Artificial Intelligence and Systems of the Earth is a book about the potential and capabilities of Artificial Intelligence and Machine Learning for studying the Earth. It aims to serve as an eye-opener on new avenues of scientific research that can be enabled by AI/ML. This is not meant to be a "how to" book but is written to answer the question "what if". It explains how these tools are currently being applied, and the new opportunities they have opened. Through many examples and application ideas from outside the Earth Sciences, the book discusses some of the most prevalent types of AI in current use, the future of AI hardware, and how AI/ML bring about change.
Features
- Provides accessible and compact coverage on the many uses AI in Earth Science.
- Covers AI, Deep Learning and causal modelling concepts in an easy-to-understand language.
- Includes descriptions of computer hardware for AI, and where it is headed.
- Contains practical examples that students and practitioners can apply in their studies and projects.
- Offers a companion website with regularly updated content.
This book is an excellent resource for researchers, academics, graduate, and senior undergraduate students in Earth Science and Environmental Science and Engineering, who wish to learn how Artificial Intelligence and Machine Learning can benefit them, its potential applications and capabilities.
1. Introduction. 2. AI refresher. 3. Current and future applications of AI in Earth-related sciences. 4. AI and challenges in Earth-related sciences. 5. AI hardware and quantum computing. 6. Why believe AI? The role of machine learning in science. 7. Generative AI. 8. Causal models: AI that asks ‘why’ and ‘what if’. 9. Conclusion.
Biography
Michel Speiser is Chief Data Scientist at the International Centre for Earth Simulation (ICES Foundation) in Geneva, Switzerland. He strives to bring the advantages of AI and Machine Learning to bear on Earth Systems Modeling, Simulation & Visualization. He spent over six years at IBM Research, pushing the limits of data science, and unlocking the value hidden in large, complex data, drawing on techniques in probabilistic and statistical modeling, Machine Learning and Data Mining, and developing new tools and methods as needed. Michel holds a PhD in Information Systems and Operations Research (ETH Zurich), and Master’s degrees in Computer Science (EPFL), Complex Systems (Chalmers University of Technology), and Mathematical Sciences (EPFL).
