i) clean combustion technologies, (ii) AI-augmented simulation of multi-scale
transport phenomena, (iii) theory of learning, (iv) AI-assisted scientific
visualization and (v) smart sensors & wearables for state monitoring.
AI-based model discovery for the waste separation processes in the "zero waste" cycle
Enhanced CO2 capture in
gas-liquid contact reactors
MCMC modeling of radiative heat transfer in multiphase flows
Early detection and preventive monitoring of stalling in turbochargers
Data-driven methods are changing the way we visualize, model, interpret and control complex systems. The landscape is diverse: developments in the measurement and modeling of multiphase flows and turbulence, product design, molecular engineering, energy systems and management, diagnosis/prognosis, process control are just a glimpse of what is on the horizon.
In the first lecture, you will build up the fundamental skills and gain experience in
developing intelligent solutions for model abstractions, pattern recognition in experimental/numerical datasets, optimization and process control. The course concludes with
an End-to-End Machine Learning Project. Second lecture, Advanced Topics, expores the details of the most recent applications
in data driven engineering Building upon the skills developed in the “Machine Learning
for Dynamical Systems” course, you will learn about complex model architectures
through different “themes”, with the objective of providing a deeper background and
capability to navigate through the recent developments in the field.
Both lecture include weekly software sessions in TensorFlow / PyTorch for hands-on
experience and is integrated with individual and group projects.
Lectures are offered every semester at KIT. You can access the lecture notes, codes, dedicated wiki page and example projects from here.
Dr.-Ing. Cihan Ates
Research Group Leader
Karthik Muthukumar
PhD Candidate
Joel Arweiler
PhD Candidate
Sebastian Nutto
Master Student
Andreas Eppler
Master Student
Oliver Resch
Master Student
Furkan Yurt
Student Assistant
Maximilian Enke
Student Assistant
Alumni
Master, Bachelor, HiWi
Are you interested in joining our research group and contributing to our
ongoing projects? We welcome motivated and talented individuals to join
our team and make a difference in the field of data driven engineering.
You can find the list of currently available positions from here. We look forward to receiving your application and potentially welcoming you to our team!
We are open to discussing potential collaborations with academic institutions, companies, and organizations that align with our research goals. If you are interested in collaborating with us, please don't hesitate to reach out. We look forward to hearing from you and exploring the possibilities for working together.
Dr. Cihan Ates
Institute of Thermal Turbomachinery
, Karlsruhe Institute of Technology
Campus Süd Geb. 30.60, Straße am Forum 6 , 76131 Karlsruhe
cihan.ates@kit.edu
created with
Website Builder .