1st Edition

Methods and Applications of Autonomous Experimentation

Edited By Marcus Noack, Daniela Ushizima Copyright 2024
    444 Pages 118 Color & 8 B/W Illustrations
    by Chapman & Hall

    444 Pages 118 Color & 8 B/W Illustrations
    by Chapman & Hall

    Autonomous Experimentation is poised to revolutionize scientific experiments at advanced experimental facilities. Whereas previously, human experimenters were burdened with the laborious task of overseeing each measurement, recent advances in mathematics, machine learning and algorithms have alleviated this burden by enabling automated and intelligent decision-making, minimizing the need for human interference. Illustrating theoretical foundations and incorporating practitioners’ first-hand experiences, this book is a practical guide to successful Autonomous Experimentation.

    Despite the field’s growing potential, there exists numerous myths and misconceptions surrounding Autonomous Experimentation. Combining insights from theorists, machine-learning engineers and applied scientists, this book aims to lay the foundation for future research and widespread adoption within the scientific community.

    This book is particularly useful for members of the scientific community looking to improve their research methods but also contains additional insights for students and industry professionals interested in the future of the field.



    Chapter 1 Autonomous Experimentation in Practice
    Kevin G. Yager

    Chapter 2 A Friendly Mathematical Perspective on Autonomous Experimentation
    Marcus M. Noack

    Chapter 3 A Perspective on Machine Learning for Autonomous Experimentation
    Joshua Schrier and Alexander J. Norquist

    Chapter 4 Gaussian Processes
    Marcus M. Noack

    Chapter 5 Uncertainty Quantification
    Mark D. Risser and Marcus M. Noack

    Chapter 6 Surrogate Model Guided Optimization
    Juliane Mueller

    Chapter 7 Artificial Neural Networks
    Daniela Ushizima

    Chapter 8 NSLS2
    Philip M. Maffettone, Daniel B. Allan, Andi Barbour, Thomas A. Caswell, Dmitri Gavrilov, Marcus D. Handwell, Thomas Morris, Daniel Olds, Maksim Rakitin, Stuart I. Campbell and Bruce Ravel

    Chapter 9 Reinforcement Learning
    Yixuan Sun, Krishnan Raghavan and Prasanna Balaprakash

    Chapter 10 Applications of Autonomous Methods to Synchrotron X-ray Scattering and Diffraction Experiments
    Masafumi Fukuto, Yu-Chen Wiegart, Marcus M. Noack and Kevin G. Yager

    Chapter 11 Autonomous Infrared Absorption Spectroscopy
    Hoi-Ying Holman, Steven Lee, Liang Chen, Petrus H. Zwart and Marcus M. Noack

    Chapter 12 Autonomous Hyperspectral Scanning Tunneling Spectroscopy
    Antonio Rossi, Darian Smalley, Masahiro Ishigami, Eli Rotenberg, Alexander Weber-Barigoni and John C. Thomas

    Chapter 13 Autonomous Control and Analyses of Fabricated Ecosystems
    Trent R. Northern, Peter Andeer, Marcus M. Noack, Ptrus H. Zwart and Daniela Ushizima

    Chapter 14 Autonomous Neutron Experiments
    Martin Boehm, David E. Perryman, Alessio De Francesco, Luisa Scaccia, Alessandro Cunsolo, Tobias Weber, Yannick LeGoc and Paolo Mutti

    Chapter 15 Material Discovery in Poorly Explored High-Dimensional Targeted Spaces
    Suchismita Sarker and Apurva Mehta

    Chapter 16 Autonomous Optical Microscopy for Exploring Nucleation and Growth of DNA Crystals
    Aaron N. Michelson

    Chapter 17 Constratined Autonomous Modelin of Metal-Mineral Adsorption
    Elliot Chang, Linda Beverly and Haruko Wainwright

    Chapter 18 Physics-In-The-Loop
    Aaron Gilad Kusne

    Chapter 19 A Closed Loop of Diverse Disciplines
    Marucs M. Noack and Kevin G. Yager

    Chapter 20 Analysis of Raw Data
    Marcus M. Noack and Kevin G. Yager

    Chapter 21 Autonomous Intelligent Decision Making
    Marcus M. Noack and Kevin G. Yager

    Chapter 22 Data Infrastructure
    Marcus M. Noack and Kevin G. Yager




    Marcus M. Noack received his Ph.D. in applied mathematics from Oslo University, Norway. At Lawrence Berkeley National Laboratory, he is working on stochastic function approximation, optimization and uncertainty quantification, applied to Autonomous Experimentation.

    Daniela Ushizima, Ph.D. in physics from the University of Sao Paulo, Brazil after majoring in computer science, has been associated with Lawrence Berkeley National Laboratory since 2007, where she investigates machine learning algorithms applied to image processing. Her primary focus has been on developing computer vision software to automate scientific data analysis.