Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control

by Steven L. Brunton, J. Nathan Kutz

Data-driven discovery is revolutionizing the modeling, prediction, and control of complex systems. This textbook brings together machine learning, engineering mathematics, and mathematical physics to integrate modeling and control of dynamical systems with modern methods in data science. It highlights many of the recent advances in scientific computing that enable data-driven methods to be applied to a diverse range of complex systems, such as turbulence, the brain, climate, epidemiology, finance, robotics, and autonomy. Aimed at advanced undergraduate and beginning graduate students in the engineering and physical sciences, the text presents a range of topics and methods from introductory to state of the art.

Genres: Mathematics, Computer Science, Science, Physics, Research, Textbooks, Programming

489 pages, Kindle Edition

Published February 28, 2019

Reviews

[JC Perrin · Rating 5 out of 5]

This book is INSANELY cool. Brunton and Kutz build their way up from fundamental techniques of linear algebra, through almost every major aspect of classical control, to some of the cutting edge techniques of modern control (like SINDy which they've helped develop). And yet, though it touches on so many complex ideas, they manage to write in simple, understandable english. They center almost every new idea in examples or illustrations help illustrate the real-world meaning. And their explanations are written with such lucidity that concepts I had to prove to myself in grad school (like projecting functions into different bases) seem almost self-evident. I've used several system identification techniques they present (like Dynamic Mode Decomposition) to solve problems at work, and I see several more opportunities for direct applications of the stuff they discuss here.

For a taste of what's inside check out the book website -- databookuw dot com -- or Brunton's youtube channel. Also check out Brunton's lab website -- eigensteve dot com -- although the papers there are dense and are targeted at researchers.

[Oleksandr Nikitin · Rating 5 out of 5]

Finally, a book that bridges ML with control theory and dynamical systems (and a bit of chaos theory).
Well written, comprehensive overview of the field. Got quite a few insights and filled the gaps.

Also, I was totally surprised to find that dynamical systems research is nowhere near the 4th paradigm (data-intensive scientific discovery). I thought it's my Google-fu is failing me, but it seems there's really no (published) math yet that enables one to robustly identify, describe and simulate anything beyond simple quadratic or periodic processes :(

Now longing for something similar connecting dynamical systems to game theory, catastrophe theory, emergent behaviors, and multi-agent modeling.

[Marv · Rating 5 out of 5]

This work is a excellent book that adequately explains, what I believe, to be the future direction of technology. It explains the combining of machine learning with data mining to control complex physics and engineering problems with the use of algorithms discussed, by Brunton and Kutz. A fantastic engineering read.

[Denis · Rating 5 out of 5]

It feels like this is just the best book on the subject ever written. It makes seemingly difficult concepts look so obvious, which shows the highest level of understanding of the subject by the authors. And I just have a lot of gratitude to them for taking their time and writing this book.

[Claudio Noguera · Rating 3 out of 5]

Too technical for my liking, I'd like to have a longer book that is easier to read.
It is a reference book, not a book to learn while you read it.
However, the accompanying lectures available in YouTube and the book website with actual code are very useful

[Elise · Rating 5 out of 5]

Amazingly pedagogical! This book and the accompanying video lectures really kickstarted my understanding and passion for data-driven dynamical modelling and control topics. We need more teachers like Steve Brunton and Nathan Kutz!