Machine Learning in Earth Observation Operations: A review

Paper number

IAC-21,B1,4,4,x64496

Author

Mr. Pablo Miralles, France, GTD

Coauthor

Ms. Nitya Jagadam, India, Space Generation Advisory Council (SGAC)

Coauthor

Ms. Prerna Baranwal, India, Birla Institute of Technology and Science(BITS)

Coauthor

Mr. Bhavin Faldu, India, Space Generation Advisory Council (SGAC)

Coauthor

Mr. Daniel Wischert, Germany, Space Generation Advisory Council (SGAC)

Coauthor

Ms. Daria Stepanova, Germany, German Orbital Systems GmbH

Coauthor

Ms. Ruchita Abhang, India, University of Pune

Coauthor

Mr. Sahil Bhatia, India, University of Petroleum and Energy Studies

Coauthor

Mr. Sebastien Bonnart, United States, Space Generation Advisory Council (SGAC)

Coauthor

Ms. Ishita Bhatnagar, India, Birla Institute of Technology and Science(BITS)

Coauthor

Ms. Beenish Batul, Pakistan, University of Management and Technology (UMT)

Coauthor

Ms. Pallavi Prasad, Ireland, Space Generation Advisory Council (SGAC)

Coauthor

Mr. Héctor Ortega-González, Spain, Space Generation Advisory Council (SGAC)

Coauthor

Mr. Harrish Joseph, Italy

Coauthor

Mr. Harshal More, Italy, Sapienza University of Rome

Coauthor

Ms. Sondes Morchedi, Italy, Space Generation Advisory Council (SGAC)

Coauthor

Mr. Aman Kumar Panda, India, University of Petroleum and Energy Studies

Coauthor

Dr. Antonio Scannapieco, Austria, Space Generation Advisory Council (SGAC)

Coauthor

Mr. Marco Zaccaria Di Fraia, United Kingdom, Cranfield University, UK

Year

2021

Abstract

Analysis of down-linked satellite imagery has undeniably benefited greatly from the ongoing Machine Learning revolution. Other aspects of the Earth Observation industry, despite being less prone to an extensive application of ML, are also following this trend. This work aims at presenting - in the form of a review of Machine Learning applied to Earth Observation Operations - such applications, the existing use cases, potential opportunities and pitfalls, and perceived gaps in research. A wide range of topics are discussed including mission planning, diagnosis, prognosis, and repair of faults, optimization of telecommunications, enhanced GNC, on-board image processing, and usage of Machine Learning models within platforms with limited compute and power capabilities. The review tackles all on-board and off-board applications of machine learning to earth observation with one notable exception: it omits all post-processing of payload data on the ground, a topic that has been studied extensively by past authors. This research was produced by a team of volunteers from the Small Satellite Project Group of the Space Generation Advisory Council.

Abstract document

IAC-21,B1,4,4,x64496.brief.pdf

Manuscript document

IAC-21,B1,4,4,x64496.pdf (🔒 authorized access only).

To get the manuscript, please contact IAF Secretariat.