Artificial Intelligence in Earth Science: Best Practices and Fundamental Challenges

The repo contains the source code, notebooks, and technical resources that assist students to read the book Artificial Intelligence in Earth Science.

Authors: Ziheng Sun, Nicoleta Cristea, Kehan Yang, Aji John, Sahara Ali, Yiyi Huang, Jianwu Wang, Edwin Goh, Annie Didier, Jinbo Wang, Jayme Garcia Arnal Barbedo, Arif Masrur, Manzhu Yu, Andrew Bennett, Weiming Hu, Guido Cervone, George Young, Ahmed Alnuaim (Alnaim), Didarul Islam, Michael J. Mahoney, Lucas K. Johnson, Colin M. Beier, Geetha Satya Mounika Ganji, Wai Hang Chow Lin, Olawale Ayoade, Pablo Rivas, Nurul Rafi, Amruta Kale, Xiaogang Ma, Christopher Thompson, Gissella Bejarano

Artificial Intelligence in Earth Science: Best Practices and Fundamental Challenges provides a comprehensive, step-by-step guide to AI workflows for solving problems in Earth Science. The book focuses on the most challenging problems in applying AI in Earth system sciences, such as training data preparation, model selection, hyperparameter tuning, model structure optimization, spatiotemporal generalization, transforming model results into products, and explaining trained models. In addition, it provides full-stack workflow tutorials to help walk readers through the whole process, regardless of previous AI experience. The book tackles the complexity of Earth system problems in AI engineering, fully guiding geoscientists who are planning to implement AI in their daily work.

Table of Contents

Chapter 1 - Introduction of artificial intelligence in Earth sciences - code

Explore the exciting intersection of artificial intelligence and Earth sciences, uncovering the transformative potential of AI in tackling complex environmental challenges.

Chapter 2 - Machine learning for snow cover mapping - code

Discover how machine learning techniques can be leveraged to accurately map and monitor snow cover, facilitating better understanding of snow dynamics and their implications.

Chapter 3 - AI for sea ice forecasting - code

Dive into the world of AI-driven sea ice forecasting, uncovering advanced techniques for predicting sea ice behavior and enhancing navigational safety in polar regions.

Chapter 4 - Deep learning for ocean mesoscale eddy detection - code

Explore the applications of deep learning in detecting and characterizing mesoscale eddies in the ocean, unraveling their significance in global ocean circulation.

Chapter 5 - Artificial intelligence for plant disease recognition - code

Delve into the realm of AI-based plant disease recognition, uncovering cutting-edge approaches for early detection and management of plant diseases to ensure crop health and productivity.

Chapter 6 - Spatiotemporal attention ConvLSTM networks for predicting and physically interpreting wildfire spread - code

Discover how spatiotemporal attention ConvLSTM networks can revolutionize wildfire spread prediction, enabling proactive measures for fire management and prevention.

Chapter 7 - AI for physics-inspired hydrology modeling - code

Explore the synergy of AI and physics in hydrology modeling, harnessing advanced techniques to simulate and understand complex hydrological processes for effective water resource management.

Chapter 8 - Theory of spatiotemporal deep analogs and their application to solar forecasting - code

Unveil the theory of spatiotemporal deep analogs and their remarkable applications in solar forecasting, facilitating improved renewable energy integration and management.

Chapter 9 - AI for improving ozone forecasting - code

Investigate the role of AI in enhancing ozone forecasting capabilities, enabling better understanding of air quality and supporting informed decision-making.

Chapter 10 - AI for monitoring power plant emissions from space - code

Explore how AI can be utilized to monitor and analyze power plant emissions from space, facilitating effective environmental management and mitigation strategies.

Chapter 11 - AI for shrubland identification and mapping - code

Uncover the potential of AI in identifying and mapping shrubland areas, providing valuable insights for ecological assessment and land management practices.

Chapter 12 - Explainable AI for understanding ML-derived vegetation products - code

Gain insights into explainable AI techniques for understanding machine learning-derived vegetation products, enabling reliable interpretation and validation of remote sensing data.

Chapter 13 - Satellite image classification using quantum machine learning - code

Discover the emerging field of quantum machine learning applied to satellite image classification, unraveling the potential for improved accuracy and efficiency in remote sensing tasks.

Chapter 14 - Provenance in Earth AI - code

Explore the significance of provenance in Earth AI, delving into techniques for ensuring transparency, reproducibility, and accountability in AI-driven Earth science workflows.

Chapter 15 - AI ethics for Earth sciences - code

Dive into the ethical dimensions of AI in Earth sciences, examining the challenges, implications, and guidelines for responsible and ethical use of AI technologies.

Click on the chapter titles to access the respective chapters and start an enlightening journey exploring the diverse applications of AI in Earth sciences!