Artificial Intelligence in Earth Science. Best Practices and Fundamental Challenges

Table of Contents

1. Introduction of artificial intelligence in Earth sciences

2. Machine learning for snow cover mapping

3. AI for sea ice forecasting

4. Deep learning for ocean mesoscale eddy detection

5. Artificial intelligence for plant disease recognition

6. Spatiotemporal attention ConvLSTM networks for predicting and physically interpreting wildfire spread

7. AI for physics-inspired hydrology modeling

8. Theory of spatiotemporal deep analogs and their application to solar forecasting

9. AI for improving ozone forecasting

10. AI for monitoring power plant emissions from space

11. AI for shrubland identification and mapping

12. Explainable AI for understanding ML-derived vegetation products

13. Satellite image classification using quantum machine learning

14. Provenance in earth AI

15. AI ethics for earth sciences

Authors

Ziheng Sun Principal Investigator, Center for Spatial Information Science and Systems, George Mason University, USA. 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. Nicoleta Cristea Research scientist, Department of Civil and Environmental Engineering, University of Washington, USA. 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. Pablo Rivas Assistant Professor of Computer Science, Baylor University, USA. 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.