Book “Quantum Chemistry in the Age of Machine Learning”

The book “Quantum Chemistry in the Age of Machine Learning” guides aspiring beginners and specialists in this exciting field by covering topics ranging from basic concepts to comprehensive methodological details in machine learning, quantum chemistry, and their combinations in a single, interconnected resource. Each chapter comes with hands-on tutorials, codes, and other materials to deepen understanding of the topics. The book is a product of a massive collaborative effort of 65 authors bringing together their diverse expertise. It has been published on 16 September 2022.

Machine learning (ML) has emerged as an important tool for quantum chemistry (QC) and booming applications of ML in QC necessitate a single resource that can be used for both teaching and as a look-up reference for specialists. With this in mind, the book covers a wide variety of topics relevant to ML in QC: underlying concepts of machine learning and quantum chemistry, machine learning potentials and learning of other quantum chemical properties, machine learning-improved quantum chemical methods, analysis of Big Data from simulations, and materials design with machine learning. It also provides plenty of material for teaching and each chapter contains hands-on tutorials in the Case studies section.

The work on this book started in 2020 as an in-depth extension of my same-title Perspective providing a concise, bird-eye view of ML in QC. My biggest motivation to embark on such a big project was creating a textbook for teaching ML in QC courses and, indeed, many of my lecture notes and exercises turned out to be very useful when contributing to some of the chapters. Considering the broadness of topics, this project was obviously too big to accomplish by a single person within a reasonably short amount of time adequate for such a fast-paced field. I am very grateful to many excellent experts in their fields who enthusiastically rolled up their sleeves and created this book. Also, the contribution of the publisher’s team and all the people who peer-reviewed chapters, checked hands-on tutorials and provided suggestions and feedback was invaluable.

The book is accompanied with a companion site hosting links to repositories with programs, data, instructions, sample input, and output files required for hands-on tutorials (case studies) as well as any post-publication updates:

The table of content is below:

PrefacePavlo O. Dral
Part 1Introduction
1Very brief introduction to quantum chemistryXun Wu, Peifeng Su
2Density functional theoryHong Jiang, Huai-Yang Sun
3Semiempirical quantum mechanical methodsPavlo O. Dral, Jan Řezáč
4From small molecules to solid-state materials: A brief discourse on an example of carbon compoundsBili Chen, Leyuan Cui, Shuai Wang, Gang Fu
5Basics of dynamicsXinxin Zhong, Yi Zhao
6Machine learning: An overviewEugen Hruska, Fang Liu
7Unsupervised learningRose K. Cersonsky, Sandip De
8Neural networksPavlo O. Dral, Alexei Kananenka, Fuchun Ge, Bao-Xin Xue
9Kernel methodsMax Pinheiro Jr, Pavlo O. Dral
10Bayesian inferenceWei Liang, Hongsheng Dai
Part 2Machine learning potentials
11Potentials based on linear modelsGauthier Tallec, Gaétan Laurens, Owen Fresse–Colson, Julien Lam
12Neural network potentialsJinzhe Zeng, Liqun Cao, Tong Zhu
13Kernel method potentialsYi-Fan Hou, Pavlo O. Dral
14Constructing machine learning potentials with active learningCheng Shang, Zhi-Pan Liu
15Excited-state dynamics with machine learningLina Zhang, Arif Ullah, Max Pinheiro Jr, Mario Barbatti, Pavlo O. Dral
16Machine learning for vibrational spectroscopySergei Manzhos, Manabu Ihara, Tucker Carrington
17Molecular structure optimizations with Gaussian process regressionRoland Lindh, Ignacio Fernández Galván
Part 3Machine learning of quantum chemical properties
18Learning electron densitiesBruno Cuevas-Zuviría
19Learning dipole moments and polarizabilitiesYaolong Zhang, Jun Jiang, Bin Jiang
20Learning excited-state propertiesJulia Westermayr, Pavlo O. Dral, Philipp Marquetand
Part 4Machine learning-improved quantum chemical methods
21Learning from multiple quantum chemical methods: Δ-learning, transfer learning, co-kriging, and beyondPavlo O. Dral, Tetiana Zubatiuk, Bao-Xin Xue
22Data-driven acceleration of coupled-cluster and perturbation theory methodsGrier M. Jones, P. D. Varuna S. Pathirage, Konstantinos D. Vogiatzis
23Redesigning density functional theory with machine learningJiang Wu, Guanhua Chen, Jingchun Wang, Xiao Zheng
24Improving semiempirical quantum mechanical methods with machine learningPavlo O. Dral, Tetiana Zubatiuk
25Machine learning wavefunctionStefano Battaglia
Part 5Analysis of Big Data
26Analysis of nonadiabatic molecular dynamics trajectoriesYifei Zhu, Jiawei Peng, Hong Liu and Zhenggang Lan
27Design of organic materials with tailored optical properties: Predicting quantum-chemical polarizabilities and derived quantitiesGaurav Vishwakarma, Aditya Sonpal, Aatish Pradhan, Mojtaba Haghighatlari, Mohammad Atif Faiz Afzal, Johannes Hachmann

Link to the book “Quantum Chemistry in the Age of Machine Learning”:
Apply promo code ATR30 during checkout for 30% discount.

As an Editor and co-author of this book, I wish you happy reading!

Leave a Reply

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.