Applying Deep Learning in Mars Exploration: A Neural Network-based Study to Classify Martian Terrain Features

Sachin Lodhi, Sakshi Sakshi, Vinay Kukreja, Ankit Bansal

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The red planet has persisted in being the top destination for space exploration and has also fascinated researchers to experiment with frequently launched its dataset of images. NASA has launched various missions on the track of space expeditions to explore the surface and the environment of the potential life-sustaining planet. Among all the missions for capturing images of the Martian terrain, the HiRISE experiment has been successful in coming up with the best datasets featuring the surface of Mars. In this research study, the authors have targeted the classification of this high-quality image dataset produced as the outcome of the HiRISE using a deep learning model. The proposed model is convoluted and built with the help of neural network layers (neuron layers). Based on the classification, the authors were able to classify the images of 7 terrain features of Mars, namely Crater, Impact Ejecta, Bright Dune, Dark Dune, Slope Streak, Spider, and Swiss Cheese. And the classification accuracy achieved by the model is 94.8%.

Original languageEnglish
Title of host publication2022 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), ICRITO 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665474337
DOIs
StatePublished - 1 Jan 2022
Externally publishedYes
Event10th International Conference on Reliability, Infocom Technologies and Optimization ,Trends and Future Directions, ICRITO 2022 - Noida, India
Duration: 13 Oct 202214 Oct 2022

Publication series

Name2022 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), ICRITO 2022

Conference

Conference10th International Conference on Reliability, Infocom Technologies and Optimization ,Trends and Future Directions, ICRITO 2022
Country/TerritoryIndia
CityNoida
Period13/10/2214/10/22

Keywords

  • climate change
  • innovation
  • research and development
  • resource efficiency
  • science corporation agreements
  • technological progress

ASJC Scopus subject areas

  • Control and Optimization
  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Information Systems and Management

Fingerprint

Dive into the research topics of 'Applying Deep Learning in Mars Exploration: A Neural Network-based Study to Classify Martian Terrain Features'. Together they form a unique fingerprint.

Cite this