Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control (2nd Edition)

By Steven L. Brunton & J. Nathan Kutz

Data-Driven Science and Engineering, Second Edition, is a modern and highly influential textbook bridging machine learning, dynamical systems, and control theory. Published by Cambridge University Press, this book integrates mathematical foundations with computational tools for extracting models and insight from complex data.

The 2nd Edition expands coverage of neural networks, sparse identification methods (SINDy), Koopman operator theory, reduced-order modeling, and control applications. It is widely used in graduate engineering, applied mathematics, data science, and control systems programs.

What This Book Does

This book equips engineers and researchers with computational and analytical tools to model, predict, and control complex dynamical systems using data-driven methodologies.

Key Features of the 2nd Edition

• Integrated treatment of machine learning and dynamical systems
• Expanded neural network and deep learning coverage
• Sparse system identification (SINDy)
• Koopman operator theory applications
• Control-oriented data-driven modeling techniques

Who Should Use This Book?

• Graduate students in engineering and applied mathematics
• Researchers in machine learning and control systems
• Data scientists working with physical systems
• Robotics and dynamical systems engineers
• Academic and research libraries

Why It’s Essential

• Widely cited modern data-driven systems reference
• Bridges theory, computation, and application
• Supports interdisciplinary STEM programs
• Published by Cambridge University Press

A foundational guide to machine learning for dynamical systems and control.
Order today from BooksGoat and master modern data-driven engineering.

Product Details

• ISBN-13: 9781009098489
• Edition: 2nd
• Authors: Steven L. Brunton; J. Nathan Kutz
• Publisher: Cambridge University Press
• Format: Hardcover
• Condition: New
• Availability: In Stock
• Price: $— (Free Shipping)

Table of Contents (Highlights)

• Foundations of Data-Driven Modeling
• Linear Algebra and Dimensionality Reduction
• Machine Learning and Neural Networks
• Sparse Identification of Nonlinear Dynamics (SINDy)
• Koopman Operator Methods
• Control Applications and Reduced-Order Models

FAQs

• Is this suitable for graduate-level study?
  Yes. It is widely adopted in advanced engineering and applied math programs.
• Does it include practical computational tools?
  Yes. It integrates modeling techniques with computational implementation.
• Is it relevant to control systems and robotics?
  Yes. It connects machine learning with dynamical systems and control theory.