Machine Learning for Planetary Science

Machine Learning for Planetary Science

Table of Contents:
Part I: Introduction to Machine Learning 1. Types of ML methods (supervised, unsupervised, semi-supervised; classification, regression) 2. Dealing with small labeled datasets (semi-supervised learning, active learning) 3. Selecting a methodology and evaluation metrics 4. Interpreting and explaining model behavior 5. Hyperparameter optimization and training neural networks Part II: Methods of machine learning 6. The new and unique challenges of planetary missions 7. Data acquisition (PDS nodes, etc.) and Data types, projections, processing, units, etc. Part III: Useful tools for machine learning projects in planetary science 8. The Python Spectral Analysis Tool (PySAT): A Powerful, Flexible, Preprocessing and Machine Learning Library and Interface 9. Getting data from the PDS, pre-processing, and labeling it Part IV: Case studies 10. Enhancing Spatial Resolution of Remotely Sensed Imagery Using Deep Learning and/or Data Restoration 11. Surface mapping via unsupervised learning and clustering of Mercury’s Visible–Near-Infrared reflectance spectra 12. Mapping Saturn using deep learning 13. Artificial Intelligence for Planetary Data Analytics - Computer Vision to Boost Detection and Analysis of Jupiter's White Ovals in Images Acquired by the Jiram Spectrometer

About the Author :
Joern Helbert has been a staff scientist at the German Aerospace Center since 2003 and is head of the “Planetary spectroscopy group”. He is an expert in planetary remote sensing using infrared techniques. He is involved in several space missions including BepiColombo, MarsExpress, VenusExpress, the NASA MESSENGER mission to Mercury and the JAXA Hayabusa 2 sample return mission. He is Co-Private Investigator of the MERTIS instrument on BepiColombo. Mario D’Amore has been a staff researcher at the Institute of Planetary Research of the German Aerospace Center (PF-DLR) since 2008.. He is an expert in data analysis, GIS spatial analysis and databases for scientific purposes. Currently, he is the Data Archive and Handling Manager for the MERTIS instrument on the BepiColombo mission at the PF-DLR. He was involved in ESA's Mars and Venus Express Mission as CoI, Data Archive Manager and Calibration Manager for the PFS experiment. Before that, he obtained a fellowship as Guest Scientist at PF-DLR focused on the development of remote sensing data interpretation algorithms, using the data acquired in the Planetary Emissivity Laboratory (PEL) at the PF-DLR. Michael Aye is a Research Associate at the Laboratory for Atmospheric and Space Physics, University of Colorado at Boulder. He has been or is currently involved with many missions, including NASA Dawn, Cassini, LRO, MRO, Maven and BepiColombo missions for instrument development, project management, calibration and data analysis. He is Co-Investigator on a NASA Research project and lead analyst on Citizen Science project “Planet Four”. He specializes in cameras, far IR calibration, and image and large data analyses. He is interested in pushing the consolidation of planetary python tools. Hannah Kerner is an assistant research professor at the University of Maryland in College Park, Maryland in the USA. Her research focuses on machine learning applications for planetary science, specifically novelty detection and change detection. She is a science team member for Mars Science Laboratory (MSL) Curiosity and is on the tactical operations team for the Mars Exploration Rover (MER) Opportunity. She has worked at Planet, a remote sensing company based in San Francisco, as well as NASA’s Jet Propulsion Laboratory, Goddard Space Flight Center, and Langley Research Center. She earned her B.S. in computer science at the University of North Carolina at Chapel Hill, where she conducted research in robot motion planning.

Review :
"Machine Learning for Planetary Science presents planetary scientists with a way to introduce machine learning into the research workflow as increasingly large nonlinear datasets are acquired from planetary exploration missions. The book explores research that leverages machine-learning methods to enhance our scientific understanding of planetary data and serves as a guide for selecting the right methods and tools for solving a variety of everyday problems in planetary science using machine learning. Illustrating ways to employ machine learning in practice with case studies, the book is clearly organized into four parts to provide thorough context and easy navigation. The book covers a range of issues, from data analysis on the ground to data analysis onboard a spacecraft, and from prioritization of novel or interesting observations to enhanced missions planning. This book is therefore a key resource for planetary scientists working in data analysis, missions planning, and scientific observation." --Lunar and Planetary Institutte