Increase the exploitation of mars satellite images via deep learning techniques

Mariam AlMarzooqi, Srikanth Bezawada, Asayel AlNaqbi, Elfadil A. Mohamed, Aysha AlMheiri, Nazar Zaki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Mars is the fourth planet from the sun and the second smallest planet in the solar system after Mercury. Like Earth, Mars has a range of surface features such as valleys, deserts, and polar ice caps. Scientists around the globe have developed a specific interest in the terrain and climate of Mars because it is believed to have the potential to host life. To assist scientists to discover past or present life on Mars, we developed machine learning models (based on deep learning) to analyze the satellite images received from the Red Planet. The models automatically eliminated satellite images that were of a low quality and subsequently classified the high-quality images based on climate/environmental conditions. The models were tested on sample datasets and demonstrated the ability to achieve considerable accuracy. We also integrated additional functionality to convert two-dimensional (2D) satellite images into an informative (3D) format for better analysis and exploration. Furthermore, the solution was integrated into a mobile application that can be used by scientists and members of the public who are interested in space science.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Robotics, Control and Automation Engineering, RCAE 2018 and 2018 International Conference on Advanced Mechanical and Electrical Engineering, AMEE 2018
PublisherAssociation for Computing Machinery
Pages171-175
Number of pages5
ISBN (Electronic)9781450361026
DOIs
Publication statusPublished - Dec 26 2018
Event2018 International Conference on Robotics, Control and Automation Engineering, RCAE 2018 - Beijing, China
Duration: Dec 26 2018Dec 28 2018

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2018 International Conference on Robotics, Control and Automation Engineering, RCAE 2018
Country/TerritoryChina
CityBeijing
Period12/26/1812/28/18

Keywords

  • 3D images
  • Deep learning
  • Mars
  • NIMA
  • Satellite images
  • Space science

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Increase the exploitation of mars satellite images via deep learning techniques'. Together they form a unique fingerprint.

Cite this