Artificial Intelligence in Earth Science

Best Practices and Fundamental Challenges

1st Edition - April 26, 2023
Editors: Ziheng Sun, Nicoleta Cristea, Pablo Rivas
Language: English
Paperback ISBN:
9 7 8 - 0 - 3 2 3 - 9 1 7 3 7 - 7
eBook ISBN:
9 7 8 - 0 - 3 2 3 - 9 7 2 1 6 - 1

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… Read more

Purchase options

LIMITED OFFER

Save 50% on book bundles

Immediately download your ebook while waiting for your print delivery. No promo code is needed.

Institutional subscription on ScienceDirect

Request a sales quote

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.

Cover image
Title page
Table of Contents
Copyright
Contributors
Chapter 1: Introduction of artificial intelligence in Earth sciences
Abstract
1: Background and motivation
2: AI evolution in Earth sciences
3: Latest developments and challenges
4: Short-term and long-term expectations for AI
5: Future developments and how to adapt
6: Practical AI: From prototype to operation
7: Why do we write this book?
8: Learning goals and tasks
9: Assignments & open questions
References
Chapter 2: Machine learning for snow cover mapping
Abstract
1: Introduction
2: Machine learning tools and model
3: Data preparation
4: Model parameter tuning
5: Model training
6: Model performance evaluation
7: Conclusion
8: Assignment
9: Open questions
References
Chapter 3: AI for sea ice forecasting
Abstract
1: Introduction
2: Sea ice seasonal forecast
3: Sea ice data exploration
4: ML approaches for sea ice forecasting
5: Results and analysis
6: Discussion
7: Open questions
8: Assignments
References
Chapter 4: Deep learning for ocean mesoscale eddy detection
Abstract
Acknowledgments
1: Introduction
2: Chapter layout
3: Data preparation
4: Training and evaluating an eddy detection model
5: Discussion
6: Summary
7: Assignments
8: Open questions
References
Chapter 5: Artificial intelligence for plant disease recognition
Abstract
1: Introduction
2: Data retrieval and preparation
3: Step-by-step implementation
4: Experimental results and how to select a model
5: Discussion
6: Conclusion
7: Assignment
8: Open questions
References
Chapter 6: Spatiotemporal attention ConvLSTM networks for predicting and physically interpreting wildfire spread
Abstract
1: Introduction
2: Methodology
3: Earth AI workflow
4: Results
5: Conclusions
6: Assignment
7: Open questions
References
Chapter 7: AI for physics-inspired hydrology modeling
Abstract
1: Introduction and background
2: PyTorch and autodifferentiation
3: Extremely brief background on numerical optimization
4: Bringing things together: Solving ODEs inside of neural networks
5: Scaling up to a conceptual hydrologic model
6: Conclusions
References
Further reading
Chapter 8: Theory of spatiotemporal deep analogs and their application to solar forecasting
Abstract
1: Introduction
2: Research data
3: Methodology
4: Results and discussion
5: Final remarks
6: Assignment
7: Open questions
Appendix A: Deep learning layers and operators
Appendix B: Verification of extended analog search with GFS
Appendix C: Weather analog identification under a high irradiance regime
Appendix D: Model attribution
References
Chapter 9: AI for improving ozone forecasting
Abstract
1: Introduction
2: Background
3: Data collection
4: Dataset preparation
5: Machine learning
6: ML workflow management
7: Discussion
8: Conclusion
9: Assignment
10: Open questions
11: Lessons learned
References
Chapter 10: AI for monitoring power plant emissions from space
Abstract
1: Introduction
2: Background
3: Data collection
4: Preprocessing
5: Machine learning
6: Managing emission AI workflow in Geoweaver
7: Discussion
8: Summary
9: Assignment
10: Open questions
11: Lessons learned
References
Chapter 11: AI for shrubland identification and mapping
Abstract
1: Introduction
2: What you’ll learn
3: Background
4: Prerequisites
5: Model building
6: Discussion
7: Summary
8: Assignment
9: Open questions
References
Chapter 12: Explainable AI for understanding ML-derived vegetation products
Abstract
Acknowledgments
1: Introduction
2: Background
3: Prerequisites
4: Method & technique
5: Experiment & results
6: Summary
7: Assignment
8: Open questions
9: Lessons learned
References
Further reading
Chapter 13: Satellite image classification using quantum machine learning
Abstract
Acknowledgment
1: Introduction
2: Data
3: Applying QML on MODIS hyperspectral images
4: Conclusions
5: Assignments
6: Open questions
References
Chapter 14: Provenance in earth AI
Abstract
Acknowledgments
1: Introduction
2: Overview of relevant concepts in provenance, XAI, and TAI
3: Need for provenance in earth AI
4: Technical approaches
5: Discussion
6: Conclusions
7: Assignment
8: Open questions
References
Chapter 15: AI ethics for earth sciences
Abstract
1: Introduction
2: Prior work
3: Addressing ethical concerns during system design
4: Considerating algorithmic bias
5: Designing ethically driven automated systems
6: Assessing the impact of autonomous and intelligent systems on human well-being
7: Developing AI literacy, skills, and readiness
8: On documenting datasets for AI
9: On documenting AI models
10: Carbon emissions of earth AI models
11: Conclusions
12: Assignments
13: Open questions
References
Index

Ziheng Sun

Ziheng Sun is a Principal Investigator at the Center for Spatial Information Science and Systems, and a research assistant professor the Department of Geography and Geoinformation Science at George Mason University. He is a practitioner of using the latest technologies such as artificial intelligence and high-performance computing, to seek for answers to the questions in geoscience. He invented RSSI, a novel index for artificial object recognition from high resolution aerial images, and proposed parameterless automatic classification solution for reducing the parameter-tuning burden on scientists. Prof Sun has published over 50 papers in renowned journals in geoscience and has worked on several federal-funded projects to build geospatial cyberinfrastructure systems for better disseminating, processing, visualizing, and understanding spatial big data.

Affiliations and expertise

Principal Investigator, Center for Spatial Information Science and Systems, George Mason University, USA

Nicoleta Cristea

Nicoleta Cristea is a research scientist in the Department of Civil and Environmental Engineering at the University of Washington (UW), a research scientist with the UW Freshwater Initiative, and a data science fellow at the UW eScience Institute. Her current research focus is on modeling snow surface temperature and evaluating spatially distributed hydrologic models. Nicoleta is currently leading an NSF-funded project on mapping snow covered areas from Cubesat imagery using deep learning techniques.

Affiliations and expertise

Research scientist, Department of Civil and Environmental Engineering, University of Washington, USA

Pablo Rivas

Pablo Rivas is assistant professor of computer science at Baylor University where he teaches courses related to machine learning, deep learning, data mining, and theory. His research areas include deep machine learning and large-scale data mining in big data analytics, large-scale multidimensional multispectral signal analysis, statistical pattern recognition methods, image restoration, image analysis, intelligent software systems, and health-care imaging. Other research areas include applied mathematics, numerical optimization, swarm intelligence optimization, evolutionary algorithms, soft computing, fuzzy logic, neural networks, and neuro-fuzzy systems.

Affiliations and expertise

Assistant Professor of Computer Science, Baylor University, USA